Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,418 skills from 2,407 repositories · updated 17 minutes ago
49,416 skills
- meta-evalagentscope-ai/OpenJudgeUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.TestingNo warnings★ 1.1K↓ —
- establishing-project-contextGanyuanRan/AegisUse when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.ProductivityNo warnings★ 1.4K↓ —
- aeoalirezarezvani/claude-skillsUse when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.OtherNo warnings★ 29.3K↓ —Also in 1 other repo
- analyze-objectsmicrosoft/power-platform-skillsUse when analyzing interacting object types, object-centric processes, leading-object executions or cross-object delay.OtherNo warnings★ 1.1K↓ —
- arcmirahashgraph-online/awesome-codex-pluginsAnswers what YouTube shows and podcasts said: transcripts, who was mentioned, sponsors, recommendations, momentum. Use for the arcmira MCP server or CLI.EngineeringNo warnings★ 1.5K↓ —
- analyze-driversmicrosoft/power-platform-skillsUse when seeking explanatory attributes or hypotheses for differences in process duration, waiting, utilization or rework.OtherNo warnings★ 1.1K↓ —
- 00-arena-routeragentscope-ai/OpenJudgeUse when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.PlanningNo warnings★ 1.1K↓ —
- communicating-conciselyGanyuanRan/AegisUse when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.OtherNo warnings★ 1.4K↓ —
- openspec-archive-changeMemeMeow-Studio/MemeMeowArchive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.ProductivityNo warnings★ 1.3K↓ —Also in 1 other repo
- anti-entropy-governanceGanyuanRan/AegisUse when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.OtherNo warnings★ 1.4K↓ —
- ui-ux-governanceGanyuanRan/AegisUse when designing, changing, or reviewing user-facing interfaces or interaction flows, including API changes that alter visible states or recovery. Backend-only work without user-facing effects stays on its existing route.DesignNo warnings★ 1.4K↓ —
- nanoresearch-planningOpenRaiser/NanoResearchProduce an experiment blueprint from a research hypothesisPlanningNo warnings★ 1.3K↓ —
- openspec-exploreMemeMeow-Studio/MemeMeowEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.FinanceNo warnings★ 1.3K↓ —
- openspec-sync-specsMemeMeow-Studio/MemeMeowSync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.PlanningNo warnings★ 1.3K↓ —
- mariadb-operator-commentmariadb-operator/mariadb-operatorPost a comment (or a formal PR review) to a GitHub issue or pull request in mariadb-operator/mariadb-operator. Use whenever the user wants to publish something to GitHub for this repo — "comment on issue #123", "post this as a PR comment", "leave a note on #456", "reply on the PR" — and especially when they want the output of the mariadb-operator-pr-review skill delivered to GitHub instead of just shown in chat, e.g. "review PR #1234 and post it as a comment" or "post the review results to the PR". Always confirms the exact comment text with the user before publishing — never posts autonomously.EngineeringNo warnings★ 1K↓ —
- catch-upNewhashgraph-online/awesome-codex-pluginsBrief the user in plain language on what happened in this conversation since their last typed message, with pictures where they help, then lay out every decision waiting on them with a recommendation, evidence and risk. Use when the user runs /catch-up.OtherNo warnings★ 1.5K↓ —
- routerhashgraph-online/awesome-codex-pluginsFind the right doc before reading code. Use when asked "where is X documented", "is there a spec/ADR for X", "what's the roadmap", "open bugs", "read the docs about X", or "share the docs".PlanningNo warnings★ 1.5K↓ —
- new-skillhyhmrright/brooks-lintScaffold a new brooks-lint analysis skill so it passes `npm run validate` and `npm run evals` on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends paired eval scenarios. Triggers when the maintainer asks to "add a new skill", "scaffold a skill", or "create a brooks-lint mode". Do NOT trigger for: editing an existing skill's content, adding a single eval to an existing skill, or authoring skills for some other plugin.WritingNo warnings★ 1.6K↓ —
- goal-framingGanyuanRan/AegisUse when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.ProductivityNo warnings★ 1.4K↓ —
- openspec-sync-specsMemeMeow-Studio/MemeMeowSync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.PlanningNo warnings★ 1.3K↓ —
- openspec-sync-specsMemeMeow-Studio/MemeMeowSync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.PlanningNo warnings★ 1.3K↓ —
- using-aegisGanyuanRan/AegisUse when starting a turn or checking Aegis skill routing.OtherNo warnings★ 1.4K↓ —
- mariadb-operator-release-notesmariadb-operator/mariadb-operatorCreate the release notes and upgrade guide for a mariadb-operator release. Given the release PR whose body lists every PR included in the release, it gathers each PR, groups the changes by relevance, and produces `docs/releases/RELEASE_<version>_HEADER.md.gotmpl` and `docs/releases/UPGRADE_<version>.md` in the format the previous releases use, then opens a PR targeting `release-<version>`. If no release PR is provided it asks for the new version and infers the changes from git history since the last tag. Use whenever the user wants release notes, an upgrade/update guide, or docs for a new mariadb-operator version — "create the release notes for 26.10.0", "write the upgrade guide", "document this release", "prepare the release PR docs" — even if they don't mention a release PR.ProductivityNo warnings★ 1K↓ —
- receiving-code-reviewGanyuanRan/AegisUse when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.EngineeringNo warnings★ 1.4K↓ —
ultragoal
huytieu/COG-second-brain
OtherUpdated Oct 23, 2026
From the author
Run a large, multi-session goal (e.g. shipping a whole side product) through the full V-model closed loop, one phase at a time, with cross-session state and a final north-star acceptance gate. Ultragoals never downgrade the lane: every phase runs CP-1→CP-6 with adversarial verification. Opt-in: invoke with /ultragoal or by calling something a long-running goal. Ordinary work does not run this.
Install
npx skills add huytieu/COG-second-brain --skill ultragoal -a claude-code
Installs to .claude/skills/ultragoal/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance77
Maintenance100
Licence100
Adoption50
Files (1)
- SKILL.md