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.
49,495 skills from 2,391 repositories · updated 24 minutes ago
48,453 skills
- implementing-domain-driven-designciembor/agent-rules-booksApply Vaughn Vernon-inspired implementation DDD rules when building aggregates, domain events, repositories, application services, or context integrations.DesignNo warnings★ 3.2K↓ —
- domain-driven-designciembor/agent-rules-booksApply Eric Evans-inspired DDD rules when modeling a complex domain, defining bounded contexts, protecting ubiquitous language, or designing aggregates.DesignNo warnings★ 3.2K↓ —
- domain-driven-design-distilledciembor/agent-rules-booksApply Vaughn Vernon-inspired lightweight DDD rules when using bounded contexts, subdomains, context maps, and tactical modeling without excess ceremony.DesignNo warnings★ 3.2K↓ —
- sci-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when deciding which sci-* sub-skill to invoke next, or when sequencing a manuscript from significance test through reviewer rebuttal for Science (AAAS). Routes — it does not replace — the specialized skills.ProductivityNo warnings★ 1.4K↓ —
- sharpenNewhashgraph-online/awesome-codex-pluginsRewrite a draft prompt so it asks for an expert-depth version of the same task (expert moves, raw sources, named methods, an outside check) without widening scope. Returns the rewritten prompt and does not do the task. Use for "/sharpen <prompt>" or "make this prompt better before I send it".ProductivityNo warnings★ 1.5K↓ —
- release-itciembor/agent-rules-booksApply Michael T. Nygard-inspired production reliability rules when designing failure handling, timeouts, retries, circuit breakers, observability, or deployment behavior.DevOpsNo warnings★ 3.2K↓ —
- rss-camera-readybrycewang-stanford/Awesome-Journal-SkillsJournal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能包，从选题、识别策略到表格规范与审稿回复全流程，助你快速发论文。PlanningNo warnings★ 1.4K↓ —
- clean-codeciembor/agent-rules-booksApply Robert C. Martin-inspired clean code rules when improving readability, naming, function design, responsibilities, or testable everyday code.EngineeringNo warnings★ 3.2K↓ —
- ppopp-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a PPoPP submission campaign end to end, sequencing the summer paper deadline, the author-response rebuttal window, notification, the post-acceptance CGO-shared artifact-evaluation round, the camera-ready, and the presentation inside the co-located HPCA/CGO/PPoPP/CC week.ProductivityNo warnings★ 1.4K↓ —
- pods-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ACM PODS research submission for EasyChair readiness, covering the chosen cycle's abstract-then-paper deadlines, the acmsmall[review,anonymous] format and 15-page budget, the at-submission proof appendix, lightweight double-anonymity, the declared conflicts of interest, PACMMOD-track publication, and desk-risk triage before the AoE cutoff.ScienceNo warnings★ 1.4K↓ —
- youtube-playlistZeroPointRepo/youtube-skillsUse when a YouTube playlist is involved: pasted playlist links or IDs, requests to list playlist videos, browse playlist contents, or work through a playlist for transcripts or research. Also use when the user wants all videos from a series, course, or collection. Not for creating playlists or account management.ScienceNo warnings★ 1.2K↓ —
- os-step-by-stepkharmanskyi/open-stepsALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever they ask how to do something or say they do not know what to do: "step by step", "walk me through it", "what do I do", "what should I do", "I don't understand what to do", "explain what I need to do", in any language. Picking which task comes next is os-whats-next; this skill is for doing the thing in front of you. First earn the ask: try it yourself, find another route, shrink it to the part only they can do. Then one action per step, commands labelled by what they touch, no jargon. Commands are single lines that prompt for any value - typing hidden for secrets - and confirm in plain words. Afterwards verify their step.ProductivityNo warnings★ 1.3K↓ —
- research-competitorsgooseworks-ai/goose-skillsCompetitor research: what every main rival is running, launching, charging and saying now, what works for them, and what that means for you. Use when the marketer asks for competitor research or a teardown, "what ads are my competitors running", "how do they price", "find gaps and angles", "what changed this week" (a weekly watch), or "X just launched / shut down / cut prices" (react now). Also builds a sales battlecard, checks a competitor page's tools/pixels, or studies who engages with their LinkedIn posts. Delivers a readable report saved to the brand, so the next run reports what changed. Never copies their words or disparages them. Not for what people say about you or your market — use research-market; not for who your buyers are — use research-audience.ScienceNo warnings★ 1.3K↓ —
- os-check-workkharmanskyi/open-stepsALWAYS invoke this skill when the user asks about work done outside this session - "check work", "check the others", "check other sessions" - or to accept one: "the session is done, check it", "can we merge it" - in any language. You are the receiving party: treat the report as a claim, verify each part against machine state, name every gap between claimed and true. Verified-ready work merges in the same pass. End with what is left, one next step, and any reply another session needs, ready to paste.OtherNo warnings★ 1.3K↓ —
- cell-citationbrycewang-stanford/Awesome-Journal-SkillsUse to convert references to Cell Press author–date style — in-text "(Smith et al., 2021)", an alphabetical reference list by first author with full author lists, journal names spelled out. This is the OPPOSITE of Science's numbered-by-appearance style.ScienceNo warnings★ 1.4K↓ —
- asc-release-flowrorkai/app-store-connect-cli-skillsOrchestrate App Store releases with asc, including staging a version, uploading or building an artifact, publishing, and submitting for review. Use when the user wants to prepare or execute a release. Keep Game Center item preparation in this skill; route other readiness failures, stuck submissions, cancellation, and retry decisions to asc-submission-health.EngineeringNo warnings★ 1.1K↓ —
- cav-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a CAV (Computer Aided Verification) submission for portal readiness, covering the four submission categories (Regular / Short Tool / Short Application / Industrial Experience & Case Studies), the LNCS page limits, the per-category anonymization matrix, the artifact-intent declaration, and desk-reject triage before the AoE paper deadline.ScienceNo warnings★ 1.4K↓ —
- ap-jurorSpielewoy/autoprompt-skillReport the compatibility redirect to `ap-independent-checker`; this retired role cannot perform new work.OtherNo warnings★ 1.2K↓ —
- review-prfcakyon/claude-codex-settingsThis skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PREngineeringNo warnings★ 1.2K↓ —
- asc-xcode-buildrorkai/app-store-connect-cli-skillsBuild, archive, export, and manage Xcode version/build numbers with asc, including portable iOS compilation and packaging. Use when creating an IPA or PKG for App Store Connect, TestFlight, or registered-device release testing.TestingNo warnings★ 1.1K↓ —
- asc-crash-triagerorkai/app-store-connect-cli-skillsTriage TestFlight crashes, beta feedback, and performance diagnostics using asc. Use when the user asks about TF crashes, TestFlight crash reports, beta tester feedback, app hangs, disk writes, launch diagnostics, or wants a crash summary for a build or app.WritingNo warnings★ 1.1K↓ —
- soda-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when preparing or auditing a SODA (ACM-SIAM Symposium on Discrete Algorithms) submission — the no-page-limit full-version norm, the title-page abstract, 11-point single-column letter format, lightweight double-blind rules, HotCRP entry, and the July AoE deadline with its summary-rejection triggers.ProductivityNo warnings★ 1.4K↓ —
- metronomefcakyon/claude-codex-settingsGuides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products), invoicing lifecycle (grace periods, finalization, Stripe sync), credit and commit management (prepaid, postpaid, thresholds, auto-recharge), and Stripe integration (arrears invoicing, tax providers, line item limits). Use when building, modifying, or reviewing any Metronome integration — including ingesting usage events, creating customers, contracts, or rate cards, designing billable metric group keys, managing credits and commits, configuring invoicing, syncing invoices with Stripe Billing, billing AI applications for token usage, setting up self-serve (PLG) pricing, reviewing customer health, commit burn, portfolios, or renewals, or migrating from Stripe Billing Meters to Metronome.DesignNo warnings★ 1.2K↓ —
- youtube-dataZeroPointRepo/youtube-skillsUse when structured YouTube data is needed: pasted video/channel/playlist links, transcripts for analysis, video metadata, channel upload history, search results, or playlist contents — without Google API quotas or OAuth. Triggers on YouTube URLs, creator names, topic research, or any request needing YouTube content, even if not mentioned explicitly. Not for uploads, account management, or written-source-only research.MediaNo warnings★ 1.2K↓ —
huggingface-community-evals
huggingface/skills
OfficialOtherUpdated 5 days ago
From the author
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Install
npx skills add huggingface/skills --skill huggingface-community-evals -a claude-code
Installs to .claude/skills/huggingface-community-evals/ · 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
Runs bundled scriptsNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 88
Security85
Provenance100
Maintenance100
Licence100
Adoption63
Files (6)
- SKILL.md
- examples/.env.example
- examples/USAGE_EXAMPLES.md
- scripts/inspect_eval_uv.py
- scripts/inspect_vllm_uv.py
- scripts/lighteval_vllm_uv.py