Context & AI engineering
25,610 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
CohenD/cc-stack/.claude/skills/promptfoo-evals Skill
no license0★ repoWrite, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions, model-graded rubrics, transforms, datasets, exports, and CI gates. Use for non-redteam eval coverage, regression tests, or new eval matrices. Do not use for adversarial redteam plugin or strategy setup.
zakelfassi/skdd-commons/packs/2026-07-frontier/staff-the-swarm Skill
0★ repoFan wide work out to parallel agents — one lane and one definition of done per agent — then adversarially verify the findings and synthesize a single answer. Use when work is wide rather than deep (full-site audits, migrations across many call sites, research from multiple angles, review across dimensions), when a linear walk would take hours, or when independent perspectives materially reduce the chance of a wrong conclusion.
Hefrock/agent-skills/skills/agent-redteam Skill
0★ repoGenerates adversarial test cases targeting safe-failure behavior — refusals, hedging, graceful degradation. Use this when you want to stress-test an agent's safety boundaries, check for prompt injection, or build an adversarial eval set. Pairs with agent-eval for scoring: agent-redteam generates cases, agent-eval runs and scores them. Triggers on "red team my agent," "test for jailbreaks," "adversarial cases," "prompt injection testing," or "does my agent refuse correctly."
Hefrock/agent-skills/skills/deid-reid-harness Skill
0★ repoBuild and run an adversarial de-identification ⟷ re-identification evaluation harness for clinical text: generate synthetic clinical notes with ground-truth identifier spans, run a de-id pipeline (defender) over them, and score leakage against an attacker. Use this whenever the task involves evaluating a PHI scrubber or de-id pipeline, measuring re-identification risk, testing HIPAA Safe Harbor coverage or Expert Determination risk, building a privacy-utility frontier for clinical NLP, or comparing de-identification approaches — even if the user only says "test my de-identifier," "how leaky is this scrubber," or "de-id eval." Prefer this over an ad-hoc script whenever synthetic clinical data, PHI, or de-identification evaluation is mentioned.
Hefrock/agent-skills/skills/repo-pincer Skill
0★ repoReverse-engineers a codebase by reconciling what it claims to do against what it actually does. Runs two independent passes — top-down from docs/README/manifests/API surface, bottom-up from entry points through the actual implementation — then classifies every claim as Confirmed, Drift (was true, isn't anymore), Aspirational (documented but never built), or Silent (implemented but undocumented). The discrepancy list is the deliverable, not either summary alone. Use this when onboarding onto an unfamiliar codebase, auditing whether documentation matches implementation, evaluating a dependency or vendor repo before committing to it, or when a long-lived project's docs and code have drifted apart. Triggers on "reverse engineer this repo," "does the documentation match the code," "audit this codebase," "onboard me onto this project," or "find where the docs and code disagree." Runs standalone — no MCP or wiki setup required. If an obsidian-vault MCP server is connected, offers to compile its output into Sources/raw/ for wiki-operator's /source command to pick up.
Hefrock/agent-skills/skills/wiki-governor Skill
0★ repoRuns the wiki's self-governing maintenance loop and holds it accountable to its own constitution. Orchestrates wiki-librarian (structure), wiki-synthesizer (compilation), and wiki-warehouse (cold-storage integrity, if in use), then adds the things none of them do — a constitution-compliance audit, a tracked wiki health score, and a knowledge-gap queue. Use on a weekly cadence or when the vault hasn't been maintained in a while. Triggers on "govern my wiki," "maintain my wiki," "is my wiki healthy," "wiki health score," "check constitution compliance," "what am I missing in my vault," and the command /govern. Requires the obsidian-vault MCP server connected. Pairs with wiki-librarian, wiki-synthesizer, and wiki-warehouse, which it invokes rather than reimplements.
Hefrock/agent-skills/skills/wiki-librarian Skill
0★ repoMaintains the structural health of the wiki. Audits for broken links, orphan pages, stale notes, near-duplicates, and contradictions. Proposes and applies fixes with user confirmation. Run weekly or before a major synthesis session. Triggers on "audit my wiki," "clean up my vault," "check wiki health," "find duplicates," "fix broken links," and the command /audit. Requires the obsidian-vault MCP server connected. Pairs with wiki-operator for on-demand edits and wiki-synthesizer for content compilation.
Hefrock/agent-skills/skills/wiki-operator Skill
0★ repoOperates a Karpathy-style personal knowledge wiki by reading and writing an Obsidian vault directly via MCP — searching before creating, updating existing concept pages over adding new ones, merging duplicates, and keeping all notes linked. Use this skill for any vault operation: processing new learning into wiki notes, improving a concept page, finding connections between ideas, reviewing note quality, generating study prompts, or running maintenance. Triggers on "add this to my wiki," "update my notes on X," "what do I know about Y," "connect these ideas," "clean up my vault," and the commands /learn /update /connect /ask /review /quiz /map /source /clean /health. Requires an Obsidian MCP server connected with read and write tool access.
Hefrock/agent-skills/skills/wiki-synthesizer Skill
0★ repoCompiles raw material into the wiki. Automatically preprocesses unstructured journal entries, then promotes ideas into Knowledge/ concept pages and compiles Sources/raw/ into source pages. Updates Maps/_context.md after each run. Use this after learning sessions. Triggers on "synthesize my notes," "compile my wiki," "promote from journal," "process raw sources," and the command /synthesize. Requires the obsidian-vault MCP server connected. Pairs with wiki-operator for on-demand edits and wiki-librarian for maintenance.
Hefrock/agent-skills/skills/wiki-warehouse Skill
0★ repoIngests raw research documents (PDFs, ebooks, scans, articles) into a separate private "cold storage" GitHub repo, then writes a lean pointer note into the Obsidian vault — keeping originals and full extracted text out of the vault so it stays fast and git-diffable. Use when the user wants to file, archive, warehouse, or "add a document/paper/PDF to my knowledge base," or to keep large source files outside the vault. Triggers on "warehouse this," "ingest this document," "add this PDF to cold storage," "file this paper," and the commands /ingest and /warehouse-audit. Requires the obsidian-vault MCP server connected and the knowledge-warehouse repo cloned locally. Pairs with wiki-synthesizer (which compiles the resulting Source note into concepts) and wiki-librarian (structural audits).
HorizonBrute/Horizon_AI_OS/horizon_system/skills_bin/handoff Skill
no license0★ repoWrite a structured handoff document capturing current session state. Use when the user types /handoff, asks to "write a handoff", "produce a handoff document", "save session state", or wants to capture current state for a future session.
HorizonBrute/Horizon_AI_OS/horizon_system/skills_sbin/agent-teams Skill
no license0★ repoCreate or edit agent-team definitions in local.agent_teams.md at any scope (OS, project, brain, or subfolder) — define the agent chain, each role's model-group preference, and loop/retry constructs. Use when the user types /agent-teams, asks to "add an agent team", "define an agent team", "edit agent teams", or "create a team for this project/scope".
HorizonBrute/Horizon_AI_OS/horizon_system/skills_sbin/convert-prompt-to-saill Skill
no license0★ repoConvert a natural-language prompt into a SAILL agent-team flow — roles with model groups, control-flow flags (parallel/wait/Loop/if needed/if asked/ask user), boxes for sub-teams and nesting, and -context- for run-time values. Use when the user types /convert-prompt-to-saill, says "turn this into SAILL", "convert my prompt to SAILL", or "express this as an agent team / SAILL flow".
HorizonBrute/Horizon_AI_OS/horizon_system/skills_sbin/handoff Skill
no license0★ repoWrite a structured handoff document capturing current session state. Use when the user types /handoff, asks to "write a handoff", "produce a handoff document", "save session state", or wants to capture current state for a future session.
HorizonBrute/Horizon_AI_OS/horizon_system/skills_sbin/test-agent-teams Skill
no license0★ repoEnd-to-end self-test of the Agent Teams system — walk every defined team (or one named team) and spawn each role so it echoes a self-generated nonce, its role, what it was told to do (its charter), and the model it actually ran as. Use when the user types /test-agent-teams --all-teams (all) or /test-agent-teams <team-name> (one team), says "test the agent teams", "run the agent-team self-test", or wants to verify team resolution + model routing. The skill generates its own nonce.
cipradu/Agent-Workbench/skills/coding-project-orchestrator Skill
0★ repoUse before acting on real-repository coding-project work when the correct workflow, current source authority, ceremony level, downstream owner, or acceptance gate must be chosen. Trigger on features, bugs, refactors, specs/plans, architecture, implementation, reviews, agents/skills/rules, source-control, external sync, or any request where missing truth, blast radius, verification, or ownership is unclear.
cipradu/Agent-Workbench/skills/hindsight-memory Skill
0★ repoUse when Hindsight tools are available and the work requires storing or retrieving durable team operational memory — a user shares a lasting fact, correction, decision, or procedure; an incident is resolved; someone asks about prior incidents, device history, or whether a problem has happened before; or an explicit remember or recall request appears.
ffidelis16/GEO-OS/skills/geo-os-orchestrator Skill
0★ repoUse quando um pedido em linguagem natural precisa ser classificado e roteado para o menor fluxo suficiente entre as skills, módulos e templates existentes do GEO OS.
kunkun-pubilic/skill-toolkit-public/skills/skill-overlay Skill
0★ repo当上游官方或可信 Agent Skill 基本可用但需要 Kun/Codex/Claude 兼容层时使用。触发关键词:official-overlay / overlay skill / 给官方 skill 加兼容层 / 上游 skill 二次封装。不用于从零创建 skill。
sharklandy/claude-code-starter-kit/skills/process/avoid-agentic-pitfalls Skill
0★ repoApply on virtually any non-trivial coding task, regardless of domain or stack. Enforces discipline against silent unverified assumptions, over-engineering, and out-of-scope edits. Trigger on any substantial code change, not just specific cases.
GeekXtop/obsidian-agent-skills/skills/obinit Skill
0★ repo初始化或更新软件项目的 Obsidian-backed 通用 agent 工作约定。适用于用户要求为新项目或已有仓库建立通用 agent 指令、创建或连接 Obsidian 项目笔记、创建 allowlist 范围内的 agent/doc 目录,或为 Codex、Claude Code 以及其他 coding agent 统一项目 onboarding 流程。
udsy19/.claude/skills/anti-hallucination Skill
no license0★ repoGrounds every factual claim and every API/library usage in a verified source before asserting it, and researches the current best approach before implementing in an unfamiliar project or domain. Use whenever you are about to state a fact, use an API/flag/config key/version, cite something, or decide "the best way to do X" — especially in an unfamiliar codebase. Prevents confident, plausible, wrong answers.
udsy19/.claude/skills/browser-testing-with-devtools Skill
no license0★ 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.
The same file is in 94 other repositories
udsy19/.claude/skills/context-engineering Skill
no license0★ 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.
udsy19/.claude/skills/memory-discipline Skill
no license0★ repoGoverns what to persist to Claude Code's native memory and where it belongs, so memory accumulates durable, reusable knowledge instead of noise. Use when you learn something worth carrying across sessions (a build command, a non-obvious convention, a user preference, a debugging insight, a decision with rationale), when the user says "remember this" or "for next time", or when deciding whether a fact belongs in auto-memory, CLAUDE.md, a rule, or nowhere.
udsy19/.claude/skills/using-agent-skills Skill
no license0★ 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.
ch040602/skill-vaccine/tests/fixtures/graph_skills/prompt_injector Skill
no license0★ repoProvides risky agent instruction experiments.
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Business & Ops/context-window-management Skill
0★ repoStrategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Business & Ops/cross-eval Skill
0★ repo/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation. Use when a high-stakes memo needs an independent sanity check before the boardroom — e.g. a bet-the-company pivot or fundraise terms.
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Business & Ops/google-calendar-automation Skill
0★ repoLightweight Google Calendar integration with standalone OAuth authentication. No MCP server required.
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Business & Ops/jobgpt Skill
0★ repoJob search automation, auto apply, resume generation, application tracking, salary intelligence, and recruiter outreach using the JobGPT MCP server.
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Business & Ops/llm-structured-output Skill
0★ repoGet reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Creative/linear-claude-skill Skill
0★ repoManage Linear issues, projects, and teams
The same file is in 4 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-creator Skill
0★ repoCreate custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
The same file is in 1 other repository
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-designer Skill
0★ repoUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-evaluation Skill
0★ repoTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-framework-azure-ai-py Skill
0★ repoBuild persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-manager-skill Skill
0★ repoManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-memory-mcp Skill
0★ repoA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-memory-systems Skill
0★ repoMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-name Skill
0★ repoOne paragraph describing what this agent does, who it's for, and when to activate it.
Agent orchestration improve agent
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-orchestration-improve-agent Skill
0★ repoSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
The same file is in 7 other repositories
Agent orchestration multi agent optimize
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-orchestration-multi-agent-optimize Skill
0★ repoOptimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-protocol Skill
0★ repoInter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-squad Skill
0★ repoMain agent orchestrator that coordinates a specialized squad of agents
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-tool-builder Skill
0★ repoTools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agent-workflow-designer Skill
0★ repoDesign production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.
The same file is in 3 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agenthub Skill
0★ repoMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
The same file is in 4 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agentic-actions-auditor Skill
0★ repoAudits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/agents-md Skill
0★ repoThis skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/ai-agent-development Skill
0★ repoAI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/ai-agents-architect Skill
0★ repoExpert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/ai-dev-jobs-mcp Skill
0★ repoSearch 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/ai-engineer Skill
0★ repoBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/ai-ml Skill
0★ repoAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/antigravity-agent-manager Skill
0★ repoConfigure and orchestrate parallel agents using the standalone Antigravity 2.0 Agent Manager and Antigravity IDE.
The same file is in 5 other repositories
Antigravity skill orchestrator
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/antigravity-skill-orchestrator Skill
0★ repoA meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
The same file is in 3 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/autonomous-agent-patterns Skill
0★ repoDesign patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).
The same file is in 7 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/autoresearch-agent Skill
0★ repoAutonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
The same file is in 4 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Data & AI/clarvia-aeo-check Skill
0★ repoScore any MCP server, API, or CLI for agent-readiness using Clarvia AEO (Agent Experience Optimization). Search 15,400+ indexed tools before adding them to your workflow.
The same file is in 5 other repositories