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.
49,466 skills from 2,407 repositories · updated 15 minutes ago
49,464 skills
- cicd-playbookmohitagw15856/pm-claude-skillsWrite a CI/CD pipeline playbook for a service or team. Use when asked to document a CI/CD pipeline, write a deployment process, define release gates, document build and test stages, or create a deployment guide. Produces a structured playbook covering pipeline stages, environment definitions, deployment gates, rollback procedures, and on-call responsibilities.TestingNo warnings★ 1.5K↓ —
- wacv-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing WACV experiments, covering Applications-track systems evidence (latency, power, robustness under real constraints) versus Algorithms-track matched-baseline novelty, comparative assessment under the deployed condition, uncertainty over seeds and sessions, ablations, and evidence that survives the two-round review.DevOpsNo warnings★ 1.4K↓ —
- second-brain-graphundefined-ui/second-brain-osAnalyse the vault's link graph and report on its shape: orphan rate, average degree, components, hubs, bridges and clusters, with what each number means for retrieval. Use this skill when the user asks about the health or structure of their graph, wants metrics, asks which pages are most connected or most isolated, or asks whether the vault is fragmented. Do NOT use for fixing what it finds, which is second-brain-lint, or for answering a content question.OtherNo warnings★ 1.4K↓ —
- brief-buildermohitagw15856/pm-claude-skillsInterview the user with sharp, one-at-a-time questions to turn a vague request into a tight, complete brief any other skill can run on. Use when a request is fuzzy, under-specified, or 'help me think this through', or before running a skill that needs inputs the user hasn't given. Produces a structured brief (goal, audience, constraints, success criteria) and hands off to the right skill — by interrogating, not guessing.PlanningNo warnings★ 1.5K↓ —
- email-lifecycle-lifecycle-auditgooseworks-ai/goose-skillsStep of the email-lifecycle playbook: audits list, consent, live flows, recent sends and sending setup, marking every item verified, from-you or unknown. Run email-lifecycle instead; not for direct use.ProductivityNo warnings★ 1.3K↓ —
- vis-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when revising an IEEE VIS paper for a task-grounded visualization contribution on the first page, a design rationale that ties each visual encoding and interaction to a task, evaluation matched to the contribution type, honest limitations, and disciplined use of the VGTC/TVCG 9+2 page budget for a paper that will be read as an IEEE TVCG journal article.WritingNo warnings★ 1.4K↓ —
- aaai-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when preparing an accepted AAAI paper for camera-ready source submission to AAAI Press, including proceedings page limits, two-column template compliance, copyright transfer, purchased extra technical pages, deanonymization, registration, oral or poster presentation, and final public artifact release.ScienceNo warnings★ 1.4K↓ —
- doca-rmaxNVIDIA/skillsDOCA Rivermax (doca_rmax) receive streams for timing-precise media over IP (SMPTE ST 2110 video / audio, market data, scientific feeds) on a target BlueField DPU (DOCA Rivermax apps run only there), once the Rivermax libraries and license are installed; getting them is doca-setup / doca-public-knowledge-map territory. Trigger on "ST 2110 receive isn't getting frames", "sub-microsecond jitter on my media receiver", "NOT_SUPPORTED from doca_rmax_init", "no recv events after stream start", or "license check failing on a media receiver", even without naming Rivermax. Covers doca_rmax_in_stream sessions, the SDK + license precondition check, doca_rmax_get_*_supported capability queries, pairing with doca-eth queues and doca-flow steering, and DOCA_ERROR_* from Rivermax calls. Refuse and route elsewhere for programming the underlying queue (doca-eth), steering rules (doca-flow), PTP / clock sync (doca-firefly), or best-effort packet I/O.MediaNo warnings★ 3.9K↓ —
- ase-review-processbrycewang-stanford/Awesome-Journal-SkillsUse when reasoning about how an ASE (IEEE/ACM Automated Software Engineering) research submission is evaluated, covering double-anonymous review, the early-rejection stage before rebuttal, the Accept / Revision / Reject outcomes, the criteria-bound revision round, and how ASE's process differs from FSE's PACMSE Major Revision, ICSE's cycles, and ISSTA's rounds.EngineeringNo warnings★ 1.4K↓ —
- second-brain-lintundefined-ui/second-brain-osAudit a second-brain vault for structural problems and repair them: broken wikilinks, orphan pages, empty stubs, frontmatter that violates the schema, near-duplicate pages, and stale index entries. Use this skill whenever the user asks to lint, clean, audit or check the health of their vault, says pages feel messy or links are broken, after a large bulk import, or when a scheduled maintenance run fires. Do NOT use for ingesting new sources, for answering questions from the vault, or for rewriting page content that is structurally fine but reads badly.OtherNo warnings★ 1.4K↓ —
- cikm-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when turning an accepted CIKM paper into its ACM proceedings version inside the short notification-to-camera-ready window, covering de-anonymization, the e-rights and TAPS pipeline into the ACM Digital Library, CCS concepts and metadata, GenAI-disclosure retention, artifact link publication, and Rome presentation logistics.ScienceNo warnings★ 1.4K↓ —
- paid-adsalirezarezvani/claude-skillsUse for paid campaign strategy on Google, Meta, LinkedIn or X: structure, targeting, bids, retargeting and budgets. Scores account health with ad_health_scorer.py and models ROAS with roas_calculator.py. Ad copy only: ad-creative.MarketingNo warnings★ 29.3K↓ —
- 00-academic-routeragentscope-ai/OpenJudgeUse when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.ScienceNo warnings★ 1.1K↓ —
- asplos-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning an ASPLOS campaign across the two-deadline cycle — sequencing evidence building, the September 9, 2026 submission gate, author-response windows, the December 21 notification, Major Revision resubmission six weeks later, artifact evaluation, and the April 2027 conference in Crete, with owners per risk.ProductivityNo warnings★ 1.4K↓ —
- plan-campaigngooseworks-ai/goose-skillsCampaign planner: turns a product, offer, goal, budget and date into a plan the marketer can approve and a designer can start from today, with every channel kept or dropped for a reason. Zero paid is a valid answer; it never spends. Use when the ask names a campaign, a launch, drop or season push, a budget or a date: I have this budget and a launch date — what do I run, where?; plan my launch, drop or Black Friday push; plan a campaign; how should I split $5k; plan next month's campaign; our CAC blew up — replan. Not for a broad "grow my brand", "get more customers" or "where do I start" with no campaign, budget or date — use where-to-start; not for pausing ads on a sold-out product — use run-paid-campaigns; not for an email-only send plan — use email-lifecycle; not for reading this week's numbers — use analyze-performance.MarketingNo warnings★ 1.3K↓ —
- claims-gategooseworks-ai/goose-skillsChecks every claim in a piece of copy (ads, emails, posts, pages, scripts, briefs) against the claims the brand has approved. Keeps, rewrites or cuts each line, and lists the proof that would bring a cut line back. When a line the copy needs has no approval, it asks for a short sign-off on the 3 or 4 lines that matter and records the answer. Use alone when you already have the copy and a brand set up; otherwise run the playbook for the job (e.g. make-static-ads, make-content, write-outreach).MarketingNo warnings★ 1.3K↓ —
- metric-designagentscope-ai/OpenJudgeUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.DesignNo warnings★ 1.1K↓ —
- cell-star-methodsbrycewang-stanford/Awesome-Journal-SkillsUse to build Cell's mandatory STAR Methods — the Key Resources Table, the three Resource Availability subsections, Experimental Model and Subject Details, Method Details, and Quantification and Statistical Analysis, in the exact required order.OtherNo warnings★ 1.4K↓ —
- atc-review-processbrycewang-stanford/Awesome-Journal-SkillsUse when reasoning about how an ATC (ACM SIGOPS Annual Technical Conference, formerly USENIX ATC) submission is evaluated — the two-round extended-abstract model, the round-one gate by two reviewers, the round-two read by 3-4 reviewers, double-blind reviewing, rebuttal, conditional acceptance with shepherding, and how ATC differs from OSDI/SOSP/NSDI.EngineeringNo warnings★ 1.4K↓ —
- exportNewChatCut-Inc/agent-pluginExport, render, download, or deliver a ChatCut timeline from WorkBuddy as video, audio, subtitles, Premiere Pro or DaVinci Resolve-compatible project files, or a motion-graphic render.MediaNo warnings★ 1K↓ —
- 01-paper-reviewagentscope-ai/OpenJudgeReview academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.ScienceNo warnings★ 1.1K↓ —
- ui-regressionfcakyon/claude-codex-settingsThis skill should be used when the user asks to "verify UI changes", "audit UI quality", "test every screen and action", "run regression QA", "check a deployed UI", or "validate an extension release". Test known web and browser-extension workflows on localhost, staging, or production with action coverage, recovery, localization, accessibility, and real integration evidence. Use dogfood for open-ended bug discovery.DesignNo warnings★ 1.2K↓ —
- researchalirezarezvani/claude-skillsUse for any research request that doesn't clearly match a research specialist ('research X', 'look into Y'). Routes with classifier.py to pulse, grants, litreview, syllabus, patent, dossier or deepread, or runs its own cited search.ScienceNo warnings★ 29.3K↓ —
- patentalirezarezvani/claude-skillsUse for prior-art search, freedom-to-operate, patent landscape, acquisition diligence or litigation prior art. Picks the use case with sub_use_case_router.py, searches Google Patents, Espacenet and USPTO and writes a .docx; not legal advice.DocumentsNo warnings★ 29.3K↓ —
ai-eval-plan
mohitagw15856/pm-claude-skills
PlanningUpdated 6 hours ago
From the author
Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human evals, a pass bar, and a regression gate.
Install
npx skills add mohitagw15856/pm-claude-skills --skill ai-eval-plan -a claude-code
Installs to .claude/skills/ai-eval-plan/ · 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 onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance78
Maintenance100
Licence100
Adoption51
Files (1)
- SKILL.md