Context & AI engineering
25,729 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
Coding agent capability mapper
frankxai/awesome-gamification-agent-skills/skills/coding-agent-capability-mapper Skill
1★ repoMap coding-agent capabilities into loadouts, skills, tools, eval gates, repo permissions, task classes, and progression tracks. Use when designing Codex, Claude, Grok, Gemini, Antigravity, AO, SO, or swarm capability systems.
yzp100911/CrabAgent/xCrab/skills/browser-use-guide Skill
1★ repo让AI代理控制浏览器自动化网页操作。支持 Claude/GPT/Gemini/Ollama,可执行填表、购物、搜索等任务。
The same file is in 1 other repository
yzp100911/CrabAgent/xCrab/skills/openclaw-agent-browser Skill
1★ repoHeadless browser automation CLI for AI agents. Use when interacting with websites — navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, scraping, testing web apps, downloading files, or automating any browser task. Triggers on requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data", "test this web app", "login to a site", "monitor a page", or any task requiring programmatic web interaction.
The same file is in 2 other repositories
Self improving proactive agent
yzp100911/CrabAgent/xCrab/skills/self-improving-proactive-agent Skill
1★ repoA unified OpenClaw skill that merges self-improvement and proactivity: learn from corrections, maintain active state, recover context fast, and keep work moving with clear boundaries.
The same file is in 1 other repository
yzp100911/CrabAgent/xCrab/skills/skylv-agent-team-coordinator Skill
1★ repoMulti-agent orchestration designer. Designs agent collaboration, task routing, and state management. Triggers: multi-agent, agent orchestration, agent collaboration.
comment-hq/skills/skills/comment-identity Skill
1★ repoGive this session a named, session-scoped Comment.io identity only when it is about to make a direct REST write without either a supplied per-doc token or a human-selected registered identity. Never invoke for Comment.io tools/MCP, browser actions, URL fetches, or reads: those routes carry their own identity and access, or are read-only. Runtime-generic (Claude Code, Codex, any shell agent). Mints one Ephemeral handle through a paired computer or owner ark_ key and degrades to anonymous when neither authority is available.
comment-hq/skills/skills/comment-init Skill
1★ repoInitialize or refresh a repo for the `comment-*` skill family. Two layers: (1) the **repo config the skills read** — the `AGENTS.md`/`CLAUDE.md` "Agent Skill Config" pointer plus `docs/DELIVERY.md` (topology, bounded review, and receipts) and `docs/TESTING.md` (focused iteration and final certification), inferred from the repo's build/test setup; and (2) the **architecture docs as comms** — one living "Architecture Overview" comm plus immutable per-decision ADRs in a Team Wiki folder. Idempotent — re-running reconciles existing files/comms instead of duplicating them. Trigger on "set up comment-init / the comment skills for this repo", "set up the testing config", "set up the architecture doc", "get my architecture", "document the architecture", "write an ADR", or "update the architecture overview". Works identically under Codex and Claude Code.
Vertiso/memory-codex/vertiso-memory/skills/handoff Skill
1★ repoWrite a claimable Vertiso Memory handoff when the user asks to end or transfer a work session, invokes /handoff, or affirmatively accepts an agent's offer before switching tools, ending a session, or approaching compaction. Gather past context through the checkpoint workflow and preserve the handoff's decisions and state without requiring a second capture approval.
The same file is in 2 other repositories
Vertiso/memory-cursor/vertiso-memory/skills/handoff Skill
1★ repoWrite a claimable Vertiso Memory handoff when the user asks to end or transfer a work session, invokes /handoff, or affirmatively accepts an agent's offer before switching tools, ending a session, or approaching compaction. Gather past context through the checkpoint workflow and preserve the handoff's decisions and state without requiring a second capture approval.
The same file is in 2 other repositories
cosmefae/claude-skills/skills/write-handoff Skill
1★ repoWrites a HANDOFF.md for the current task. Documents state, relevant files with @path and line ranges, verification commands, and next steps. Use when you need to hand off task context concisely.
Vertiso/memory-claude/vertiso-memory/skills/handoff Skill
1★ repoWrite a claimable Vertiso Memory handoff when the user asks to end or transfer a work session, invokes /handoff, or affirmatively accepts an agent's offer before switching tools, ending a session, or approaching compaction. Gather past context through the checkpoint workflow and preserve the handoff's decisions and state without requiring a second capture approval.
The same file is in 4 other repositories
po4yka/llm-wiki-skills/skills/llm-wiki-archive Skill
1★ repoPrepare an LLM-Wiki for long-term durability and archival. Use when the user wants a wiki to remain readable in 5-10+ years, export opaque stores, preserve raw sources, rebuild indexes, vendor key references, or create an archive manifest.
po4yka/llm-wiki-skills/skills/llm-wiki-capture-pipeline Skill
1★ repoDesign cross-channel capture architecture and named connector runbooks for LLM-Wiki. Use when the user wants an inbox/raw topology, metadata contract, dedupe boundary, triage handoff, privacy defaults, capture-to-ingestion flow, or Telegram/email/Slack/PDF/GitHub/voice connector rules.
po4yka/llm-wiki-skills/skills/llm-wiki-choose Skill
1★ repoHelp a user choose between ready-made LLM-Wiki tools, a local-first workflow, a team rollout, retrieval/GraphRAG systems, or a custom implementation. Use when the user asks what solution fits their needs, whether to use OpenWiki/Obsidian/qmd/GraphRAG, or whether to build their own.
po4yka/llm-wiki-skills/skills/llm-wiki-claim-anchors Skill
1★ repoInsert deterministic claim and source anchor IDs after evidence has been inspected. Use when the user wants stable claim IDs, source anchor IDs, support-label formatting, anchor validation, or reproducible claim references; route missing-evidence investigation to llm-wiki-provenance.
po4yka/llm-wiki-skills/skills/llm-wiki-company-flow-audit Skill
1★ repoMap company/team information flows into an LLM-Wiki adoption plan. Use when the user asks where team knowledge lives, which streams can be automated, how Confluence/Jira/Slack/Drive changes stay synced, how fragile review is, how confidential data is handled, or whether maintenance cost is worth the benefit.
po4yka/llm-wiki-skills/skills/llm-wiki-conflict-resolver Skill
1★ repoHelp resolve contradictions found by wiki-lint, provenance checks, or user review. Use when LLM-Wiki pages disagree about facts, recommendations, tool status, decisions, definitions, or stale claims and the agent should mediate rather than auto-fix truth.
po4yka/llm-wiki-skills/skills/llm-wiki-critique-audit Skill
1★ repoProduce an adversarial risk audit for an LLM-Wiki proposal, domain, vault, rollout, or product plan. Use when the user wants a failure-mode register, bad-fit decision, mitigation plan, residual-risk scorecard, or criticism-first stress test; route short adoption answers to llm-wiki-faq.
po4yka/llm-wiki-skills/skills/llm-wiki-design Skill
1★ repoDesign a custom LLM-Wiki implementation, CLI, Obsidian plugin, repo-docs agent, team workflow, or product architecture. Use when the user wants to build their own system and needs data model, retrieval tier, provenance, storage, sync, review, agent integration, or MVP planning.
po4yka/llm-wiki-skills/skills/llm-wiki-doctor Skill
1★ repoDiagnose an existing vault, docs folder, repository wiki, or Markdown knowledge base before changing files. Use when the user asks what is wrong with their current notes/docs, whether they are LLM-Wiki-ready, or what the safest next step is.
po4yka/llm-wiki-skills/skills/llm-wiki-domain-pack Skill
1★ repoGenerate domain-specific LLM-Wiki templates, taxonomies, domain_type mappings, stale policies, capture rules, and review gates. Use for research papers, codebase docs, startup research, trading research, personal second brain, team onboarding, competitive intelligence, or other specialized domains.
po4yka/llm-wiki-skills/skills/llm-wiki-ecosystem-registry Skill
1★ repoBuild or refresh a current registry of LLM-Wiki implementations and adjacent open-source frameworks. Use when the user asks what projects exist, which technologies are missing, how OpenWiki/nashsu/vouch/RepoAgent compare, or which ready-made implementation to evaluate.
po4yka/llm-wiki-skills/skills/llm-wiki-eval-tooling Skill
1★ repoSelect evaluation tools and CI gates for LLM-Wiki measurement. Use when the user asks which eval framework, dataset format, scorecard file, red-team config, prompt regression test, hosted/self-hosted service, or human calibration workflow to use; route actual pilot runs to llm-wiki-eval.
po4yka/llm-wiki-skills/skills/llm-wiki-eval Skill
1★ repoDefine and execute LLM-Wiki measurement, including bounded pilot benchmarks. Use for usefulness, grounding, maintenance-health, and citation-coverage metrics, baseline vs with-wiki comparison, scoring, and decision gates; route framework/CI choices to llm-wiki-eval-tooling.
po4yka/llm-wiki-skills/skills/llm-wiki-export-publish Skill
1★ repoExport or publish a safe subset of an LLM-Wiki as public docs, an internal handbook, a static site, llms.txt, JSONL/JSON-LD, graph export, or an archive. Use when publishing from the wiki must preserve provenance and exclude private raw sources, sensitive notes, and draft pages.
po4yka/llm-wiki-skills/skills/llm-wiki-faq Skill
1★ repoExplain LLM-Wiki adoption and answer stakeholder objections. Use when the user wants a concise FAQ response, evidence summary, ROI framing, migration answer, or plain-language rebuttal; route adversarial risk registers and bad-fit audits to llm-wiki-critique-audit.
po4yka/llm-wiki-skills/skills/llm-wiki-github-action Skill
1★ repoConfigure GitHub Actions for LLM-Wiki maintenance. Use when the user wants scheduled wiki lint reports, PR-based documentation updates, Agent Skills validation, provenance checks, or safe repo-docs maintenance without direct writes to main.
Llm wiki gitlab operating model
po4yka/llm-wiki-skills/skills/llm-wiki-gitlab-operating-model Skill
1★ repoDesign an LLM-Wiki team operating model for self-hosted GitLab and internal enterprise environments. Use for GitLab Self-Managed or air-gapped contours with groups, merge requests, CODEOWNERS, approval rules, protected branches, CI/CD, LDAP/SAML, RBAC, audit and compliance.
po4yka/llm-wiki-skills/skills/llm-wiki-human-first-design Skill
1★ repoDesign or audit an LLM-Wiki so it remains useful to humans without agents. Use when the user fears an agent-generated document dump or a new Confluence-like mess, or needs human-readable page contracts, navigation maps, and agent-free acceptance tests.
Llm wiki implementation deep dive
po4yka/llm-wiki-skills/skills/llm-wiki-implementation-deep-dive Skill
1★ repoCompare concrete open-source LLM-Wiki implementations at architecture depth. Use when the user asks for implementation deep dives, production readiness, architecture patterns, or what to copy from OpenWiki, nashsu/llm_wiki, Vouch, RepoAgent, llm-wiki-compiler, SwarmVault, Obsidian plugins, or session-transcript wikis.
po4yka/llm-wiki-skills/skills/llm-wiki-ingestion-stack Skill
1★ repoDesign an ingestion and document-conversion stack for LLM-Wiki. Use when PDFs, Office files, web clips, audio/video, code repos, chats, scans, or tables must become source-preserving Markdown, or for source manifests, incremental sync, golden corpora, and ingestion evals.
po4yka/llm-wiki-skills/skills/llm-wiki-interview Skill
1★ repoExtract tacit knowledge into an LLM-Wiki through an agent-led interview. Use when the wiki has open questions, weak areas, onboarding gaps, undocumented decisions, or the user wants voice/text answers turned into draft pages without pretending they are sourced facts.
po4yka/llm-wiki-skills/skills/llm-wiki-local-first-stack Skill
1★ repoDesign a local-first LLM-Wiki stack. Use when the user wants Markdown, git, Obsidian, ripgrep, local embeddings, qmd-style retrieval, SQLite/FTS/vector indexes, local LLMs, offline operation, or safe sync without cloud lock-in; route retrieval/index layer design to llm-wiki-retrieval-architect.
po4yka/llm-wiki-skills/skills/llm-wiki-mcp-integration Skill
1★ repoDesign or review MCP/API integration for an LLM-Wiki. Use when the user wants agents such as Claude Code, Codex, Cursor, ChatGPT, VS Code, GitHub Copilot, LangGraph or other MCP clients to search, read, lint, rescan, propose, review or export wiki knowledge through MCP or a local/remote API.
po4yka/llm-wiki-skills/skills/llm-wiki-migration-planner Skill
1★ repoCreate a no-write migration plan for turning existing notes, docs, Obsidian vaults, Notion exports, research archives, or repository documentation into an LLM-Wiki. Use when the user wants a dry-run plan before moving or editing files; route applying the approved plan to llm-wiki-refactor.
po4yka/llm-wiki-skills/skills/llm-wiki-model-policy Skill
1★ repoDefine model and data-use policy for LLM-Wiki workflows. Use when the user asks which models/providers can process which sources, what must stay local, how to split cheap/heavy models, or how to record model provenance in wiki frontmatter.
po4yka/llm-wiki-skills/skills/llm-wiki-news-radar Skill
1★ repoFind and summarize fresh news, releases, papers, repositories, standards, and technologies related to LLM-Wiki, wiki memory, OpenWiki, Agent Skills, agent memory, RAG/GraphRAG, local-first knowledge tools, and coding-agent knowledge workflows. Use when the user asks for latest/current/recent ecosystem updates.
po4yka/llm-wiki-skills/skills/llm-wiki-obsidian-hardening Skill
1★ repoHarden an Obsidian vault for coding-agent and LLM-Wiki workflows. Use when the user wants Claude Code, Codex, Cursor, or other agents to edit an Obsidian vault without breaking wikilinks, attachments, frontmatter, sync, or human-owned synthesis.
po4yka/llm-wiki-skills/skills/llm-wiki-orient Skill
1★ repoExplain the LLM-Wiki pattern, its raw/wiki/schema architecture, how it differs from RAG, GraphRAG and agent memory, and what ready-made solution families exist. Use when the user asks what LLM-Wiki is, whether it is worth adopting, what OpenWiki/wiki memory means, or how the ecosystem fits together.
po4yka/llm-wiki-skills/skills/llm-wiki-paf-adoption Skill
1★ repoAnswer questions that map LLM-Wiki to Product Architecture Framework concepts such as Nexus, Cortex, Product Engineer, Product Ops, Context Ripeness, Confidence Point. Use when the user asks whether LLM-Wiki is a Nexus/Cortex, how to start or share a company-level Nexus, or how to measure decision impact.
po4yka/llm-wiki-skills/skills/llm-wiki-privacy-redactor Skill
1★ repoPreview and plan redaction of private or sensitive content before publishing, exporting, or sending LLM-Wiki context to external models. Use for emails, tokens, internal URLs, phone numbers, private tags, and sensitive page metadata.
po4yka/llm-wiki-skills/skills/llm-wiki-provenance Skill
1★ repoInspect and repair evidence links before adding stable IDs. Use when pages have unsupported claims, generated summaries cite other summaries, raw-source links are missing, support labels are wrong, or the user wants a provenance gap report; route deterministic ID insertion to llm-wiki-claim-anchors.
po4yka/llm-wiki-skills/skills/llm-wiki-refactor Skill
1★ repoRefactor an existing docs folder, Obsidian vault, or messy note collection into an LLM-Wiki structure. Use for applying an approved migration plan, with frontmatter normalization, raw/wiki separation, link repair, and review-safe restructuring; route no-write migration planning to llm-wiki-migration-planner.
po4yka/llm-wiki-skills/skills/llm-wiki-repo-docs Skill
1★ repoBuild or maintain an LLM-Wiki for codebase documentation. Use when the user wants agent-readable repo docs, architecture maps, module pages, ADR links, OpenWiki-style output, or AGENTS.md/CLAUDE.md pointer patterns for Claude Code, Codex, Cursor, or other coding agents.
po4yka/llm-wiki-skills/skills/llm-wiki-retrieval-architect Skill
1★ repoDesign the retrieval/indexing layer for an LLM-Wiki. Use for lexical/FTS search, BM25, hybrid retrieval, vector databases, rerankers, metadata filters, or GraphRAG, or when `rg`/index.md no longer retrieves enough context; route whole-stack local-first tooling choices to llm-wiki-local-first-stack.
po4yka/llm-wiki-skills/skills/llm-wiki-security-review Skill
1★ repoReview an existing LLM-Wiki or Agent Skills setup for practical security gaps. Use when the user asks whether current permissions, MCP/API exposure, exports, cloud-model use, or data boundaries are safe enough; route new architecture threat modeling to llm-wiki-threat-model.
po4yka/llm-wiki-skills/skills/llm-wiki-setup Skill
1★ repoInstall, configure, and connect a chosen LLM-Wiki workflow. Use for setting up a raw/wiki/schema vault, Agent Skills, coding-agent integration, Obsidian/local-first workflows, hooks, templates, or git review; route a guided first-demo walkthrough to llm-wiki-zero-to-working-wiki.
po4yka/llm-wiki-skills/skills/llm-wiki-skill-compiler Skill
1★ repoCompile procedural knowledge from an LLM-Wiki into installable Agent Skills. Use when wiki pages, runbooks, checklists, recurring workflows, troubleshooting notes, or query answers should become SKILL.md files with evidence links and validation.
po4yka/llm-wiki-skills/skills/llm-wiki-skill-doctor Skill
1★ repoAudit Agent Skills in this repository or a user's project for quality, trigger clarity, overlap, unsafe permissions, stale facts, supply-chain risk, and skill smells. Use when authoring, reviewing, or preparing SKILL.md files for distribution.
po4yka/llm-wiki-skills/skills/llm-wiki-source-refresh Skill
1★ repoRe-check stale or time-sensitive LLM-Wiki sources and create refresh reports or review patches. Use when stale_after is reached, current ecosystem facts may have changed, links are dead, or wiki pages need source freshness review.
po4yka/llm-wiki-skills/skills/llm-wiki-team-rollout Skill
1★ repoPlan and implement LLM-Wiki adoption for a team or company. Use for onboarding knowledge, bus factor, repo docs, decision records, PR-based agent writes, CODEOWNERS, permissions, governance, RACI/DACI, SLOs, review queues, team rituals, staffing, dashboards, security boundaries and operating models.
po4yka/llm-wiki-skills/skills/llm-wiki-threat-model Skill
1★ repoBuild a formal security architecture threat model for an LLM-Wiki system. Use when the user asks for STRIDE, LINDDUN, PASTA, data-flow diagrams, trust boundaries, attack-surface mapping, abuse cases, risk matrices, red-team scenarios, or control baselines; route existing-config safety reviews to llm-wiki-security-review.
po4yka/llm-wiki-skills/skills/llm-wiki-trust-audit Skill
1★ repoAudit an LLM-Wiki system for anti-slop controls such as provenance, review gates, protected human synthesis, stale claims, and unsafe agent write permissions. Use when the user asks whether their wiki can be trusted; route setup/permission safety reviews to llm-wiki-security-review and proposal risk audits to llm-wiki-critique-audit.
po4yka/llm-wiki-skills/skills/llm-wiki-zero-to-working-wiki Skill
1★ repoCreate a first useful LLM-Wiki from zero. Use when the user wants a zero-to-working-wiki walkthrough, first vault, first source ingest, first reusable query, first lint report, or a visible demo loop before a larger rollout; route full workflow installs to llm-wiki-setup.
Paldom/llm-council-skills/skills/llm-council-aggregation Skill
1★ repoCombines multiple LLM answers or judge verdicts robustly - correlated-error limits of majority voting, reliability weighting, side-swapped pairwise comparison, judge-synthesizer separation, and surfacing dissent. Use for "combine/aggregate model outputs", "LLM judge panel/jury", "majority vote across models", "rank council responses". Not for pipeline topology, member choice, or stage prompts.
Paldom/llm-council-skills/skills/llm-council-architecture Skill
1★ repoDesigns LLM council orchestration - parallel fan-out, anonymized peer review, chairman synthesis, topology choice by task shape, debate round caps, stopping rules, graceful degradation. Use for "build/design an LLM council", "multi-model deliberation architecture", "structure a debate/review/synthesis pipeline". Not for member selection, prompt wording, aggregation math, or cost tuning.
Paldom/llm-council-skills/skills/llm-council-cost Skill
1★ repoCuts cost and latency of multi-model LLM pipelines - route-first gating so the council fires only on hard queries, calibrated-confidence escalation, prompt caching, batching, tail-latency budgeting. Use for "the council/ensemble is too expensive or slow", "route to a cheaper model then escalate", "reduce multi-LLM cost". Not for deciding whether to adopt a council or aggregation choice.
Paldom/llm-council-skills/skills/llm-council-failure-modes Skill
1★ repoDefends LLM councils against failure modes - sycophancy and groupthink (structured dissent, round caps, no early-stop-on-consensus), correlated-error monitoring, and prompt-injection amplification containment. Use for "models keep agreeing", "council groupthink", "multi-agent prompt injection", "consensus feels fake". Not for single-agent jailbreak hardening or member selection.
Paldom/llm-council-skills/skills/llm-council-harness Skill
1★ repoImplements an LLM council over headless coding harnesses in plain Python - one router over Claude Code, Codex CLI, and API models, subprocess hygiene, JSON contracts with tolerant extraction, per-member failure isolation, boss-synthesis fallback. Use for "council of Claude Code/Codex CLIs", "run coding agents headless as council members". Not for API-only orchestration frameworks.
Paldom/llm-council-skills/skills/llm-council-members Skill
1★ repoSelects and role-designs LLM council members - provider-diverse 3-5 model panels, cognitive lenses over personas, role-to-model routing, anonymization and identity effects, persona-drift countermeasures. Use for "which models should sit on the council", "pick council members", "design advisor personas/lenses". Not for pipeline topology, aggregation math, or stage prompt wording.