Context & AI engineering
25,729 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
h3y6e/agent-skills/.vendor/skills/agent-platform-model-registry Skill
0★ repoAgent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
Agent platform prompt management
h3y6e/agent-skills/.vendor/skills/agent-platform-prompt-management Skill
0★ repoManages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
Agent platform rag engine management
h3y6e/agent-skills/.vendor/skills/agent-platform-rag-engine-management Skill
0★ repoManage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google Workspace RAG, or other RAG products like gRAG.
h3y6e/agent-skills/.vendor/skills/agent-platform-skill-registry Skill
0★ repoInteract with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.
Agent platform tuning management
h3y6e/agent-skills/.vendor/skills/agent-platform-tuning-management Skill
0★ repoManages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use `agent-platform-tuning`), deploying models to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).
h3y6e/agent-skills/.vendor/skills/agent-platform-tuning Skill
0★ repoAgent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use `agent-platform-deploy`), or managing serving endpoints (use `agent-platform-endpoint-management`).
h3y6e/agent-skills/.vendor/skills/ai-component-description Skill
0★ repoGenerate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write component description for AI, Figma MCP description, write the description for Claude to read, six-section description, describe this component for AI, or anything about writing text that makes components legible to LLMs. Do NOT trigger for JSON metadata schemas, structured constraint files, or programmatic tooling data — use metadata-schema-generator for those.
h3y6e/agent-skills/.vendor/skills/alloydb-basics Skill
0★ repoManages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB model context protocol (MCP) tools for automated database operations.
h3y6e/agent-skills/.vendor/skills/browser-testing-with-devtools Skill
0★ repoTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
h3y6e/agent-skills/.vendor/skills/claude-handoff Skill
0★ repoHand the current conversation off to a fresh background agent that picks up the work immediately.
h3y6e/agent-skills/.vendor/skills/context-engineering Skill
0★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
h3y6e/agent-skills/.vendor/skills/dispatching-parallel-agents Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
h3y6e/agent-skills/.vendor/skills/empirical-prompt-tuning Skill
0★ repoMethodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run them and evaluating two-sidedly (executor self-report + instruction-side metrics) until improvements plateau. Use after creating or revising a prompt or skill.
h3y6e/agent-skills/.vendor/skills/git-guardrails-claude-code Skill
0★ repoSet 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.
h3y6e/agent-skills/.vendor/skills/gpt-tasteskill Skill
0★ repoElite 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.
h3y6e/agent-skills/.vendor/skills/pi-coding-agent Skill
0★ repoEmbed `@mariozechner/pi-coding-agent` as a coding-agent runtime in Node scripts, write pi extensions (plugins) with `pi.registerTool` / `pi.registerCommand` / `pi.on`, package and `pi install` from npm/git, and pick between the SDK and `pi --mode rpc` for non-Node hosts. Covers session setup, the cwd × tools factory trap, TypeBox tool schemas, and the `peerDependencies` rule.
h3y6e/agent-skills/.vendor/skills/playwright-cli Skill
0★ repoUse when running Playwright via terminal CLI — `npx playwright test` (test runner), `codegen` (interactive recording), `screenshot` / `pdf` (one-off captures), and CI sharding. NOT for agent-driven real-time browser control (use `claude-in-chrome` MCP tools for that).
h3y6e/agent-skills/.vendor/skills/retrospective-codify Skill
0★ repoOn task completion, pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, skill, or CLAUDE.md rule. Use after trial-and-error solutions to spare future-you (or another agent) the same trap. Trigger phrases: "codify today's lessons," "make it a skill," "drop it into lint."
h3y6e/agent-skills/.vendor/skills/session-memory Skill
0★ repoPersist and recall findings across skill runs within and between sessions, building a cumulative knowledge base of what has been discovered about a design system. This is the cross-skill memory layer — it saves what was found, when, and by which skill, so future runs can compare, correlate, and avoid repeating work. Trigger when someone says: save these findings, remember this for later, compare with last run, what did we find before, load previous findings, recall the last audit, session history, show me what changed, cross-reference with previous runs, or anything about persisting, recalling, or comparing findings over time. Do NOT trigger for generating a single standalone report — use the specific skill for that. Do NOT trigger for running a full diagnostic — use full-system-diagnostic for that.
h3y6e/agent-skills/.vendor/skills/skill-finder Skill
0★ repoUse ONLY when the user explicitly asks to discover or evaluate a skill from OUTSIDE the curated catalog — e.g., "find a Stripe skill", "is there a skill for X?", "evaluate this candidate before adopting". Meta-skill, complementary to skill-selector: do NOT auto-invoke on routine apm-management, project-init, or catalog-resident requests. Cross-source survey across vetted registries (Anthropic official, claude-skill-registry, VoltAgent/awesome-agent-skills, ComposioHQ, Superpowers, GitHub topic) with a mandatory waxa-eval adoption gate.
h3y6e/agent-skills/.vendor/skills/subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
h3y6e/agent-skills/.vendor/skills/system-benchmark Skill
0★ repoBenchmark a design system against industry standards and comparable public systems, producing a qualitative comparison across dimensions with specific, named reference points. Goes beyond an internal health assessment to answer 'how does our system compare to what good looks like out there?' Trigger when someone says: benchmark our system, how do we compare, industry comparison, rate our system against others, where do we stand, compare us to Material Design, how mature is our system, are we behind or ahead, competitive assessment of our design system, or anything about comparing a design system's maturity or quality against external benchmarks. Do NOT trigger for an internal health check without external comparison — use system-health for that. Do NOT trigger for auditing a specific dimension — use the specific audit skill for that.
h3y6e/agent-skills/.vendor/skills/using-agent-skills Skill
0★ repoDiscovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
h3y6e/agent-skills/.vendor/skills/waxa-eval Skill
0★ repoUse when iterating on a skill's prompt with the waxa CLI (https://github.com/mizchi/skills/tree/main/tools/waxa) — authoring scenarios, choosing graders, interpreting unclear-points, advancing a ledger, and judging convergence. Encodes the four-stage iteration pattern observed in real iter loops (structural fix → grader breadth → surface-form coverage → residual unclear) and the scenario-design pitfalls (blank-slate executor's network limit, prompt expectation explicitness, regex coverage of Japanese/English surface forms). Meta-skill: do NOT auto-invoke for routine skill edits; fires only when the user explicitly runs waxa or asks for a skill-quality eval.
h3y6e/agent-skills/.vendor/skills/workload-manager-basics Skill
0★ repoUse this skill to manage Google Cloud Workload Manager evaluations, rules, scanned resources, and validation results by using public client libraries and the REST API. Use when you need to inspect workload best-practice rules, create and run evaluations for Google Cloud general best practices, SAP, SQL Server, or custom organizational rules, review violations, export results to BigQuery, or automate Workload Manager through client libraries because no service-specific public CLI or MCP server is available. Don't use for general Google Compute Engine instance management, VPC configuration, or standard IAM auditing.
h3y6e/agent-skills/skills/dispatching-parallel-agents Skill
0★ repomy agent skills
mocikadev/mocika-skills/project-ai-system Skill
no license0★ repoUse when 需要为项目建立、修订或审计 AI 工作系统:澄清新项目 spec、 制定执行协议、整理 AGENTS.md/CLAUDE.md/GEMINI.md、规划 docs 结构, 或判断内容应放入口文件、docs 还是 project skill。
lyoneel/ly-agent-skills/gen-agent Skill
0★ repoGenerate new agent definition files with proper structure and metadata. Use when creating new specialized agents for task-specific behaviors or when scaffolding agent templates.
Autter-dev/agentic-sales-skills/01-preparation/positioning/skills/knowledge-base-setup Skill
0★ repoBuilds a structured context/ directory with 7 markdown files that power every other skill in the toolkit.
Autter-dev/agentic-sales-skills/02-prospecting-and-outreach/agents/sdr-agent Skill
0★ repoAutonomous SDR that monitors pipeline, drafts outreach, qualifies inbound, and manages follow-ups
Autter-dev/agentic-sales-skills/04-proposals-and-close/skills/handoff-to-cs Skill
0★ repoGenerates structured handoff documents from sales to customer success with relationship context and promises tracking
Autter-dev/agentic-sales-skills/general/skills/agentic-sales-setup Skill
0★ repoThe starting point for the Agentic Sales toolkit. Explains how everything works, assesses where you are in sales, and kicks off the right skills for your stage.
ultimatile/development-skills/skills/code-review-gate Skill
no license0★ repoRun the built-in /code-review against the current diff through a fallback lane chain (headless claude -p, user-run, fresh-context subagent) with lane-failure, retry, and exhaustion handling, for when the Skill tool cannot invoke it directly.
ultimatile/development-skills/skills/copilot-review Skill
no license0★ repoPersonalized Development Skills
palmiro72-coder/palmiros-claude/plugins/palmiros-secops/skills/bug-bounty Skill
0★ repoWorkflow de bug bounty pós-Mythos (era de LLMs e agentes autônomos). Stack híbrido humano+IA: ProjectDiscovery, ffuf, Burp, Ghidra, semgrep, codeql, claude-cli para análise de código e geração de exploits. Cobre moat humano (business logic, cross-service invariants, novelty), bypass de WAF/CDN, checklists por vuln, redação de reports para triagem dual (IA+humano), e binary bounty (Pwn2Own/ZDI/Apple). Use sempre que o usuário mencionar bug bounty, HackerOne, Bugcrowd, Intigriti, BugHunt, caça a vulnerabilidades, recon, pentest ofensivo, fuzzing, bypass de WAF, exploit, payload, CVE, CVSS, CWE, AI-assisted pentesting, XBOW, PentestGPT, LLM vuln discovery, memory corruption, ou programas de recompensa por falhas.
tRollNhard/1st/custom-skills/mcp-builder Skill
no license0★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). Triggered by build an MCP server, create MCP tools, integrate API via MCP, write MCP server, or MCP for a specific service.
rerelurelu/skillbox/skills/delegating-via-herdr Skill
0★ repoDelegates a task to another coding agent (Codex, Claude Code, etc.) in a visible herdr pane and waits for completion in the background, so the user can watch progress live while the conversation stays responsive. Triggers on: "herdr で", "ペインで", "delegate", "隣で動かして", "Codex にやらせて", "バックグラウンドでレビュー", "/delegating-via-herdr". Use when the user asks to hand work to another coding agent inside herdr, or wants an agent's progress visible in a split pane. Requires HERDR_ENV=1.
okayus/okayus-skills/skills/cloudflare-mcp-claude-tooling Skill
0★ repoAgent Skills for Claude Code / agentskills.io-compatible agents. Cloudflare Workers + Discord integration patterns.
okayus/okayus-skills/skills/sandboxed-agent-git-relay Skill
0★ repoAgent Skills for Claude Code / agentskills.io-compatible agents. Cloudflare Workers + Discord integration patterns.
jacobleft/techang/skills/latex-optimizer Skill
no license0★ repoOptimize LaTeX compilation for AI agents by reducing token usage and making errors/warnings clear. Auto-detects available tools (texfot, pplatex, latexmk, tectonic) and configures the best compilation strategy. Use whenever compiling LaTeX documents to minimize output tokens and maximize error clarity. Essential for AI-assisted LaTeX workflows in Claude Code, OpenCode, Cursor, or any agent environment.
gerardbalaoro/skills/skills/general/handoff Skill
no license0★ repoCompact the current conversation into a handoff document for another agent to pick up.
0SxD/openrouter-swarm-orch-agent/agentic_auto_buildX_ai_bundle_repos/sagex_plugin_v0.1_example_copy/skills/worktree-isolation Skill
0★ repoCreate and manage git worktrees for parallel coding agent isolation. Invoke when two independent coding tasks need to run simultaneously (max 2).
The same file is in 2 other repositories
sanjeevafk/agent-skills/skills/mattpocock/setup-matt-pocock-skills Skill
0★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
The same file is in 15 other repositories
mj-deving/pai-skills/skills/Beads/HookAudit Skill
no license0★ repoAudit and repair Claude-side Beads hook behavior on the local machine. USE WHEN Beads hooks, SessionStart, PreCompact, Stop, PostToolUse, hook doctrine, auto-close risk, or machine-level Beads alignment.
mj-deving/pai-skills/skills/Beads/UpgradePath Skill
no license0★ repoAudit and safely upgrade a repo's Beads operating tier. USE WHEN evolve Beads workflow, move T1 to T2, move T2 to T3, add multi-agent coordination, add routing or orchestration, or confirm that no upgrade is justified.
mj-deving/pai-skills/skills/GitWorkflow Skill
no license0★ repoGit workflow and versioning — atomic commits, save point pattern, worktrees for parallel agents, commit conventions, change summaries. USE WHEN git workflow, commit strategy, branching, git conventions, commit message, worktree, parallel work, save point, git bisect, version control, how to commit, when to commit, split commits, act, local actions, test workflow, git-cliff, changelog, release notes.
mj-deving/pai-skills/skills/Security/PromptInjection Skill
no license0★ repoTest LLM applications for prompt injection vulnerabilities — jailbreak attempts, system prompt extraction, context manipulation, guardrail bypass techniques, direct injection, indirect injection, multi-stage attacks, and reconnaissance. USE WHEN prompt injection, jailbreak, LLM security, AI security assessment, pentest AI application, test chatbot, guardrail bypass, direct injection, indirect injection, RAG poisoning, multi-stage attack, complete assessment, reconnaissance.
mj-deving/pai-skills/skills/Thinking/ContextEngineering Skill
no license0★ repoStrategic context management for AI agents — 5-level hierarchy, starvation/flooding diagnosis, brain dump structuring, confusion surfacing. USE WHEN context management, context strategy, too much context, too little context, context window, context budget, brain dump, session context, what context to load, context starvation, context flooding, agent context, prompt engineering context.
mj-deving/pai-skills/skills/Utilities/Cloudflare Skill
no license0★ repoDeploy and manage Cloudflare Workers, Pages, and services via Code Mode MCP (API queries) + wrangler (deploys). OAuth auth for wrangler (tokens lack Pages perms). USE WHEN Cloudflare, worker, deploy, Pages, MCP server, wrangler, DNS, KV, R2, D1, Vectorize.
mj-deving/pai-skills/skills/Utilities/Delegation Skill
no license0★ repoParallelize work via background/foreground agents, built-in types, custom agents, or agent teams/swarms. USE WHEN 3+ independent workstreams, parallel execution, agent specialization, Extended+ effort, agent team, swarm, create an agent team.
mj-deving/pai-skills/skills/Utilities/Evals Skill
no license0★ repoObjective eval metrics via code/model/human graders with pass@k/pass^k scoring. USE WHEN eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test, run eval, compare models, compare prompts, create judge, create use case, view results, failure to task, suite manager, transcript capture, trial runner, skillgrade, skill eval, skill test, docker eval, external eval.
mj-deving/pai-skills/skills/Utilities/Prompting Skill
no license0★ repoMeta-prompting system that generates optimized prompts using templates, standards, and patterns. Produces structured prompts with role, context, and output format. USE WHEN meta-prompting, template generation, prompt optimization, programmatic prompt composition, render template, validate template, prompt engineering.
mj-deving/pai-skills/skills/Utilities Skill
no license0★ repoDeveloper utilities — CLI generation, skill scaffolding, agent delegation, system upgrades, evals, documents, parsing, audio editing, Codex, Cloudflare, browser automation, prompting, aphorisms, n8n workflows, beads management, full output enforcement, knowledge base, compound engineering. USE WHEN create CLI, scaffold skill, delegate, upgrade system, eval, document, parse, cloudflare, browser, n8n, beads, full output, knowledge, compound engineering.
mj-deving/pai-skills/skills/Utilities/n8n/n8n-code-mode Skill
no license0★ repoCode-mode runtime for n8n — sandboxed TypeScript execution that collapses sequential LLM tool calls into one shot. Architecture, sandbox rules, lazy imports, sibling auto-register, LLM gotchas, and benchmark data. USE WHEN code-mode, code mode, utcp, sandbox, n8n sandbox, toolCode, n8n code execution, token savings, tool consolidation, code-mode-tools, code-mode-core, MCP n8n, sibling tools, auto-register, lazy import, isolated-vm, n8n agent optimization, n8n cost reduction.
mj-deving/pai-skills/skills/Utilities/n8n/n8n-mcp-tools-expert Skill
no license0★ repoExpert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any n8n-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions n8n, workflows, nodes, or automation and you have n8n MCP tools available, use this skill first.
fbsmna-coder/karpathy-pro-max/skills/memory-hygiene Skill
0★ repoMaintain persistent memory files (CLAUDE.md, MEMORY.md, rules indexes) so they actually load and stay useful. Use when adding, editing, or auditing memory entries — to prevent silent truncation, orphan files, and split sections.
narenaryan/agent-skills/skills/go/go-interfaces-embedding Skill
0★ repoUse when designing Go type hierarchies with interfaces, type switches, or struct/interface embedding — covers implicit satisfaction, comma-ok assertions, compile-time interface checks via var _, method promotion rules, and name-collision resolution
mithraeums/skills/corp/skills/corp Skill
0★ repoA company in a folder — a referential multi-agent org for any AI coding assistant. Loads CEO, DEV, DESIGN, QA, and ARCH agents from markdown on demand. Use when a task spans multiple domains, before building anything non-trivial, or to decide which agent handles a given task. Host-agnostic (Claude / Codex / Cursor / Gemini / hako / any). Trigger: /corp, "which agent", "load corp", "who handles X".
mithraeums/skills/handoff Skill
0★ repoWrite a START-HERE state doc so the next session (you, later, or a teammate) resumes in seconds instead of re-deriving everything. Use at session end, before a long pause, when context is about to compact, or when the user says "wrap up / save state / where were we". Captures done / next / gotchas — not a transcript. Host-agnostic. Trigger: /handoff, "wrap up", "save state", "where were we", "hand off", "session notes".
mithraeums/skills/memory Skill
0★ repoPersistent file-based memory for any agent. Keep durable facts across sessions in a MEMORY.md index + one-fact-per-file, with rules for what to save, how to recall, and how to avoid stale/duplicate memories. Use when the user shares a durable preference, a project constraint, or says "remember this" / "from now on" — or at session start to recall. Host-agnostic; no database, just markdown. Trigger: /memory, "remember", "don't forget", "save this", "what do you know about".