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
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-pm-eng-loop Skill
14★ repoPair a product-manager agent with engineer agents through spec, pushback, scope negotiation, and acceptance so the build matches intent. Use when an agent team must turn a fuzzy request into a shipped, accepted increment.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-postmortem-council Skill
14★ repoRun a team of postmortem agents that builds the timeline, analyzes causes, drafts corrective actions, and reviews for blamelessness and completeness. Use after an incident when you need a rigorous, blameless writeup and owned action list instead of a hasty narrative that pins it on a person.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-qa-gate Skill
14★ repoPlace a QA agent as the last blocking node before output ships, checking acceptance criteria against executed test evidence with the power to veto. Use when builder agents keep declaring done on work that does not meet its criteria and you need one gate that runs the artifact instead of trusting the claim.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-red-team-blue-team Skill
14★ repoRun attacker and defender agents in a fix-and-re-attack loop so exploitable bugs get found, triaged, fixed, and verified before ship. Use when you want a system probed and hardened by an agent team rather than one pass of review.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-release-train Skill
14★ repoRun release agents that draft the changelog, scan risk, verify the candidate, and gate publish behind a go/no-go check. Use when cutting a release and you want the boring parts automated and the risky parts caught before ship.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-research-lab Skill
14★ repoRun a lab of researcher agents that search in parallel, verify sources independently, and synthesize a cited answer. Use when a question needs breadth of sources and every load-bearing claim must trace to evidence.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-role-definition Skill
14★ repoWrite role cards that pin each agent to one charter with declared inputs, outputs, refusal rules, and non-overlapping scope. Use when assembling a multi-agent team and you need every agent to stay in its lane instead of all drifting toward the same work.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-security-audit-team Skill
14★ repoRun a security audit as agents that map the attack surface, review each surface in parallel, skeptic-test every finding, and assemble one report. Use when you want a codebase audited by a coordinated agent team instead of a single review pass.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-startup-squad Skill
14★ repoRun a lean startup team of agents (builder, marketer, analyst) through one disciplined weekly loop of ship, promote, and measure. Use when you want a small agent team to move a single product metric week over week.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-support-desk Skill
14★ repoRun a team of support agents that triages each ticket, reproduces the problem, drafts a reply, and hands clean escalations to a human. Use when inbound support volume needs consistent handling and a person must approve every customer-facing reply before it goes out.
Amey-Thakur/AI-SKILLS/skills/performance/benchmark-design Skill
14★ repoWrite benchmarks that do not lie, controlling warmup, isolation, and statistics so the number reflects the code and not the environment. Use when comparing implementations, defending a performance claim, or a microbenchmark result looks too good.
Amey-Thakur/AI-SKILLS/skills/performance/memory-optimization Skill
14★ repoCut a program's memory footprint by fixing data layout, reusing allocations, and streaming input instead of buffering it whole. Use when a process is killed by the OOM killer, garbage collection dominates the profile, or heap growth tracks input size.
Amey-Thakur/AI-SKILLS/skills/systems-languages/c-memory-safety Skill
14★ repoWrite C with explicit ownership conventions, bounds discipline, and sanitizers wired into every test run. Use when writing or reviewing C code, or hunting memory corruption.
ngocsangyem/MeowKit/.claude/skills/agent-detector Skill
14★ repoDetects task agent and complexity tier at Phase 0 orient. Invoked first in every workflow. Provider adapters select any model/runtime policy. NOT for runtime agent routing inside a single skill (see orchestration-rules.md).
ngocsangyem/MeowKit/.claude/skills/benchmark Skill
14★ repoExperimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.
ngocsangyem/MeowKit/.claude/skills/context-audit Skill
14★ repoRead-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against the model context window. NOT for monetary cost tracking — that's /mk:budget. NOT for transcript size monitoring — long-session continuity defers to Claude Code native compaction. NOT for runtime context decisions (what to read, when to compact) — see mk:context-engineering. Use when planning to add context capacity, diagnosing perceived slowdowns, or auditing health.
ngocsangyem/MeowKit/.claude/skills/context-engineering Skill
14★ repoRuntime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).
ngocsangyem/MeowKit/.claude/skills/cook Skill
14★ repoOrchestrates single-task implementation pipeline: plan → test → build → review. Shipping is an explicit follow-up. Use for feature work, plan execution, or fixes scoped to a single task. NOT for green-field product builds (see mk:autobuild); NOT for auto-invoked workflow orchestration (see mk:workflow-orchestrator).
ngocsangyem/MeowKit/.claude/skills/henshin Skill
14★ repoUse when transforming existing code into agent-consumable surfaces — CLI (npm-publishable), MCP server (stdio/SSE/Streamable HTTP), and a companion skill. Triggers on 'agentize', 'henshin', 'expose as MCP', 'wrap as CLI', 'publish to npm', 'make LLM-accessible', 'turn into agent tool', 'expose feature as tool'. Runs when the user has existing code and wants to ship it to agents. NOT for building new code from scratch (see mk:bootstrap); NOT for reviewing or verifying existing code (see mk:review).
ngocsangyem/MeowKit/.claude/skills/lazy-agent-loader Skill
14★ repoDeprecated compatibility shim. Agent routing reads the canonical inventory under .claude/agents/ directly; do not use this skill for agent selection.
ngocsangyem/MeowKit/.claude/skills/memory Skill
14★ repoJSON-canonical session memory. Use when capturing session learnings, extracting patterns, or tracking costs — persists to .meowkit/memory JSON stores; matching Markdown files are generated views. Activates during Phase 0 (Orient) to load context and Phase 6 (Reflect) to persist it. NOT for weekly-cadence engineering retrospectives (see mk:retro); NOT for arbitrary file storage.
ngocsangyem/MeowKit/.claude/skills/orchestrate Skill
14★ repoCoordinates staged or parallel jobs across live-verified coding-agent runtimes (Claude Code, Codex, Cursor, and other installed CLIs) and in-session toolkit subagents. Routes each job by capability and risk tier, isolates parallel writers in git worktrees, captures redacted output, resumes interrupted runs, and blocks completion until an independent arbiter verifies the results. Use when work should be split across multiple runtimes or subagents, run as staged or parallel jobs, and reviewed before handoff. NOT for a single-agent task or the in-session 7-phase flow (use mk:cook / mk:workflow-orchestrator).
ngocsangyem/MeowKit/.claude/skills/prompt-enhancer Skill
14★ repoUse when refining a draft user prompt before sending it to a coding agent. Decomposes goal/context/constraints/acceptance/output-format, detects ambiguity and model-coupled framing, then emits a model-agnostic rewrite. Supports --analyze, --score, and --deep. NOT for prompts from scratch (mk:brainstorming), plans/reviews (mk:elicit), implementation plans (mk:plan-creator), or general codebase scouting (mk:scout).
ngocsangyem/MeowKit/.claude/skills/skill-creator Skill
14★ repoCreate new skills with proper structure, compliance checks, and registration. Use when asked to create a skill, build a new skill, or scaffold a skill template. Enforces mk: prefix, sub-agents.md structure, and context engineering principles.
ngocsangyem/MeowKit/.claude/skills/skill-template-secure Skill
14★ repoSecure skill template with prompt injection defenses. Copy this template when creating new skills.
ngocsangyem/MeowKit/.claude/skills/team-config Skill
14★ repoSet up parallel agent team for COMPLEX tasks. Creates worktree structure, generates ownership map, and initializes task queue. Use when orchestrator decomposes a task into parallel subtasks, or when asked to "set up team", "parallel setup", or "configure worktrees".
ngocsangyem/MeowKit/.claude/skills/workflow-orchestrator Skill
14★ repoAuto-invoked 7-phase workflow for complex-feature intent. Includes fasttrack mode for pre-approved specs. NOT for explicit user-invoked single tasks (see mk:cook); NOT for green-field autonomous builds (see mk:autobuild); NOT for simple bug fixes (see mk:fix).
ngocsangyem/MeowKit/.claude/skills/worktree Skill
14★ repoManages git worktrees for parallel agent isolation. Creates isolated worktrees for parallel agents on parallel/{name}-{timestamp} branches, merges results with conflict detection, prunes stale metadata, and reports health status. NOT for user-initiated feature branches — use git worktree directly for that.
ngocsangyem/MeowKit/assets Skill
14★ repoUse this skill to generate well-branded interfaces and assets for MeowKit (AI Agent Toolkit for Claude Code), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-agent-browser Skill
14★ repoBrowser automation CLI for agents: navigate, click/fill, screenshot, extract data, test apps, Electron/Slack, cloud browsers. NOT for the user's real Chrome profile/cookies (mk:chrome-profile).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-agent-detector Skill
14★ repoDetects the right agent and complexity tier at Phase 0 orient; runs first in every workflow. NOT for runtime agent routing inside a single skill.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-benchmark Skill
14★ repoExperimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-context-engineering Skill
14★ repoRuntime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for .codex/ overhead audit (mk:context-audit).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-cook Skill
14★ repoSingle-task pipeline: plan → test → build → review (ship separately). Use for a feature or scoped fix. NOT for green-field builds (mk:autobuild) or auto-orchestration (mk:workflow-orchestrator).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-henshin Skill
14★ repoConvert existing code into agent-consumable CLI/MCP server + companion skill. Use for 'agentize', 'expose as MCP', 'wrap as CLI'. NOT new code from scratch (mk:bootstrap) or review (mk:review).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-lazy-agent-loader Skill
14★ repoDeprecated compatibility shim. Agent routing reads the canonical inventory under .codex/agents/ directly; do not use this skill for agent selection.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-memory Skill
14★ repoJSON-canonical session memory in .meowkit/memory (Markdown is a generated view). Capture learnings, patterns, costs; loads at Orient, persists at Reflect. NOT for retrospectives (mk:retro).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-prompt-enhancer Skill
14★ repoRefine a draft prompt before sending to a coding agent: decomposes goal/context/constraints, flags ambiguity, emits a model-agnostic rewrite. NOT for prompts from scratch (mk:brainstorming).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-skill-creator Skill
14★ repoCreates new skills with proper structure, compliance checks, and registration. Enforces mk: prefix, sub-agents.md structure, and context-engineering principles. Use to scaffold a new skill.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-skill-template-secure Skill
14★ repoSecure skill template with prompt injection defenses. Copy this template when creating new skills.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-workflow-orchestrator Skill
14★ repoAuto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/codex/root/.agents/skills/mk-worktree Skill
14★ repoManages git worktrees for parallel agent isolation: creates parallel/{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-agent-browser Skill
14★ repoBrowser automation CLI for agents: navigate, click/fill, screenshot, extract data, test apps, Electron/Slack, cloud browsers. NOT for the user's real Chrome profile/cookies (mk:chrome-profile).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-agent-detector Skill
14★ repoDetects the right agent and complexity tier at Phase 0 orient; runs first in every workflow. NOT for runtime agent routing inside a single skill.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-benchmark Skill
14★ repoExperimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a fully automated runner.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-context-audit Skill
14★ repoRead-only audit of the project's agent-tree structural overhead vs the context window. NOT for cost tracking (budget skill); NOT for read/compact decisions (mk:context-engineering).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-context-engineering Skill
14★ repoRuntime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for agent-tree overhead audit (context-audit).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-cook Skill
14★ repoSingle-task pipeline: plan → test → build → review (ship separately). Use for a feature or scoped fix. NOT for green-field builds (mk:autobuild) or auto-orchestration (mk:workflow-orchestrator).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-henshin Skill
14★ repoConvert existing code into agent-consumable CLI/MCP server + companion skill. Use for 'agentize', 'expose as MCP', 'wrap as CLI'. NOT new code from scratch (mk:bootstrap) or review (mk:review).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-lazy-agent-loader Skill
14★ repoDeprecated compatibility shim. Agent routing reads the canonical inventory under .cursor/agents/ directly; do not use this skill for agent selection.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-memory Skill
14★ repoJSON-canonical session memory in .meowkit/memory (Markdown is a generated view). Capture learnings, patterns, costs; loads at Orient, persists at Reflect. NOT for retrospectives (mk:retro).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-prompt-enhancer Skill
14★ repoRefine a draft prompt before sending to a coding agent: decomposes goal/context/constraints, flags ambiguity, emits a model-agnostic rewrite. NOT for prompts from scratch (mk:brainstorming).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-skill-creator Skill
14★ repoCreates new skills with proper structure, compliance checks, and registration. Enforces mk: prefix, sub-agents.md structure, and context-engineering principles. Use to scaffold a new skill.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-skill-template-secure Skill
14★ repoSecure skill template with prompt injection defenses. Copy this template when creating new skills.
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-workflow-orchestrator Skill
14★ repoAuto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).
ngocsangyem/MeowKit/packages/mewkit/src/migrate/modules/cursor/root/.cursor/skills/mk-worktree Skill
14★ repoManages git worktrees for parallel agent isolation: creates parallel/{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).
Z-M-Huang/vcp/plugins/dev-buddy/skills/dev-buddy-ralph Skill
14★ repoDrive a Ralph run end-to-end through the dev-buddy MCP server.
Z-M-Huang/vcp/plugins/mcp-doc/skills/mcp-doc-add-tool Skill
14★ repoCreate a custom MCP tool for the documentation manifest. Guides the user through defining the tool's purpose, generating an action script with embedded data, computing the hash, and adding it to the manifest.
Z-M-Huang/vcp/plugins/mcp-doc/skills/mcp-doc-generate Skill
14★ repoGenerate AI-written documentation for a specific directory or all undocumented directories. Creates structured READMEs optimized for both human and AI consumption, and updates the manifest.
Z-M-Huang/vcp/plugins/mcp-doc/skills/mcp-doc-init Skill
14★ repoInitialize documentation manifest for git-doc-mcp. Scans the project for documentation files (*.md, READMEs, ADRs, etc.), creates .mcp/manifest.yml with resource entries and search tools, and configures .mcp.json for the git-doc-mcp MCP server. Run this once when setting up project documentation.