agentsclimarketplace

Context & AI engineering

25,745 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Llm models

    VRIL-LABS/skill-jam/skills/ai-ml/skills-main/skills-main/tools/llm/llm-models Skill

    no license2★ repo

    Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative

  • Agent browser

    VRIL-LABS/skill-jam/skills/ai-ml/skills-main/skills-main/tools/utilities/agent-browser Skill

    no license2★ repo

    Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

    The same file is in 3 other repositories

  • Agent ui

    VRIL-LABS/skill-jam/skills/ai-ml/skills-main/skills-main/ui/agent-ui Skill

    no license2★ repo

    Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop

    The same file is in 4 other repositories

  • Tools ui

    VRIL-LABS/skill-jam/skills/ai-ml/skills-main/skills-main/ui/tools-ui Skill

    no license2★ repo

    Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending

    The same file is in 4 other repositories

  • Vercel labs agent browser agent browser 1.0.3

    VRIL-LABS/skill-jam/skills/browser-automation/vercel-labs-agent-browser-agent-browser-1.0.3 Skill

    no license2★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

    The same file is in 1 other repository

  • Kubernetes orchestrator

    VRIL-LABS/skill-jam/skills/core-collections/new-skills-2026/devops-infrastructure/kubernetes-orchestrator Skill

    no license2★ repo

    Orchestrate Kubernetes clusters and workloads — deployment management, resource configuration, and cluster operations. Use when deploying applications to K8s, troubleshooting pod issues, scaling workloads, configuring ingress and services, managing namespaces, or setting up cluster autoscaling and resource quotas.

  • Multi cloud orchestrator

    VRIL-LABS/skill-jam/skills/core-collections/new-skills-2026/devops-infrastructure/multi-cloud-orchestrator Skill

    no license2★ repo

    Orchestrate resources across multiple cloud providers — unified management and deployment. Use when managing multi-cloud infrastructure, avoiding vendor lock-in, or implementing cloud-agnostic solutions.

  • Memory profiler

    VRIL-LABS/skill-jam/skills/core-collections/new-skills-2026/performance-optimization/memory-profiler Skill

    no license2★ repo

    Profile memory usage — leak detection and optimization. Use when investigating memory issues, optimizing memory, or finding leaks.

  • Agent readiness

    VRIL-LABS/skill-jam/skills/core-collections/spellbook-master/spellbook-master/skills/agent-readiness Skill

    no license2★ repo

    Assess and improve codebase readiness for AI coding agents. Dispatches parallel subagents to evaluate style, testing, docs, architecture, CI, observability, security, and dev environment. Produces a scored report with prioritized remediation. Then executes the highest-impact fixes. Use when: "agent readiness", "is this codebase agent-ready", "readiness report", "make this codebase agent-friendly", "agent-ready assessment", "readiness audit", "prepare for agents". Trigger: /agent-readiness, /readiness.

  • Harness

    VRIL-LABS/skill-jam/skills/core-collections/spellbook-master/spellbook-master/skills/harness Skill

    no license2★ repo

    Build, maintain, evaluate, and optimize the agent harness — skills, agents, hooks, CLAUDE.md, AGENTS.md, and enforcement infrastructure. Use when: "create a skill", "update skill", "improve the harness", "sync skills", "eval skill", "lint skill", "tune the harness", "add skill", "remove skill", "convert agent to skill". Trigger: /harness, /focus, /skill, /primitive.

  • Inference sh skills agent tools 1.0.2

    VRIL-LABS/skill-jam/skills/dev-tools/inference-sh-skills-agent-tools-1.0.2 Skill

    no license2★ repo

    Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

    The same file is in 4 other repositories

  • Dimillian skills ios debugger agent 1.0.2

    VRIL-LABS/skill-jam/skills/ios-mobile/dimillian-skills-ios-debugger-agent-1.0.2 Skill

    no license2★ repo

    Use XcodeBuildMCP to build, run, launch, and debug the current iOS project on a booted simulator. Trigger when asked to run an iOS app, interact with the simulator UI, inspect on-screen state, capture logs/console output, or diagnose runtime behavior using XcodeBuildMCP tools.

    The same file is in 4 other repositories

  • Neversight skills feed non linear 1.0.1

    VRIL-LABS/skill-jam/skills/other/neversight-skills_feed-non-linear-1.0.1 Skill

    no license2★ repo

    Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.

  • Neversight skills feed arxiv mcp 2.0.0

    VRIL-LABS/skill-jam/skills/search-research/neversight-skills_feed-arxiv-mcp-2.0.0 Skill

    no license2★ repo

    Search and retrieve academic papers from arXiv.org using WebFetch and Exa. No MCP server required - uses existing tools to access arXiv API directly.

  • Openclaw skills prompt guard 2.6.0

    VRIL-LABS/skill-jam/skills/security/openclaw-skills-prompt-guard-2.6.0 Skill

    no license2★ repo

    Advanced prompt injection defense system for Clawdbot with HiveFence network integration. Protects against direct/indirect injection attacks in group chats with multi-language detection (EN/KO/JA/ZH), severity scoring, automatic logging, and configurable security policies. Connects to the distributed HiveFence threat intelligence network for collective defense.

  • Skill builder

    VRIL-LABS/skill-jam/skills/skill-builder Skill

    no license2★ repo

    Deep-research-backed SKILL.md authoring guide exclusively by VRIL LABS. Instructs agents on how to design, structure, write, and validate flawlessly optimal SKILL.md files that conform to the Agent Skills open format and perform at the highest level across Claude Code, GitHub Copilot, Cursor, Codex CLI, Windsurf, and any Skills CLI-compatible agent runtime. Invoke when asked to create a new skill, write a SKILL.md file, audit an existing skill for quality, or understand best practices for skill specification authoring.

  • Cis benchmark audit

    vahagn-madatyan/netsec-skills-suite/skills/cis-benchmark-audit Skill

    2★ repo

    CIS benchmark compliance assessment for network infrastructure devices. Maps device configuration against CIS benchmark controls organized by Management Plane, Control Plane, and Data Plane categories across Cisco IOS, PAN-OS, JunOS, and Check Point platforms. References control IDs for traceability without reproducing copyrighted benchmark content.

    The same file is in 1 other repository

  • Agent browser

    t4sh/dotfiles/agents/skills/agent-browser Skill

    no license2★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

    The same file is in 2 other repositories

  • Agent memory

    t4sh/dotfiles/agents/skills/agent-memory Skill

    no license2★ repo

    Cross-interface persistent memory for project context, decisions, conventions, and session handoffs. Use when the user asks to "manage project memory", "initialize .agent-memory", "migrate memory", "build memory from docs", "save session learnings", "sync memory", "run memory maintenance", "check memory status", or mentions persistent memory across Claude Code, Cursor, VS Code, Craft Agent, or other file-reading agents.

  • Claude handoff

    t4sh/dotfiles/agents/skills/claude-handoff Skill

    no license2★ repo

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    The same file is in 5 other repositories

  • Design handoff

    t4sh/dotfiles/agents/skills/design-handoff Skill

    no license2★ repo

    Generate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interaction states, responsive breakpoints, edge cases, and animation details.

    The same file is in 3 other repositories

  • Git guardrails claude code

    t4sh/dotfiles/agents/skills/git-guardrails-claude-code Skill

    no license2★ repo

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

    The same file is in 18 other repositories

  • Gpt taste

    t4sh/dotfiles/agents/skills/gpt-taste Skill

    no license2★ repo

    Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

    The same file is in 13 other repositories

  • Handoff

    t4sh/dotfiles/agents/skills/handoff Skill

    no license2★ repo

    Compact the current conversation into a handoff document for another agent to pick up.

    The same file is in 11 other repositories

  • Init rulebook

    t4sh/dotfiles/agents/skills/init-rulebook Skill

    no license2★ repo

    Load the user-level agent rulebook — an `~/.agents/AGENTS.md` index plus every referenced `rules/*.md` — so one consistent, portable baseline applies across any agent app (Claude Code, Codex, Conductor, Copilot, Craft-Agents,Cursor, OpenCode etc.). Re-run after context compaction to rehydrate. Triggers: init rulebook, reload rulebook, load user-level agent rules.

  • Paseo handoff

    t4sh/dotfiles/agents/skills/paseo-handoff Skill

    no license2★ repo

    Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent.

  • Skill architect

    t4sh/dotfiles/agents/skills/skill-architect Skill

    no license2★ repo

    Architect and audit portable agent skills for retrieval, predictability, progressive disclosure, evals, and repository gates. Use when the user asks to "create a skill", "author a skill", "improve a skill", "review a skill", "refactor a skill", "compare skill rubrics", "distill a skill from sessions", "reconcile skill plans", or "teach skill authoring"; when paths include `skills/<name>/SKILL.md`, `references/*.md`, helper scripts, evals, lockfiles, security manifests, or vendor adapters; or when mentions include skill-creator, Skill Development, skills.sh, trigger descriptions, completion criteria, leading words, or model/user invocation.

  • Skill creator

    t4sh/dotfiles/agents/skills/skill-creator Skill

    no license2★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 3 other repositories

  • Meta prompt

    GlamgarOnDiscord/claude-saas-blueprint/.claude/skills/meta-prompt Skill

    2★ repo

    Métaprompt Creator — Génère des skills, rules, hooks et prompts optimisés.

  • Claude code

    jacob-balslev/skills/skills/agent-ops/claude-code Skill

    2★ repo

    Use when deciding whether to run a task in the Claude Code agent harness, when scoping work to its native capabilities (skills, hooks, subagents, MCP, plan mode, 1M-context Opus, background tasks, slash commands), or when choosing Claude Code versus a different harness (Codex, OpenCode, Copilot) for a given piece of work. Covers what the harness is good at, the extensibility stack and when each layer earns its keep, and the decision boundaries against rival harnesses. Do NOT use for writing Anthropic SDK / API code (use `claude-api`), for choosing which Claude MODEL to route a task to versus GPT (use `gpt-5-5`), or for designing a generic autonomous agent loop (use `autonomous-loop-patterns`).

  • Claude haiku

    jacob-balslev/skills/skills/agent-ops/claude-haiku Skill

    2★ repo

    Use when deciding whether to route a task to the fast/cheap tier (Claude Haiku) — transcription, polling, format conversion, structured-output slot-filling, small-diff review, high-volume low-latency work — and where the boundary is that should escalate to Sonnet/Opus. Covers the cost/latency floor, the 200K context ceiling (vs the upper tiers' 1M), the absence of the effort knob, the separate rate-limit pool, and when to drop below Haiku to a script. Do NOT use for ordinary multi-step feature work (use claude-sonnet), the hardest reasoning (use claude-opus), loop design (use autonomous-loop-patterns), or Claude API request syntax (read the claude-api reference).

  • Claude opus

    jacob-balslev/skills/skills/agent-ops/claude-opus Skill

    2★ repo

    Use when deciding whether to route a task to Anthropic's frontier reasoning tier (Claude Opus) — architecture, multi-file synthesis, hard debugging, security reasoning, long-horizon agentic planning — and when NOT to (mechanical work belongs on a cheaper tier). Covers the Opus capability profile: 1M-token context, the cost/latency premium, adaptive thinking, the Opus-only effort ceiling (xhigh/max), task budgets, prompt-caching minimums, and high-resolution vision. Do NOT use for picking the balanced implementation tier (use claude-sonnet), the fast/cheap tier (use claude-haiku), designing the loop the model runs inside (use autonomous-loop-patterns), or for Claude API request syntax (read the claude-api reference).

  • Claude sonnet

    jacob-balslev/skills/skills/agent-ops/claude-sonnet Skill

    2★ repo

    Use when deciding whether to route a task to the balanced implementation tier (Claude Sonnet) — feature work, bug fixes, test writing, multi-step code — as the default lane that is cheaper/faster than the frontier tier and more capable than the fast tier. Covers the cost/quality tradeoff vs Opus and Haiku, the shared 1M context window, effort behavior, and the 1M-context subscription billing caveat. Do NOT use for the hardest reasoning/architecture/security work (use claude-opus), high-volume mechanical or low-latency work (use claude-haiku), loop design (use autonomous-loop-patterns), or Claude API request syntax (read the claude-api reference).

  • Codex

    jacob-balslev/skills/skills/agent-ops/codex Skill

    2★ repo

    Use when deciding whether to run a task in the Codex CLI agent harness (which drives a frontier GPT model), when scoping work to its native capabilities (resumable `codex exec resume` sessions, non-interactive `exec` stdout-piping, in-process dispatch, `/permissions` sandbox modes, MCP, on-demand subagents, the `/review` code-review agent), or when choosing Codex versus the Claude Code harness for a piece of work — and when avoiding its known failure modes (non-autonomous subagents, Full-Access network reach, cold-one-shot context loss). Do NOT use for routing a task to the GPT MODEL versus Claude (use `gpt-5-5`), for the Claude Code harness decision (use `claude-code`), or for designing a generic resumable agent loop (use `autonomous-loop-patterns`).

  • Context engineering

    jacob-balslev/skills/skills/agent-ops/context-engineering Skill

    2★ repo

    Use when designing what information reaches an LLM agent before it reasons — system prompt, persistent memory, always-loaded rules, injected skills, and the user prompt — or when diagnosing why an agent produced a wrong answer despite a clear instruction. Covers the four context failure modes (missing, stale, wrong, overwhelming), the five-layer context stack, four context quality metrics (injection precision and recall, utilization, freshness), the Frequent Intentional Compaction (FIC) protocol, subagent delegation for context-heavy work, and the failure-mode decision tree. Do NOT use for prompt wording (use `prompt-craft`), authoring a new SKILL.md (use `skill-scaffold`), or deciding which skill the router activates for a given query (use `skill-router`).

  • Context graph

    jacob-balslev/skills/skills/agent-ops/context-graph Skill

    2★ repo

    Use when designing or auditing the multi-graph context architecture of an AI-coding workspace: skill graph, document routing graph, memory index, script registry, and the cross-graph edges between them. Covers edge typing, orphan detection, connectivity health, deterministic graph synthesis signals, change-propagation checks, and drift or hub-and-spoke anti-patterns. Do NOT use for authoring one SKILL.md (use `skill-scaffold`), validating one skill (use `skill-infrastructure`), live routing decisions (use `skill-router`), context-window budgeting (use `context-window`), or session load/drop choices (use `context-management`).

  • Context management

    jacob-balslev/skills/skills/agent-ops/context-management Skill

    2★ repo

    Use when deciding what to load into an active agent session, recovering from context drift, preparing compaction or restart, distilling raw inputs into a working summary, or writing a handoff another agent can resume quickly. Covers intake triage, the active-context contract, the six-step context-management loop, working-set shaping, evidence capsules and observation masking, just-in-time handle-before-payload loading, prompt-caching alignment, context-rot defenses, drift signals and reset, the runtime-primitives boundary, compaction-ready handoffs, and selective rebuild after context loss. Do NOT use for token math (use `context-window`), prompt wording (use `prompt-craft`), persistent memory curation, or multi-graph context architecture (use `context-graph`).

  • Context window

    jacob-balslev/skills/skills/agent-ops/context-window Skill

    2★ repo

    Use when allocating context-window budget across system, skill-injection, working, and output zones; monitoring context health; deciding when to compact; preserving state before compaction; recovering after compaction; or choosing strategies for 1M, 200K, or 128K context windows. Covers zone budgets, practical model-budget tables, the 80% compaction rule, pre/post-compact protocols, persistence hierarchy, operation token costs, and token-reduction techniques. Do NOT use for deciding what information belongs in the working set (use `context-management`), prompt design (use `prompt-craft`), graph architecture (use `context-graph`), or memory curation.

  • Gemini pro

    jacob-balslev/skills/skills/agent-ops/gemini-pro Skill

    2★ repo

    Use when deciding whether to route a task to Google's Gemini Pro frontier model (current Gemini 3.1 Pro generation, moving to Gemini 3.5 Pro) instead of Claude Opus or GPT-5 — especially for very-large-context reasoning (1M-token input), whole-codebase or long-document analysis, native multimodal input (audio/video/PDF/image in one call), or capability-per-dollar at the frontier. Covers the context window, the 200K context-tier pricing cliff, multimodal support, and the per-lane comparison against Claude Opus / GPT-5. Do NOT use for choosing the cheap/fast tier (use `gemini-flash`), for general agent-system architecture (use `agent-engineering`), or for dispatching among local skills (use `skill-router`).

  • Github copilot

    jacob-balslev/skills/skills/agent-ops/github-copilot Skill

    2★ repo

    Use when deciding whether to spend GitHub Copilot's metered budget on a task (its premium-request / post-June-2026 AI-credit model, where 1 credit = $0.01 and cost = tokens × per-model rate), what Copilot is good at vs expensive at, which plan allowance (Pro 300 / Pro+ 1500, no rollover) applies, and when a cheaper or free lane should take the work instead. Covers the June 1 2026 shift from premium-request multipliers to usage-based token billing, the always-free completions/next-edit surface, and the IDE-native frontier-model lane. Do NOT use for choosing or operating the OpenCode runtime (use `opencode`), for picking a specific free model (use `opencode-free-models`), or for authoring an agent loop (use `autonomous-loop-patterns`).

  • Gpt 5 5

    jacob-balslev/skills/skills/agent-ops/gpt-5-5 Skill

    2★ repo

    Use when deciding whether to route a task to OpenAI's GPT-5.5 frontier model versus Claude Opus or Sonnet — picking the model lane for infrastructure scripts, CI pipelines, concrete implementation, analytical code review, security review, or CLI/terminal-heavy work, and weighing GPT-5.5's context window, pricing, and per-benchmark strengths against the Claude tiers for the same task. Covers the decision-useful capability and pricing facts, and the boundary against the Claude routing skills. Do NOT use for running the GPT model through a harness (use `codex`), for choosing among the Claude tiers themselves (use `claude-opus` / `claude-sonnet`), or for routing among local skills at request time (use `skill-router`).

  • Opencode free models

    jacob-balslev/skills/skills/agent-ops/opencode-free-models Skill

    2★ repo

    Use when deciding WHICH free or cheap agent model to route a piece of work to (e.g. MiniMax M3 Free, NVIDIA Nemotron, GLM, GPT-5 Nano, or another OpenCode Zen free-tier model), what each is good at, where its quality ceiling sits, and when to escalate the same work to a frontier model instead. Covers cost-routing: matching deterministic/mechanical/high-volume work to the cheapest model that clears its bar, and the hard rule that quality-creating and quality-judging work never goes to a free/cheap model. Do NOT use for choosing or operating the OpenCode runtime itself (use `opencode`), for authoring the agent loop (use `autonomous-loop-patterns`), or for GitHub Copilot premium-request budgeting (use `github-copilot`).

  • Opencode

    jacob-balslev/skills/skills/agent-ops/opencode Skill

    2★ repo

    Use when deciding whether to run a task on the OpenCode agent runtime (the open-source, provider-agnostic coding agent — usable as a terminal TUI, a non-interactive `opencode run` CLI, an IDE bridge via ACP, a desktop app (beta), a web UI, or a headless `opencode serve` server), how to invoke it non-interactively, how to pick a `provider/model` string, or how OpenCode differs from Claude Code and Codex. Covers its 75+-provider model routing, the OpenCode Zen curated/free model service and the separate OpenCode Go subscription lane, model-selection and config-source (8-layer) precedence, the `--format json` JSONL event stream, the full CLI command surface (serve/web/attach/acp/session/stats/export/import/github/pr/plugin/mcp/db/debug), built-in build/plan agents and LSP code intelligence, permissions vs provider policies, native Agent Skills / MCP / references / commands extension layers, local models, and scripting/automation. Do NOT use when choosing WHICH free model to route specific work to (use `opencode-free-models`), when the runtime is already chosen and you only need to write the agent loop (use `autonomous-loop-patterns`), or for GitHub Copilot's premium-request economics (use `github-copilot`).

  • Eval driven development

    jacob-balslev/skills/skills/ai-engineering/eval-driven-development Skill

    2★ repo

    Use when reasoning about building language-model-integrated systems by writing evaluations before and alongside the system: the statistical (not binary) nature of LLM evals, the five primitives (dataset, evaluation function, aggregation, iteration loop, regression budget), the judgment-mechanism taxonomy (programmatic, model-graded, human-graded, preference comparison, trace/hybrid), the eval-surface stack (final response, trajectory/tool-use, retrieval/RAG, safety, side effects, cost/latency), continuous evals and model-upgrade gates, the statistical-significance discipline (paired tests, McNemar's test, bootstrap CI on the delta, minimum-detectable-effect, clustered standard errors), trajectory-vs-final-output evaluation for multi-step agents, judge calibration and bias, Goodhart's Law and suite saturation, benchmark contamination and eval-awareness, cost-aware regression budgets, the difference between system-specific evals and canonical benchmarks (MMLU, HumanEval, BIG-bench, GAIA), and the offline-eval-vs-production-telemetry distinction with its graded rollout spectrum. Do NOT use for deterministic unit testing (use testing-strategy), production monitoring (use evaluation or error-tracking), general-software TDD (use testing-strategy), or the construction of individual eval rubrics and task sets (outside this skill; construction belongs in task-specific eval artifacts, while this skill owns the iteration discipline).

  • Prompt craft

    jacob-balslev/skills/skills/ai-engineering/prompt-craft Skill

    2★ repo

    Use when writing, tightening, evaluating, or repairing an LLM prompt or reusable prompt template for completion, agent dispatch, grading, structured extraction, tool use, or prompt-engineered workflows. Covers instruction hierarchy, message roles, context placement, few-shot examples, structured output, positive constraints, reasoning guidance, prompt-injection resistance, provider differences, and eval-driven iteration. Do NOT use for whole context-system design (use context-engineering), eval dataset or grader design (use eval-driven-development), reviewing generated code (use code-review), authoring SKILL.md files (use skill-scaffold), choosing which skill or agent should activate (use skill-router), or root-causing a deployed failure after outputs already exist (use debugging).

  • Prompt injection defense

    jacob-balslev/skills/skills/ai-engineering/prompt-injection-defense Skill

    2★ repo

    Use when reasoning about systems that pass untrusted content to a language model: the data-vs-instruction collapse that makes this attack class a structural property of LLMs rather than a fixable bug, the direct/indirect/exfiltration/action-trigger taxonomy, the role of every untrusted surface (RAG retrievals, tool results, attachments, web content, document parsing, user-provided text), why content filters and improved system prompts do not solve it, and the defense-in-depth measures that do (capability constraint, content origin tracking, separate planning and execution stages, human-in-the-loop gates, principle-of-least-authority for tools). Do NOT use for model refusal policy or jailbreak evals (use `guardrails` or `eval-driven-development`), for general application security (use `owasp-security` or `security-fundamentals`), for runtime input validation patterns (use `type-safety` + `api-design`), or for the protocol cycle of tool calls (use `tool-call-flow`).

  • Summarization

    jacob-balslev/skills/skills/ai-engineering/summarization Skill

    2★ repo

    Use when condensing prose while preserving meaning: session findings, wrap reports, research briefs, executive summaries, TLDRs, agent handoffs, progressive summaries, audit summaries, and long-document distillation. Covers extractive vs abstractive summarization, what to keep vs drop, evidence preservation, summary levels, handoff summaries, and audit-report condensation without hiding findings. Do NOT use for byte/data compression algorithms (use `compression`), context-window budget math or compaction triggers (use `context-window`), working-set selection (use `context-management`), prose tone repair (use `writing-humanizer`), or quality scoring (use `evaluation`).

  • Tool call flow

    jacob-balslev/skills/skills/ai-engineering/tool-call-flow Skill

    2★ repo

    Use when reasoning about the protocol-level cycle by which a language model uses external tools: declaration, request, execution, continuation, model-visible transcript or provider-resumed state, ID pairing, tool-result formatting, vendor encodings (Anthropic Messages, OpenAI Responses and Chat Completions, MCP, Gemini generateContent and Interactions), client tools vs hosted/server tools, strict schemas and grammar-constrained custom tools, streaming arguments, tool search/deferred loading, programmatic tool calling, computer-use/browser-control screenshot-action loops, parallel vs sequential calls, error handling, and the separation between model intent and runtime execution. Do NOT use for deciding when or how many tools to call (use tool-call-strategy), multi-agent architecture (use agent-engineering), prompt wording (use prompt-craft), or eval design for tool-use behavior (use eval-driven-development).

  • Tool call strategy

    jacob-balslev/skills/skills/ai-engineering/tool-call-strategy Skill

    2★ repo

    Use when an agent is making too many tool calls, when context is filling from verbose tool outputs, when the same operation could be a script instead of N individual calls, or when designing a tool-use protocol for a new agent or harness. Covers the three costs of every call (token, latency, context pollution), the script-vs-call decision gate, tool-selection decision trees (file-search vs content-search vs targeted-read vs full-read), call batching and parallelization, redundancy avoidance, the poka-yoke principle, subagent delegation for context protection, and cost-benchmark heuristics by task type. Do NOT use for prompt wording (use `prompt-craft`), broader context stack design across the five layers (use `context-engineering`), runtime tool failures or production debugging (use `debugging`), or behaviour-preserving refactor mechanics (use `refactor`).

  • Cognitive load theory

    jacob-balslev/skills/skills/quality-assurance/cognitive-load-theory Skill

    2★ repo

    Sweller's Cognitive Load Theory (CLT) for agents reviewing skill bodies, prompts, documentation, dashboards, and agent outputs for avoidable cognitive burden. Working memory holds roughly 4 chunks at a time; CLT classifies load into intrinsic (irreducible task difficulty), extraneous (unnecessary load from poor presentation, ELIMINATE), and germane (the schema-building processing applied to intrinsic load, PROTECT). Use when writing a SKILL.md body (does this section add extraneous load?), designing prompts (am I asking the model to hold too much at once?), building dashboards (what is the per-screen cognitive budget?), authoring docs (is intrinsic load segmented?), or checking whether modern features (long context, structured outputs, prompt caching, subagents) actually reduce load or just move it elsewhere. Do NOT use for retrieval and session working-set design (use context-management), token budget math and compaction timing (use context-window), prompt engineering tactics (use prompt-craft), token-efficient representation mechanics (use compression), or instructional design beyond the CLT mechanisms named here.

  • Security fundamentals

    jacob-balslev/skills/skills/quality-assurance/security-fundamentals Skill

    2★ repo

    Use when reasoning about baseline application-security properties: threat modeling, trust boundaries, Saltzer and Schroeder design principles, input validation, authentication vs authorization, secrets handling, secure-by-default choices, least privilege, defense in depth, and OWASP vulnerability classes as recurring failure modes. Covers cross-cutting decisions about what is trusted, where validation belongs, where authn/authz checks live, and how to bound blast radius. Do NOT use for LLM-specific prompt injection or agent-tool authority (use prompt-injection-defense), OWASP-category deep code review (use owasp-security), vendor webhook mechanics (use webhook-integration), cryptographic primitive implementation or key-management mechanics (use vendor/KMS/library docs), compliance/legal artifacts, or the social/organizational side of security.

  • Agent engineering

    jacob-balslev/skills/skills/software-architecture/agent-engineering Skill

    2★ repo

    Use when designing or evaluating a production AI agent system, choosing a multi-agent coordination pattern (orchestrator/worker, fan-out, consensus, sequential chain, evaluator/optimizer), diagnosing coordination failures (claim races, silent stalls, context contamination, runaway loops), or auditing whether an agent loop is truly production-ready. Covers the four pillars (architecture and lifecycle, task decomposition, coordination patterns, production reliability), the six reliability requirements (observability, cost budgets, idempotency, failure recovery, safety caps, claim locks), the delegation decision framework with overhead crossover, and the most common anti-patterns. Do NOT use for prompt wording (use `prompt-craft`), per-call tool efficiency (use `tool-call-strategy`), context-stack design within a single agent (use `context-engineering`), or runtime debugging of a deployed system (use `debugging`).

  • Task path optimization

    jacob-balslev/skills/skills/software-engineering-method/task-path-optimization Skill

    2★ repo

    This skill provides decision frameworks for choosing the optimal execution path before starting work: plan-vs-act gates, agent architecture selection (chaining, routing, parallelization, orchestrator-worker, evaluator-optimizer), scope management heuristics, critical-path analysis across task networks, and context budget awareness. Use when deciding how to approach a task (plan first vs act immediately), decomposing complex work into parallelizable subtasks, choosing between subagent patterns, or when a task has failed twice and needs a fresh approach. Do NOT use for executing the chosen plan (use task-execution), debugging failures (use troubleshooting or diagnosis), or tool-level efficiency (use tool-call-strategy).

  • Version control

    jacob-balslev/skills/skills/software-engineering-method/version-control Skill

    2★ repo

    Use when designing or maintaining the shape of a repository's git history — choosing a branching model, deciding rebase vs merge, sizing commits, linking commits to tracker tickets, tagging releases, running parallel work across worktrees, and resolving the merge conflicts that arise from any of the above. Covers trunk-based development, short-lived feature branches, atomic commit discipline, linear-history conventions (rebase + squash), release tagging with annotated tags and SemVer, hotfix flows from tags, and worktree lifecycle for parallel agents or contributors. Do NOT use for the words inside the commit message (Conventional Commits format, identifier naming — use `naming-conventions`), for chasing a release-pipeline failure (use `debugging`), or for reviewing a PR's content (use `code-review`).

  • Wassenger mcp

    wassengerhq/whatsapp-skills/skills/wassenger-mcp Skill

    2★ repo

    Reference for the Wassenger Model Context Protocol (MCP) server, scoped to the official WhatsApp Business API (WABA). Use when the agent needs to choose which Wassenger tool to call, understand parameter shapes, or troubleshoot tool errors. Covers the WABA-supported tool modules — messaging, templates, chats, chat-messages, labels, contacts, team, departments, queue, campaigns, devices, files, numbers, ping. The detailed per-tool catalog lives in references/tools-reference.md and loads on demand.

  • Wassenger setup

    wassengerhq/whatsapp-skills/skills/wassenger-setup Skill

    2★ repo

    Set up Wassenger to automate WhatsApp Business with an AI agent. Use when the user is new to Wassenger, has not connected a number yet, needs an API key, or wants to install the Wassenger MCP server. Walks through API key creation, connecting a number on the official WhatsApp Business API (new or via Coexistence), MCP install, and a sanity test. Targets the official WABA only — the legacy QR-pairing path is not covered by this skills pack.

  • Onboarding

    latent-variable/agentscope/skills/onboarding Skill

    2★ repo

    First-run setup for agentscope. Interview the user, fill the AGENTS.md template + memory with their identity and preferences, detect which agent CLIs are installed, wire them all to ~/.agents, and tune optional features (ELI5 explanations, the Speak-to-me TTS block, the review-cycle workflow). Run this the first time someone clones agentscope, or when they say "onboard me" / "set up agentscope".

  • Remember

    latent-variable/agentscope/skills/remember Skill

    2★ repo

    Save a durable fact about the user or their work into the shared cross-agent memory (~/.agents/memory), then commit + push so every agent (Claude, Codex, Gemini, Pi) sees it. The write-back path: use it whenever you learn something worth persisting beyond this session, or when the user says "remember this".

  • Self correct

    latent-variable/agentscope/skills/self-correct Skill

    2★ repo

    Audit and repair the shared agent knowledge base (~/.agents) when it drifts from reality: removed/renamed dirs or repos, changed paths/flags/commands, superseded facts. Keeps instructions, memory, and skills true for every agent on the machine. Use on demand, on a schedule, or whenever you notice canon is stale mid-task.

  • Ylf project instructions

    yaolifeng0629/ylf-agent-skills/skills/ylf-project-instructions Skill

    2★ repo

    Create or update a project's AGENTS.md or CLAUDE.md with compact YLF coding standards. Use when the user asks to make their coding discipline persistent in the current project, update project instructions, sync AGENTS/CLAUDE guidance, or generate a short rule set for Codex or Claude Code.