Context & AI engineering
25,815 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
wanshuiyin/ARIS-Movie-Director/skills/comic-panel-prompt-builder Skill
79★ repoPhase-1 step of comic-author — the DETERMINISTIC compiler (搬运工原則) that turns ONE gate-approved panel_spec + its status:locked blueprint into the EXACT fixed-section bake string for the spiral engine via the shipped scripts/build_prompt.py (+ the canonical scripts/_validate.py vetoes). No Codex call in the happy path; it only emits, the engine bakes. Composes style_prefix + condition_string, injects the active failure_mode repair note on retry, and hard-REJECTS banned vocab (camera/lens/lighting/quality padding). Routes html_bubbles[] to the JSON viewer overlay, NEVER into the bake string (no baked bubbles unless the panel is text_mode:baked). Refuses unless the upstream blueprint is status==locked (the cross-layer gate's hand-off token) and every ref is a REAL locked asset path. Use when a panel_spec is locked and you need its prompt_bundle, just before comic-director's panel_gate.
wanshuiyin/ARIS-Movie-Director/skills/method-figure Skill
79★ repoGenerate a publication-grade method / architecture / pipeline / workflow figure (a paper or README 'Figure 1') as an AUDITABLE object, not a one-shot prompt. A deterministic JSON blueprint LOCKS the content; an image model (gpt-image-2, baked by the agent via mcp__codex__codex — Codex GPT-5.5 xhigh, sandbox workspace-write) bakes the aesthetic from a labeled-condition render + the project's real identity refs; a cross-model panel (Gemini + Codex) blind-transcribes the result and a script hard-diffs it against the blueprint; the loop regenerates until Gemini AND Codex approve and the diff is empty — then the calling agent (Claude) gives the structural sign-off. NOT for statistical plots (use a plotting tool) or photo scenes.
smith-horn/skillsmith/packages/mcp-server/src/assets/agent-pack Skill
no license78★ repoDelegate your agent-skill lifecycle: keep skills current, audit and clean up your inventory, and vet skills before you install them. The Skillsmith Agent diagnoses in full for free, proposes a batched fix plan, and changes files only with your per-changeset approval, with one-step undo. Triggers: "ask the Skillsmith Agent", "clean up my skills", "what skills are outdated", "audit my skills", "vet this skill before I install it".
smith-horn/skillsmith/packages/mcp-server/src/assets/skills/skillsmith Skill
no license78★ repoSkillsmith is the canonical lifecycle manager for agent skills (SKILL.md format) across any MCP-capable agent runtime — Claude Code, Cursor, Copilot, Codex, Windsurf. Discover, evaluate, install, use, maintain, author, govern, retire skills. Triggers: 'use Skillsmith', 'ask Skillsmith', 'search Skillsmith', 'find a Skillsmith skill', 'install with Skillsmith', 'Skillsmith trust tier', 'Skillsmith audit', 'create a skill with Skillsmith', 'publish to Skillsmith', 'Skillsmith quota', 'pin a Skillsmith skill', 'compare Skillsmith skills'. Routes natural-language requests to Skillsmith MCP tools and CLI commands.
JasonxzWen/harness-hub/skills/agent-reach Skill
no license77★ repoLoad when a task needs read-only internet research or content retrieval through an already installed Agent Reach CLI; diagnose available backends first, never install, upgrade, authenticate, configure, or copy credentials on the user's behalf.
JasonxzWen/harness-hub/skills/claude-api Skill
no license77★ repoLoad when a task needs Claude API or Anthropic SDK build, debug, migration, or tuning work; skip provider-neutral, OpenAI, or non-Anthropic model work.
JasonxzWen/harness-hub/skills/handoff Skill
no license77★ repoLoad when a task needs to hand off current work, compact a conversation for another agent/session, or create restart notes; do not load for visual HTML repo reports.
JasonxzWen/harness-hub/skills/mcp-builder Skill
no license77★ repoLoad when a task needs MCP server design, build, review, testing, tool schema, resource, or prompt work; skip ordinary REST clients and non-MCP integrations.
JasonxzWen/harness-hub/skills/skill-creator Skill
no license77★ repoLoad when creating, updating, adapting, or evaluating a standard agent skill; do not load for ordinary documentation edits or one-off prompt advice.
iammm0/secbot/skills/custom/execgo-agent-bridge Skill
no license77★ repoRoute shell, runtime.command, runtime.script, mcp.call, cli.run, or task_graph.submit work through Secbot's ExecGo-backed control tools.
JKHeadley/instar/skills/agent-identity Skill
76★ repoSet up persistent agent identity files (AGENT.md, USER.md, MEMORY.md) and teach the agent to read them at every session start. Works in any Claude Code project — no external dependencies required. Trigger words: who am I, identity, remember me, agent name, my principles, who are you, what are my values.
JKHeadley/instar/skills/agent-memory Skill
76★ repoTeach cross-session memory patterns using MEMORY.md — what to save, how to organize it, how to maintain it over time, and how to structure topic files as memory grows. Works in any Claude Code project with no external dependencies. Trigger words: remember this, save for later, across sessions, persistent memory, don't forget, note this, keep this, write this down.
JKHeadley/instar/skills/agent-passport Skill
76★ repoView this agent's digital passport (identity + trust + allowed/forbidden actions) and verify a peer's passport against a proposed action (EXO 3.0).
JKHeadley/instar/skills/agent-readiness Skill
76★ repoScore a task or workflow on its coordination-vs-judgment ratio to tell whether it's a good agent candidate (EXO 3.0 task-decomposition matrix).
JKHeadley/instar/skills/knowledge-base Skill
76★ repoIngest URLs, documents, and transcripts into a searchable knowledge base. Query past research and curated documentation using full-text search. Trigger words: ingest, knowledge base, look up, search knowledge, what do we know about, research, index this, add to knowledge base.
JKHeadley/instar/skills/spec-converge Skill
76★ repoIteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available family) until convergence, then produce a comprehensive ELI10 convergence report. Output is a spec tagged review-convergence — one of the two tags /instar-dev requires before it will touch instar source. NOT user-invocable; run by the instar-developing agent before any spec-driven /instar-dev work.
oprogramadorreal/optimus-claude/skills/code-review-deep Skill
75★ repoIterative auto-fix code review — runs `/optimus:code-review` in a fresh subagent context per iteration, applies fixes, runs tests, bisects failures, and continues until convergence or the iteration cap (default 8, hard cap 20). Creates a git checkpoint commit after each iteration (skip with --no-commit). Requires a test command in .claude/CLAUDE.md. Use when single-pass review leaves issues or for thorough cleanup before a release.
oprogramadorreal/optimus-claude/skills/handoff Skill
75★ repoCompacts the current conversation into one self-contained, tool-agnostic handoff document at docs/handoffs/<slug>.md so any fresh agent or teammate can resume the work from that file alone. References pushed artifacts by path or URL, inlines anything not on the remote, and redacts secrets and PII. Re-running on an existing handoff offers enhance or overwrite. Writes only that one file; never commits.
oprogramadorreal/optimus-claude/skills/permissions Skill
75★ repoConfigures Claude Code permissions for safe agent autonomy. Creates settings.json with allow/deny rules and a hook enforcing path restrictions, git branch protection (commit/push blocked on master/main), and precious-file safeguards. Use after /optimus:init to enable autonomous agent workflows, or standalone to lock down a project's permission boundaries.
oprogramadorreal/optimus-claude/skills/prompt Skill
75★ repoCrafts optimized, copy-ready prompts for any AI tool — LLMs, coding agents, image generators, workflow tools. Extracts intent, selects the right template, runs a diagnostic scan, and delivers a token-efficient prompt. Accepts input in any language; English output by default. Use when writing, fixing, improving, or adapting a prompt for any AI tool.
oprogramadorreal/optimus-claude/skills/refactor-deep Skill
75★ repoIterative refactoring of the feature-branch diff (full project when no diff exists) — runs `/optimus:refactor` in a fresh subagent context per iteration, applies fixes, runs tests, bisects failures, and continues until convergence or the iteration cap (default 8, hard cap 20). Supports `testability` or `guidelines` focus to prioritize finding categories. Fixes are applied automatically without per-change approval; for a single supervised pass, use /optimus:refactor. Creates a git checkpoint commit after each iteration (skip with --no-commit). Requires a test command in .claude/CLAUDE.md. Use for thorough guideline alignment or testability cleanup before /optimus:unit-test.
oprogramadorreal/optimus-claude/skills/worktree Skill
75★ repoCreates a git worktree for isolated parallel development — new branch in a separate directory with project setup and test baseline. Enables multiple Claude Code sessions on different tasks simultaneously. Multi-repo aware. Use when you need to work on something else without disturbing current work.
sneg55/agent-starter/skills/remember Skill
75★ repoReview auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers.
The same file is in 1 other repository
tranhieutt/software_development_department/.claude/skills/claude-api Skill
74★ repoProvides code patterns for the Anthropic Claude API including streaming, tool use, and prompt caching. Use when working with Anthropic SDK files or when the user mentions Claude API, Anthropic client, or LLM integration.
tranhieutt/software_development_department/.claude/skills/context-engineering Skill
74★ repoStrictly enforce context engineering principles to avoid context stuffing, optimize memory architecture, and manage the Research-Plan-Reset-Implement cycle.
tranhieutt/software_development_department/.claude/skills/handoff Skill
74★ repoGenerates the lightweight 3-field handoff summary for cross-domain work and optionally persists a formal handoff artifact for High-risk transfers.
tranhieutt/software_development_department/.claude/skills/llm-app-patterns Skill
74★ repoProvides architectural patterns for LLM-powered applications and AI assistants, including prompt engineering, RAG, agent loops, conversation management, and evaluation. Use when building AI-based features, chatbots, or complex AI system architectures.
tranhieutt/software_development_department/.claude/skills/map-workflow Skill
74★ repoGenerates a structured multi-agent workflow graph from a pattern and agent list. Supports Sequential, Parallel, Hierarchical, and Iterative patterns. Used by @producer to plan feature delivery before any implementation begins.
tranhieutt/software_development_department/.claude/skills/rag-engineer Skill
74★ repoProvides Retrieval-Augmented Generation patterns covering embedding models, vector databases, chunking strategies, and retrieval optimization. Use when building RAG systems or when the user mentions RAG, vector search, embeddings, or retrieval-augmented generation.
tranhieutt/software_development_department/.claude/skills/subagent-driven-development Skill
74★ repoExecutes an approved implementation plan task-by-task with a fresh implementer subagent per task and two review gates. Use when a plan is approved, tasks are mostly sequential, and quality gates are needed without full orchestrate/fork-join overhead.
tranhieutt/software_development_department/.claude/skills/vector-database-engineer Skill
74★ repoProvides vector database and semantic search patterns for Pinecone, Weaviate, Qdrant, Milvus, and pgvector in RAG and recommendation systems. Use when implementing vector search or when the user mentions vector database, semantic search, embeddings, or similarity search.
tranhieutt/software_development_department/.claude/skills/visual-engineer Skill
74★ repoGenerates high-fidelity architecture diagrams, sequence flows, and component maps for SDD projects. Use when finalizing a design phase, documenting system architecture, or visualizing agentic workflows. Default style: Style 6 (Claude Official).
lovstudio/skills/skills/image-creator Skill
72★ repoGenerate images via multiple mechanisms. Supports: (1) End-to-end AI generation via Gemini/ZenMux — given a prompt, directly output an image. (2) Code-based rendering — generate HTML/React single-file, render to PNG via Playwright. (3) Prompt engineering — generate optimized prompts for external models (nano-banana-pro, etc.). Trigger words: image, generate image, 生图, render, poster, 海报, banner, card, 卡片
likweitan/abap-skills/skills/btp-diagram-generator Skill
72★ repoGenerate SAP BTP (Business Technology Platform) solution architecture diagrams as native draw.io (.drawio) files following the official SAP BTP Solution Diagram guidelines (Fiori Horizon design system) and open them via a configured draw.io MCP server. USE WHEN: user asks to create/draw/design/sketch a BTP diagram, BTP architecture, BTP landscape, BTP solution diagram, BTP reference architecture, SAP Business Technology Platform diagram, or wants to visualize SAP BTP services (CAP, Build, Integration Suite, SAC, AI Core, HANA Cloud, Cloud Foundry, Kyma, Workzone, etc.) and their interdependencies in draw.io / drawio / diagrams.net. DO NOT USE FOR: non-BTP architecture diagrams, generic flowcharts, sequence/UML diagrams, or diagrams that should remain in Mermaid/PlantUML.
Tibsfox/gsd-skill-creator/examples/skills/music/orchestration Skill
no license71★ repoInstrumentation, arranging, and timbral analysis for ensemble and orchestral writing. Covers instrument families (strings, woodwinds, brass, percussion, keyboards), ranges, transpositions, timbral characteristics, scoring techniques, doubling and voicing, Rimsky-Korsakov's orchestration principles, Ravel's and Messiaen's timbral innovations, jazz big band voicing, popular music arranging, and notation conventions. Use when choosing instruments, scoring for ensembles, analyzing orchestral texture, or arranging music for different forces.
Tibsfox/gsd-skill-creator/examples/skills/orchestration/agent-orchestration Skill
no license71★ repoProvides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures. Use when designing agent systems, configuring MCP servers, setting up agent teams, or when user mentions 'MCP', 'A2A', 'agent orchestration', 'multi-agent', 'swarm', 'agent team', 'LangGraph', 'CrewAI', 'AutoGen'.
Tibsfox/gsd-skill-creator/examples/skills/orchestration/gupp-propulsion Skill
no license71★ repoInterrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.
Tibsfox/gsd-skill-creator/examples/skills/orchestration/mayor-coordinator Skill
no license71★ repoNorthbridge coordination pattern for multi-agent orchestration. Creates convoys, dispatches work via sling, monitors progress, and handles escalations. Never executes work directly.
Tibsfox/gsd-skill-creator/examples/skills/orchestration/runtime-hal Skill
no license71★ repoRuntime HAL for multi-runtime agent orchestration. Detects active AI assistant (Claude Code, Codex, Gemini, Cursor) and exposes uniform interface for startup injection, GUPP enforcement, and communication selection.
Tibsfox/gsd-skill-creator/examples/skills/patterns/hook-recipes Skill
no license71★ repoCurated collection of ready-to-use Claude Code hook recipes for safety, automation, formatting, logging, and context injection. Use when configuring hooks, setting up safety guards, automating workflows, or when user mentions 'hooks', 'PreToolUse', 'PostToolUse', 'guard', 'automation', 'claude hooks'.
Tibsfox/gsd-skill-creator/examples/skills/state/hook-persistence Skill
no license71★ repoPull-based work assignment channel implementing GUPP (Get Up and Push Protocol). Manages single-active-work-item hooks per agent with filesystem persistence and atomic state transitions.
Tibsfox/gsd-skill-creator/examples/skills/workflow/context-handoff Skill
no license71★ repoCreates context handoff documents for session continuity. Use when ending sessions, switching tasks, or handing off work.
Tibsfox/gsd-skill-creator/examples/skills/workflow/security-hygiene Skill
no license71★ repoSecurity hygiene for GSD's self-modifying skill and agent system. Use this skill whenever: creating, editing, or deleting skill files (.claude/skills/, .claude/commands/), modifying agent definitions (.claude/agents/), working with YAML configuration or chipset files, handling JSONL observation data (.planning/patterns/), processing community-contributed skills or chipsets, any file path operations that could involve user input, or when installing/updating project-claude configuration. Also activates for discussions about skill-creator security, trust models, or content hygiene.
Tibsfox/gsd-skill-creator/infra/packs/knowledge/skills/kp-pipeline-orchestration Skill
no license71★ repoOrchestrates knowledge pack content generation pipeline: batch scheduling, completion tracking, cross-pack dependency ordering, and validation triggering. Use when coordinating pack generation across phases 245-251.
Tibsfox/gsd-skill-creator/project-claude/skills/context-handoff Skill
no license71★ repoCreates context handoff documents for session continuity. Use when ending sessions, switching tasks, or handing off work.
Tibsfox/gsd-skill-creator/project-claude/skills/gupp-propulsion Skill
no license71★ repoInterrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.
Tibsfox/gsd-skill-creator/project-claude/skills/memory-hubness-gate Skill
no license71★ repoUse at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.
Tibsfox/gsd-skill-creator/project-claude/skills/memory-use-warrant Skill
no license71★ repoRun this appropriateness check the moment you are about to integrate a retrieved long-term memory — a Grove content-addressed hit, a chroma/pgvector neighbour, a memory-consolidation digest, or a MEMORY.md line — into a response, especially anything touching private origins, Fox Companies IP, credentials, or Center Camp / consent-governed content. It answers a question intent-router never asks: not WHAT to fetch or HOW, but WHETHER a correctly-retrieved item should reach output. Relevance is not appropriateness — a perfect similarity match can still be a boundary violation. Default is FAIL-CLOSED: if in-context authorization is uncertain, the memory may inform behaviour but must not be surfaced. Backed by RBI-Eval (arxiv 2606.06055v1). Triggers on surfacing recalled sensitive memory into a response.
Tibsfox/gsd-skill-creator/project-claude/skills/security-hygiene Skill
no license71★ repoSecurity hygiene for GSD's self-modifying skill and agent system. Use this skill whenever: creating, editing, or deleting skill files (.claude/skills/, .claude/commands/), modifying agent definitions (.claude/agents/), working with YAML configuration or chipset files, handling JSONL observation data (.planning/patterns/), processing community-contributed skills or chipsets, any file path operations that could involve user input, or when installing/updating project-claude configuration. Also activates for discussions about skill-creator security, trust models, or content hygiene.
Tibsfox/gsd-skill-creator/project-claude/skills/trace-to-skill-inducer Skill
no license71★ repoUse when you have captured session evidence — session-retro / session- observatory-live traces in .planning/patterns/, tool logs, correction records — and want to induce a reusable skill from it. Segments the traces into candidate skill units (an LLM judgment, not a deterministic parse) and decomposes each candidate into a four-part structured spec: workflow structure, execution semantics, and runtime attachments (verification, safety, rollback, state). It emits a spec object, NOT a finished SKILL.md, and hands that spec to skill-forge. It sits between skill-integration (upstream frequency detector) and skill-forge (downstream author). Backed by Agent-Trace-to-Skill Induction (arxiv 2606.06893v1). Triggers on inducing a skill from captured traces, turning a repeated pattern into a skill spec, and preparing evidence for skill-forge.
fvadicamo/dev-agent-skills/plugins/skill-authoring/skills/creating-skills Skill
70★ repoGuide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.
The same file is in 5 other repositories
seldonframe/seldonframe/.claude/skills/handoff Skill
70★ repoWrite a session handoff that lets a fresh agent (or you after compaction) resume cold with zero re-discovery. Use when ending or pausing a work session, before a likely compaction, or when passing work to another agent/worktree. Captures STATE (what is true now) over INSTRUCTIONS (what to do) — state survives when plans change; step-lists rot.
seldonframe/seldonframe/skills/seldonframe-agent-business Skill
70★ repoUse when a builder working in an IDE agent (Claude Code, Cursor, Codex) wants to build, test, deploy, sell, or get paid for an AI agent on SeldonFrame — e.g. "build me a receptionist agent and sell it", "deploy my agent to a real phone number", "list my agent on the marketplace", "run my agent's evals", "withdraw my agent earnings" — or when the SeldonFrame MCP (@seldonframe/mcp) is connected and the user asks what to do next.
DominikTobureto/awesome-grok-build/.grok/skills/research-agent Skill
70★ repoUse for current web/X research, library/API verification, competitive analysis, source-backed technical decisions, or updating docs with recent facts.
seldonframe/seldonframe/io.github.seldonframe/mcp MCP server
70★ repoBuild, deploy, and sell AI agents for local-service businesses - from your IDE.
scdenney/open-science-skills/codex/llm-calibration-logprobs Skill
no license69★ repoAnalyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
scdenney/open-science-skills/codex/model-committee-fable Skill
no license69★ repoRun a deliberative two-model committee between GPT-5.6 "Sol" and Claude Opus 5, chaired by Fable 5. Same two deliberating members as model-committee; the difference is the chair — Fable 5 aggregates the scores, applies the tie rule, and synthesizes the decision, so a lightweight Claude-family chair handles the tally and synthesis. Use when the user needs one consequential decision from multiple defensible options and wants a Fable-chaired deliberation. Suitable for architecture, research design and interpretation, manuscript strategy, ambiguous diagnosis, evaluation design, and policy or standards tradeoffs. Not for factual lookups, independent-coder reliability, open-ended brainstorming, routine implementation, or final high-stakes professional judgment.
scdenney/open-science-skills/codex/model-committee-sol Skill
no license69★ repoRun a deliberative two-model committee between GPT-5.6 "Terra" and Claude Opus 5, chaired by GPT-5.6 "Sol." Same two deliberating members as model-committee; the difference is the chair — Sol aggregates the scores, applies the tie rule, and synthesizes the decision. Use when the user needs one consequential decision from multiple defensible options and wants a Sol-chaired deliberation. Suitable for architecture, research design and interpretation, manuscript strategy, ambiguous diagnosis, evaluation design, and policy or standards tradeoffs. Not for factual lookups, independent-coder reliability, open-ended brainstorming, routine implementation, or final high-stakes professional judgment.
scdenney/open-science-skills/codex/model-committee Skill
no license69★ repoRun a deliberative two-model committee between GPT-5.6 "Sol" and Claude Opus 5. Use when the user needs one consequential decision from multiple defensible options and wants the two model families to propose independently, inspect each other's reasoning, revise, cross-rank, and converge under a predeclared rubric. Suitable for architecture, research design and interpretation, manuscript strategy, ambiguous diagnosis, evaluation design, and policy or standards tradeoffs. Not for factual lookups, independent-coder reliability, open-ended brainstorming, routine implementation, or final high-stakes professional judgment.
scdenney/open-science-skills/plugin/skills/diverge-codex Skill
no license69★ repoAgentic skills for Claude Code and Codex, built from published social-science methods sources. Covers experimental design, computational text analysis, manuscript QA, and transparent reporting.