Context & AI engineering
25,772 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
domengabrovsek/claude/skills/handoff Skill
no license15★ repoCompact the current conversation into a handoff document for another agent to pick up.
domengabrovsek/claude/skills/write-a-skill Skill
no license15★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
viktorbezdek/skillstack/api-design/skills/api-design Skill
15★ repoDesign production-grade REST, GraphQL, gRPC, and Python library APIs with correct schemas, error contracts, auth, and versioning. Use when the user asks to design an API, define endpoints, create an OpenAPI/Swagger spec, design a GraphQL schema, build a gRPC service, model request/response with Pydantic, add pagination, or review API contracts. NOT for building MCP server tools (use mcp-server). NOT for Node.js/Express API routes or backend patterns (use backend-patterns or typescript-development).
viktorbezdek/skillstack/brainstorm-swarm/skills/custom-personas Skill
15★ repoDesign ad-hoc personas for niche domains when the canonical 12 brainstorm- swarm personas don't fit. Covers: when a custom persona is justified (vs forcing canonical to fit), the persona-design template (voice, contribution shape, output format), anti-patterns (too-narrow personas, redundant personas, sock-puppet personas), and how to invoke a custom persona inline via Task() with a tailored prompt rather than a saved subagent definition. Use when running a brainstorm-swarm and the topic calls for a CFO, Security Engineer, Lawyer, Marketing, Customer Success, or other domain- specific perspective not in the canonical 12. NOT for the canonical personas (use swarm-protocol). NOT for the orchestration mechanics (use swarm-protocol). NOT for the synthesis output (use swarm-synthesis). NOT for product personas as artifacts (use persona-definition).
viktorbezdek/skillstack/brainstorm-swarm/skills/interview-facilitation Skill
15★ repoStructure the interview arc when a brainstorm-swarm interviews the user. Covers the divergent-then-convergent arc (open with breadth, close with depth), question design (open vs probing, leading vs neutral, what-vs-why- vs-how), depth-vs-breadth tradeoffs, and when to send a second round of follow-up questions to specific personas. Use when running a brainstorm swarm and the swarm-protocol skill has spawned the persona subagents — this skill teaches how those personas interact with the user during the interview phase. NOT for the persona swarm orchestration itself (use swarm-protocol). NOT for synthesizing the swarm output (use swarm-synthesis). NOT for designing custom personas (use custom-personas). NOT for one-on-one Socratic interviews (use deep-interview from skillstack).
viktorbezdek/skillstack/brainstorm-swarm/skills/swarm-protocol Skill
15★ repoOrchestration logic for running a parallel persona-swarm brainstorm — when to invoke, which subset of the 12 canonical personas to spawn (PM, Engineer, Designer, Skeptic, User Advocate, Pre-Mortem Specialist, Junior, Veteran, First-Principles Thinker, Constraint-Setter, Optimist, Operator), how to spawn them in parallel via the Task() tool with persona-specific subagent types, how to handle their outputs, and when to do a second round. Use when the user asks to brainstorm with multiple perspectives, run a persona swarm, get a virtual roundtable, workshop an idea from PM/engineer/designer/skeptic angles, pre-mortem a decision, or invoke the brainstorm-swarm. NOT for code review (use code-review). NOT for single-perspective interviews (use elicitation or deep-interview). NOT for executing or building things (use team or autopilot). NOT for designing custom personas — that's the custom-personas skill. NOT for the synthesis output formatting — that's the swarm-synthesis skill.
viktorbezdek/skillstack/brainstorm-swarm/skills/swarm-synthesis Skill
15★ repoCombine a parallel persona-swarm's outputs into an actionable artifact — consensus matrix (what every persona agreed on), dissent log (where personas disagreed and why), open questions (what nobody could answer), recommended next move (synthesized decision). Preserves dissent rather than forcing consensus. Use when running a brainstorm-swarm and the swarm-protocol skill has collected the persona outputs — this skill produces the synthesis artifact. NOT for orchestrating the spawn (use swarm-protocol). NOT for designing the interview arc (use interview-facilitation). NOT for designing custom personas (use custom-personas). NOT for short-form structured writing like BLUF or Pyramid (use communication/structured-writing).
viktorbezdek/skillstack/code-review/skills/code-review Skill
15★ repoReviews existing code and pull requests using multi-agent swarm analysis covering security, performance, style, test coverage, and documentation quality. Extracts and prioritizes PR comments, performs security audits, and generates actionable fix plans with file:line references. Use when the user asks to review code, review a PR, audit code for security, assess code quality, analyze pull request comments, get feedback on existing code, or perform a code audit. NOT for writing new code or implementing features (use other development skills), NOT for finding and fixing runtime bugs or errors (use debugging), NOT for writing tests or setting up test infrastructure (use testing-framework), NOT for TDD methodology (use test-driven-development).
viktorbezdek/skillstack/deslop/skills/deslop-copy Skill
15★ repoRemove AI slop from marketing copy, blog posts, product descriptions, emails, and editorial content — and humanize the result. Use when asked to deslop, humanize, or anti-slop marketing copy, landing pages, product descriptions, email campaigns, blog posts, or any AI-generated prose. Trigger phrases: "deslop", "anti-slop", "remove AI slop", "humanize this copy", "this sounds AI-generated", "make this sound human", "clean up marketing copy", "remove AI clichés". NOT for UI microcopy or interface text (use deslop-ui). NOT for code cleanup (use ai-slop-cleaner). NOT for creating brand-new copy from scratch (use storytelling or prompt-engineering). NOT for preventing AI detector flags specifically (use deslop-detect).
viktorbezdek/skillstack/filesystem-context/skills/filesystem-context Skill
15★ repoUsing the FILE SYSTEM for context — scratch pads, plan persistence, dynamic skill loading, sub-agent file workspaces, and terminal log persistence. Use when the user asks to "offload context to files", "implement scratch pads", "persist agent plans", "use filesystem for agent memory", or mentions file-based context management, tool output persistence, or just-in-time context loading. NOT for in-context optimization like KV-cache or observation masking (use context-optimization), NOT for summarization or compression techniques (use context-compression), NOT for understanding context theory or fundamentals (use context-fundamentals).
viktorbezdek/skillstack/git-workflow/skills/git-workflow Skill
15★ repoGit workflow management — use when the user mentions git, conventional commits, commit quality, branch management, worktree operations, GitFlow, changelog generation, semantic versioning, release notes, backlog management, or issue tracking integration. NOT for CI/CD pipelines or pipeline YAML (use cicd-pipelines), NOT for non-git workflow orchestration (use skillstack-workflows or multi-agent-patterns), NOT for code review content or PR quality assessment (use code-review).
viktorbezdek/skillstack/gws-cli/skills/gws-cli Skill
15★ repoGoogle Workspace CLI (gws) for managing all 18 Workspace APIs from the terminal. Use when running gws commands, listing Drive files, sending Gmail, reading Sheets, creating Calendar events, managing Tasks, querying Chat, pushing Apps Script, building cross-service automations, or when user mentions gws or Google Workspace CLI. NOT for building MCP servers (use mcp-server), NOT for general API design (use api-design), NOT for GCP infrastructure (use cicd-pipelines).
viktorbezdek/skillstack/hindsight/skills/hindsight-memory Skill
15★ repoInteract with and integrate Hindsight long-term AI memory in Claude Code via the `hindsight` CLI. Use for recalling past context, reflecting over a memory bank, retaining facts/decisions, managing banks/entities/mental-models, and understanding the auto-recall/auto-retain hooks this plugin installs. Trigger phrases: "what do I remember about", "recall from my memory", "reflect on my past work", "retain this", "save to my memory bank", "hindsight memory", "check my long-term memory", "is memory working". NOT for short-term session context (Claude already has the transcript), NOT for code/structural search (use CodeGraph/Semble/grep), NOT for building a memory framework from scratch (use the memory-systems skill).
viktorbezdek/skillstack/mcp-server/skills/mcp-server Skill
15★ repoMCP (Model Context Protocol) server development — use when the user mentions MCP, Model Context Protocol, FastMCP, MCP server, MCP tool, Claude Code plugin, or building agent tools with MCP. Covers server implementation in Python or TypeScript, evaluation testing, production deployment, and plugin packaging. NOT for designing tool interfaces or tool consolidation patterns for agents (use tool-design), NOT for prompt engineering or prompt optimization (use prompt-engineering).
viktorbezdek/skillstack/mcp-server/skills/mcp-server/templates/skill Skill
15★ repoTemplate for creating Claude Code skills. Replace this description with a clear explanation of what this skill does and when it should be used.
viktorbezdek/skillstack/memory-systems/skills/memory-systems Skill
15★ repoGuides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory, or memory benchmarks (LoCoMo, LongMemEval). NOT for multi-agent coordination or agent handoffs (use multi-agent-patterns), NOT for tool design or tool interfaces (use tool-design), NOT for hosted agent infrastructure or sandboxed VMs (use hosted-agents).
viktorbezdek/skillstack/multi-agent-patterns/skills/multi-agent-patterns Skill
15★ repoThis skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution. NOT for agent memory or persistence (use memory-systems), NOT for tool design or tool interfaces (use tool-design), NOT for hosted agent infrastructure or sandboxed VMs (use hosted-agents), NOT for BDI cognitive models or mental state modeling (use bdi-mental-states).
viktorbezdek/skillstack/plugin-dev/skills/plugin-architecture Skill
15★ repoDecides which Claude Code extension type to use for a given capability — skill, hook, MCP server, subagent, or slash command — and designs the plugin.json manifest around that decision. Use when designing a plugin, planning plugin structure, choosing between skill vs hook vs mcp, setting up plugin composition, laying out plugin components, or refactoring an existing plugin whose decomposition feels wrong. Covers the five extension types, the decision matrix (when each fits), plugin.json schema reference, directory layout, namespacing conventions, and worked examples from real plugins. NOT for the content of a single component — use skill-foundry, plugin-hooks, mcp-server, or plugin-composition for deep dives.
viktorbezdek/skillstack/plugin-dev/skills/plugin-hooks Skill
15★ repoAuthoritative guide to Claude Code hooks — event-driven scripts that execute before or after tool calls, session events, file changes, and more. Use when writing a PreToolUse hook to block dangerous commands, a PostToolUse hook to auto-format after edits, a SessionStart hook to inject context, a Stop hook for session loops, a Notification hook for desktop alerts, a FileChanged hook for reactive environments, a WorktreeCreate hook for custom worktree provisioning, or current documented hook events. Covers handler types (command, http, mcp_tool, prompt, agent), matcher syntax (exact/OR-list/regex), exit code semantics, and JSON output schema. NOT for designing hook script content for a specific domain (use the domain skill) — this skill covers hook mechanics and authoring only.
viktorbezdek/skillstack/prompt-engineering/skills/prompt-engineering Skill
15★ repoDesign, evaluate, and iteratively improve prompts for LLMs — system prompts, few-shot examples, reasoning structures, and instruction templates. Use when the user asks to improve a prompt, write a system prompt, optimize LLM instructions, reduce hallucinations through prompt structure, test prompt variants, or apply prompting techniques (structured reasoning, ReAct, few-shot, structured output). NOT for building MCP tools or server implementation (use mcp-server). NOT for creating Claude Code SKILL.md files (use skill-foundry). NOT for building a full agent (use build-ai-agent workflow).
viktorbezdek/skillstack/skill-foundry/skills/skill-foundry Skill
15★ repoAuthor high-quality Claude Code SKILL.md files using philosophy-first design, evidence-based prompting, progressive disclosure, and anti-pattern prevention. Use when the user asks to write a skill file, create a new Claude Code skill, design a SKILL.md, review whether a skill's description will trigger correctly, or convert a workflow into a reusable skill. NOT for optimizing standalone prompts or system prompts (use prompt-engineering). NOT for full plugin development with hooks and MCP (use plugin-architecture). NOT for generating code documentation (use documentation-generator).
viktorbezdek/skillstack/skillstack-workflows/skills/build-a-plugin Skill
15★ repoEnd-to-end workflow for authoring a Claude Code plugin from idea to validated, evaluated artifact. Composes six phases — ideation with a 7-criteria kill gate (plugin-ideation), marketplace survey and build-vs-fork decision (plugin-research), skill/hook/MCP/subagent/command decomposition (plugin-architecture), component implementation (plugin-hooks + plugin-composition + skill-creator), structural validation (plugin-validation), and trigger plus output evaluation with iteration loop (plugin-evaluation). Use when building a full Claude Code plugin with multiple components, hooks, MCP servers, or composed skills. Use when converting a working prototype into a shippable plugin. NOT for writing a single SKILL.md file — use the write-your-own-skill workflow for that. NOT for one-off prompt engineering — use prompt-engineering directly.
viktorbezdek/skillstack/skillstack-workflows/skills/build-ai-agent Skill
15★ repoFunnel workflow for going from "I want an agent that does X" to a deployed, evaluated, cost-monitored agent. Runs through nine phases starting with the is-this-task-agent-appropriate check (agent-project-development), then prompt design with eval criteria first (prompt-engineering), tool design and consolidation (tool-design), architecture selection for multi-step work (multi-agent-patterns), persistence decisions (memory-systems), context-window management (context-optimization), evaluation pipeline construction (agent-evaluation), deployment (hosted-agents), and ongoing cost and quality monitoring (cloud-finops + agent-evaluation). Use when you're starting a new agent project and want to avoid the common failure modes. NOT for one-shot prompts — use prompt-engineering directly for those.
viktorbezdek/skillstack/skillstack-workflows/skills/context-engineering-pipeline Skill
15★ repoDiagnostic-and-fix pipeline for systematic context engineering — fix agent context, context engineering, context optimization pipeline, diagnose context problems. Chains context-fundamentals (attention, budgeting), context-optimization (KV-cache, partitioning, observation masking), context-compression (summarization, anchored iterative, tokens-per-task), context-degradation (lost-in-middle, poisoning, clash diagnosis), and filesystem-context (scratch pads, plan files, dynamic loading). Use when an agent's context is degrading, token costs are bloated, the agent forgets instructions mid-session, output quality drops in long conversations, or building a new agent and wanting context right from the start. NOT for prompt engineering — use prompt-engineering. NOT for agent architecture — use build-ai-agent.
viktorbezdek/skillstack/skillstack-workflows/skills/debug-complex-issue Skill
15★ repoLoop workflow for debugging a complex issue you've been stuck on for more than 30 minutes. Runs systematic hypothesis formation (debugging skill), feedback-loop mapping when the bug looks like a dynamic problem (systems-thinking), context-pathology check when it's an LLM/agent bug (context-degradation), blast-radius assessment before any fix attempt (risk-management), and uses test-driven-development as the debugging oracle — write a failing test that reproduces the bug, then iterate fix → test until green. Use when a bug has defeated a first-pass attempt, when symptoms seem to shift under investigation, when an LLM-based system is misbehaving in ways simple prompt fixes don't resolve, or when you need to fix safely under production constraints. NOT for obvious bugs where the fix is visible — just fix those directly.
viktorbezdek/skillstack/skillstack-workflows/skills/evaluate-and-improve-agent Skill
15★ repoDiagnostic-loop workflow for improving an underperforming AI agent. Starts with baseline measurement using rubrics and LLM-as-judge scoring (agent-evaluation), then diagnoses architectural problems like task-model mismatch and pipeline bottlenecks (agent-project-development), redesigns the agent topology — supervisor, swarm, or specialized agents (multi-agent-patterns), adds the right memory framework when persistence is the gap (memory-systems), and re-evaluates against the original baseline to prove improvement. Use when an existing agent is underperforming, producing inconsistent results, failing on edge cases, or costing too much per interaction. NOT for building a new agent from scratch — use the build-ai-agent workflow instead. NOT for prompt-only fixes — use prompt-engineering directly.
viktorbezdek/skillstack/skillstack-workflows/skills/evaluate-plugin-or-skill Skill
15★ repoUse when evaluating a Claude Code plugin or single SKILL.md and a verdict is needed — ship-ready, needs improvement, or rework. Multi-pass audit workflow that composes plugin-dev's structural validation, plugin-evaluation's activation and output measurement, and skill-foundry's anti-pattern audit to grade quality across five dimensions: structure, activation reliability, content discipline, output behavior, and documentation completeness. Trigger phrases include "evaluate this plugin", "review this skill", "audit this SKILL.md", "is this ready to publish", "check the quality of this plugin", "should this skill be shared", "give feedback on this plugin", "score this plugin before shipping". Use also when reviewing a third-party plugin before installation or recommendation. NOT for building a new plugin from scratch (use build-a-plugin). NOT for fixing a known bug or extending an existing plugin (use update-a-plugin). NOT for measuring runtime agent quality in production (use evaluate-and-improve-agent).
viktorbezdek/skillstack/skillstack-workflows/skills/llm-cost-optimization Skill
15★ repoFunnel-with-gate workflow for reducing LLM costs without degrading quality. Starts with diagnosing the cost surface using cloud-finops (specifically the finops-for-ai and finops-anthropic references), then applies context-optimization to reduce context per call, context-compression to compress what can't be reduced, prompt-engineering for shorter prompts and better model selection, and uses agent-evaluation as a mandatory gate — if any optimization degrades quality, roll it back. Finishes with prioritization of remaining opportunities and risk-management guardrails for future auto-scaling. Use when LLM costs are growing faster than usage, when leadership is asking why the bill doubled, when unit economics are turning negative, or when a new feature is about to ship and cost containment is part of the launch plan. NOT for cost reductions that don't involve LLMs — use cloud-finops directly.
viktorbezdek/skillstack/skillstack-workflows/skills/write-your-own-skill Skill
15★ repoMeta-workflow for creating your own Claude Code skill that actually activates when needed and delivers genuine value. Starts with skill-creator as the canonical starting point, adds elicitation frameworks when the skill is for a human/domain area (interviewing, research, therapy-adjacent), designs the examples that will illustrate the skill (example-design), aligns with repo conventions (consistency-standards), writes structural validation tests before the content (test-driven-development), audits the draft against anti-patterns (critical-intuition), and generates the README with scenario tables (documentation-generator). Use when creating any new Claude Code skill that you want to be activation-reliable, well-scoped, and maintainable. NOT for quick-and-dirty prompts — use prompt-engineering directly.
viktorbezdek/skillstack/tool-design/skills/tool-design Skill
15★ repoThis skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces. NOT for building MCP servers or MCP protocol implementation (use mcp-server), NOT for multi-agent coordination or agent handoffs (use multi-agent-patterns), NOT for agent memory or persistence (use memory-systems).
allemaar/open-skills/skills/extract-signal Skill
15★ repoAn elastic signal-extraction methodology run under /multi-agent-mode. INFERS from the call what signal, what form, what stakes, and where output goes. Default is agentic — a normal call spawns a freshly-primed sub-agent that gathers, vets, and returns the signal; when extract-signal IS the agent (in-session / new-session) it works inline with output inline by default (or to a file if specified). Composes techniques per task: gather (/prime-sweep, /prime-fetch, /prime-expand), diverge (/insight-explore), vet (/insight-critique → /insight-assess), cold second opinion (/cold-review-style). Vetting scales with stakes; the presented signal carries provenance and is sensitivity-matched to its destination. Trigger on /extract-signal, "extract the signal on X and present it as Y", "gather + vet + report the signal about X". Not the prime-* / insight-* / cold-review skills it composes; not /multi-agent-mode (the mode it runs under).
allemaar/open-skills/skills/handoff-execute Skill
15★ repoExecute a handoff brief with enforced source-read discipline — load the brief's @SOURCES.required tier fully before planning, cite sources per plan step, run @OUTCOME.verify after, emit the retro per @GROUND_TRUTH_REQUIRED. Trigger when the user runs /handoff-execute <brief-path>, or pastes the activation phrase emitted by /handoff. Not auto-triggered — the receiving session invokes explicitly. Use /plan-execute for PLAN.md files (different schema); use /handoff to *create* a brief; use /cold-review for outside-agent review, not for executing the work itself.
allemaar/open-skills/skills/handoff Skill
15★ repoGenerate a structured cold-agent handoff brief (YAML frontmatter + Obsidian markdown + YON blocks) that any fresh LLM session can pick up and execute. Trigger when the user runs /handoff or says "create a handoff", "dispatch to a fresh agent", "hand this to a cold session", "switch to a new session", "I have N tasks for cold agents", "package this for another agent". Use /orchestrate-mode instead when you want to keep the *current* session as coordinator (no artifact produced).
allemaar/open-skills/skills/human-rewrite Skill
15★ repoThe repair pass on text that already exists — an agent's own last output, a subagent's report, a supplied document, a research summary, a legal or medical paragraph — rewritten so a person can read it fast and act on it, without changing what it claims. Meaning-preserving by contract: uncertainty, scope conditions, numbers, sample sizes, attribution, absent results, and reversing caveats all survive. Works on any subject, not just software. Trigger phrases: "/human-rewrite", "translate that into human", "that was a wall of text", "I can't follow this", "say that again but readable", "shorten this without losing anything". Not /human-output (the writing contract, which this skill links to rather than restates) or /human-draw (builds a picture) — human-rewrite governs the transformation of text that already exists.
allemaar/open-skills/skills/multi-agent-mode Skill
15★ repoActivate multi-agent mode: the lead agent still works directly but delegates independent helper slices when useful. Trigger on /multi-agent-mode, "multi-agent mode", "use helper agents", "work with subagents", or "parallelize if useful". Use orchestrate-mode instead when the lead agent must dispatch only and not execute.
allemaar/open-skills/skills/new-skill-creator Skill
15★ repoScaffold a new Agent Skill end-to-end into a skills repo you maintain (folder, SKILL.md, optional protocol.yon for dual-doc skills, tri-runtime links for Claude Code + Codex + the shared .agents/ dir, commit and push). The maintainer's authoring loop — it links your own clone into your runtimes because you write the changes those links carry. Trigger when the user runs /new-skill-creator or says "create a skill", "make a new skill for X", "add a slash command", "turn this workflow into a skill", "codify this as a skill". Not for editing existing skills — edit the SKILL.md directly. Not for installing skills you did not write — copy those, per README.md. For migrating an existing single-doc skill to the dual-doc YON pattern, see section 6 below.
allemaar/open-skills/skills/orchestrate-mode Skill
15★ repoActivate orchestrator mode in the current session: the lead agent dispatches governed worker subagents and does not execute concrete work directly. Trigger on /orchestrate-mode, "become an orchestrator", "orchestrator mode", "delegate everything", or "do not execute". Use multi-agent-mode instead when the lead agent should still work directly while delegating helper slices.
zivtech/accessibility-skills/.claude/skills/drupal-a11y-patch-eval Skill
15★ repoEvaluate a Drupal accessibility patch end-to-end: baseline evidence, patch hygiene, after-patch verification, manual/AT checks, critic gate, and upstream handoff. Evidence-gated — never VERIFIED without before/after proof under the same conditions.
adryanmoldokkr32-pixel/anthropics-skills/skills/claude-api Skill
no license15★ repoBuild, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks to use the Claude API, Anthropic SDKs, or Managed Agents (/v1/agents, /v1/sessions, /v1/environments). DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
The same file is in 17 other repositories
adryanmoldokkr32-pixel/anthropics-skills/skills/mcp-builder Skill
no license15★ 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).
The same file is in 42 other repositories
adryanmoldokkr32-pixel/anthropics-skills/skills/skill-creator Skill
no license15★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
jackchuka/skills/claude-skill-prereq-audit Skill
15★ repoScan skills for prerequisite tools, MCP servers, and auth requirements, then check if everything is installed and authenticated. Offers to fix issues. Use when setting up a new machine, after installing skills, or to verify your environment. Triggers: "check prerequisites", "skill prereqs", "are my tools installed", "verify skill dependencies", "/claude-skill-prereq-audit".
jackchuka/skills/claude-skill-spec-audit Skill
15★ repoAudit skill SKILL.md files for compliance with the agentskills.io specification and house conventions. Checks frontmatter fields (name, description, compatibility, metadata, argument-hint), metadata sub-fields (author, scope, layer, confirms), and layer/suffix consistency. Use when adding new skills, reviewing skill quality, or ensuring all skills follow the spec. Triggers: "audit skills", "check skill spec", "skill compliance", "are my skills up to spec", "/claude-skill-spec-audit".
bntvllnt/agent-skills/skill-builder Skill
15★ repoBuild correct, consistent Agent Skills for any compatible agent product. Use when creating, updating, renaming, deleting, or validating a skill, or when improving skill descriptions, structure, safety rules, progressive disclosure, or trigger reliability.
cofin/flow/templates/agent/skills/flow-memory-keeper Skill
15★ repoUse at task, phase, flow, sync, archive, finish, revise, or failure checkpoints to keep Flow specs clean, capture learnings and failures, elevate durable patterns, and refine this skill with project-specific nuances
The same file is in 1 other repository
EntityProcess/agentv/plugins/agentic-engineering/skills/agent-architecture-design Skill
15★ repoUse when designing an AI agent system, selecting agentic design patterns, planning multi-phase workflows, choosing between single-agent and multi-agent architectures, or when asked "what kind of agent should I build", "how should I structure this automation", "design an agent for X", or "which agentic pattern fits this problem".
EntityProcess/agentv/plugins/agentic-engineering/skills/agent-plugin-review Skill
15★ repoUse when reviewing an AI plugin pull request, auditing plugin quality before release, or when asked to "review a plugin PR", "review skills in this PR", "check plugin quality", or "review workflow architecture". Covers skill quality, structural linting, and workflow architecture review.
EntityProcess/agentv/plugins/agentv-dev/skills/agentv-dev Skill
15★ repoAgentV CLI skills for evaluating, optimizing, and governing AI agents. Triggers: run evals, benchmark agents, write evals, review evals, analyze traces, optimize prompts, governance linting. Covers: eval running, eval writing, eval review, trace analysis, description optimization, autoresearch, and governance compliance.
EntityProcess/agentv/skills-data/agentv-bench Skill
15★ repoRun AgentV evaluations and optimize agents through eval-driven iteration. Triggers: run evals, benchmark agents, optimize prompts/skills against evals, compare agent outputs across providers, analyze eval results, offline evaluation of recorded sessions, run autoresearch, optimize unattended, run overnight optimization loop. Not for: writing/editing eval YAML without running (use agentv-eval-writer), analyzing existing traces/JSONL without re-running (use agentv-trace-analyst).
EntityProcess/agentv/skills-data/agentv-eval-migrations Skill
15★ repoMigrate AgentV eval YAML across breaking schema changes, especially workspace contract updates and portable-vs-local runtime binding cleanup.
EntityProcess/agentv/skills-data/agentv-eval-review Skill
15★ repoUse when reviewing eval YAML files for quality issues, linting eval files before committing, checking eval schema compliance, or when asked to "review these evals", "check eval quality", "lint eval files", or "validate eval structure". Do NOT use for writing evals (use agentv-eval-writer) or running evals (use agentv-bench).
EntityProcess/agentv/skills-data/agentv-eval-writer Skill
15★ repoWrite, edit, review, and validate AgentV EVAL.yaml / .eval.yaml evaluation files. Use when asked to create new eval files, update or fix existing ones, add or remove test cases, configure graders (`llm-rubric`, `script`), review whether an eval is correct or complete, convert between EVAL.yaml and evals.json using `agentv convert`, or generate eval test cases from chat transcripts (markdown conversation or JSON messages). Do NOT use for creating SKILL.md files, writing skill definitions, or running evals — running and benchmarking belongs to agentv-bench.
EntityProcess/agentv/skills-data/agentv-governance Skill
15★ repoAuthor, edit, and lint `governance:` blocks in `*.eval.yaml` files. Use when creating or updating evaluation suites that carry AI-governance metadata (OWASP LLM Top 10, OWASP Agentic Top 10, MITRE ATLAS, EU AI Act, ISO 42001). Also use non-interactively (e.g., from a GitHub Action) to lint changed eval files and report violations against the rules in `references/lint-rules.md`. Do NOT use for running evals or benchmarking — that belongs to agentv-bench.
jawwadfirdousi/agent-skills/prompt-template-wizard/skills/prompt-template-wizard Skill
no license15★ repoRigorously collects and validates all fields needed to produce a complete, unambiguous prompt template for features and bug fixes. The skill asks targeted questions until the template is fully filled, consistent, and ready to paste into a Codex/GPT-5.2 coding session.
ivanshamaev/de-agent-skills/group_skills/infra_dataops_group_skills/aiops_observability_copilot Skill
no license15★ repoAIOps observability copilot — natural language to PromQL/LogQL translation, alert explanation in plain English (what fired/why/impact), Grafana dashboard auto-generation from service topology, anomaly narrative generation from metric patterns, on-call context enrichment (related alerts/recent deploys/runbook links), log pattern clustering for noise reduction, SLO status explanation, automated weekly observability health digest
Aiops platform optimization agent
ivanshamaev/de-agent-skills/group_skills/infra_dataops_group_skills/aiops_platform_optimization_agent Skill
no license15★ repoAIOps continuous platform optimization agent — autonomous optimization loop (observe→analyze→recommend→apply), Kubernetes resource rightsizing (VPA recommendation reader + apply), Kafka consumer lag auto-scale, Spark job configuration tuning from history, idle resource detection (unused deployments/PVCs/topics), compaction and VACUUM scheduling, auto-ANALYZE stale statistics, cost savings attribution, optimization audit trail, human approval gate for high-risk changes
Dataops workflow orchestration review
ivanshamaev/de-agent-skills/group_skills/infra_dataops_group_skills/dataops_workflow_orchestration_review Skill
no license15★ repoWorkflow orchestration comparison and review — Airflow vs Prefect vs Dagster vs Temporal (architecture, execution model, dependency management, observability), when to choose each, migration patterns from Airflow to Prefect/Dagster, orchestrator evaluation scorecard, event-driven vs schedule-based triggering, Software-Defined Assets (Dagster) vs task-based (Airflow), hybrid orchestration patterns
Platform engineering agentic control plane
ivanshamaev/de-agent-skills/group_skills/infra_dataops_group_skills/platform_engineering_agentic_control_plane Skill
no license15★ repoAgentic control plane for data platform — MCP (Model Context Protocol) server exposing platform tools to AI agents (FastMCP/Python SDK), natural language platform operations (trigger DAG/create topic/run dbt/query Trino via LLM), Claude-based platform assistant with tool use, multi-agent platform governance (audit agent/cost agent/reliability agent), MCP server deployment (Docker/Kubernetes), tool authorization and audit logging, agentic workflow patterns (plan-execute-verify), platform chat interface
Airflow starrocks cdc orchestrator
ivanshamaev/de-agent-skills/group_skills/starrocks_group_skills/airflow_starrocks_cdc_orchestrator Skill
no license15★ repoAirflow CDC orchestration for StarRocks — watermark-based incremental sync, Routine Load health check DAG, Flink job submission via REST API, offset lag alerting, dead letter queue reprocessing, multi-table incremental sync with dependency graph, schema change detection and pipeline pause/resume
ivanshamaev/de-agent-skills/group_skills/starrocks_group_skills/starrocks_admin_compaction Skill
no license15★ repoStarRocks compaction tuning — base compaction vs cumulative compaction, compaction score analysis, write amplification reduction, BE config parameters (compaction_threads/min_cumulative_compaction_num_singleton_deltas/max_compaction_candidate_num), SHOW PROC '/compactions', manual compaction trigger, Primary Key table compaction, rowset management