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.
49,105 skills from 2,358 repositories · updated 15 hours ago
48,055 skills
- oma-voicefirst-fluke/oh-my-agentGenerate or transcribe speech with Voicebox or VoiceStudio, or process existing audio locally. Use for narration, transcripts, timed speech, and loudness conversion; video editing uses oma-video.MediaNo warnings★ 1.4K↓ —
- slo-architectalirezarezvani/claude-skillsUse when defining or reviewing SLOs, SLIs, error budgets or burn-rate alerts. Designs SLOs with slo_designer.py, computes budgets and multi-window burn-rate thresholds with error_budget_calculator.py and catches common SLO bugs with slo_review.py.PlanningNo warnings★ 29.2K↓ —
- asc-whats-new-writerrorkai/app-store-connect-cli-skillsGenerate engaging, localized App Store release notes (What's New) from git log, bullet points, or free text using canonical metadata under `./metadata`. Optionally pairs with promotional text updates.WritingNo warnings★ 1.1K↓ —
- minutes-debriefsilverstein/minutesPost-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- hf-cloud-serving-image-selectionhuggingface/skillsPick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.OfficialMediaNo warnings★ 11.3K↓ —
- fse-writing-stylebrycewang-stanford/Awesome-Journal-SkillsUse when revising an ESEC/FSE paper for a practitioner-grounded software-engineering contribution on the first page, research-question contracts, a threats-to-validity section that argues rather than recites, evidence proportional to the claim, double-anonymous wording, and disciplined use of the ACM-template page budget.WritingNo warnings★ 1.4K↓ —
- nsdi-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the evaluation of an NSDI submission — choosing traces, testbeds, and deployment evidence, sizing scale and failure-injection experiments, picking baselines that fight back, and reporting tail behavior so networked-systems reviewers can see where the design wins, loses, and breaks.DevOpsNo warnings★ 1.4K↓ —
- kdd-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when splitting a KDD paper across its 8 content pages, the optional appendix after the references, and the cited repository, under the camera-ready rule capping references plus appendix at 3 of 12 pages. Covers appendix triage, reviewer-discretion reality, and the one-page cross-cycle resubmission change summary.ScienceNo warnings★ 1.4K↓ —
- fixing-flaky-testsamplifthq/openmeldGuides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when `hogli ci:insights` or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a flaky job, when asked to check Trunk Flaky Tests for a test, PR, or master, or when asked to deflake, stabilize, or fix a flaky Jest, pytest, or Playwright test. Core discipline: reproduce locally before changing anything, fix the root cause (never mask it with sleeps, retries, or bigger timeouts), and prove the fix with an N-run validation loop sized to the observed failure rate. Stabilizing is not the only valid outcome — the skill also gates whether the test should exist, so deleting a test that catches nothing real, or re-leveling one that flakes because of the level it runs at, are first-class endings.TestingNo warnings★ 1.4K↓ —
- uai-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when splitting a UAI paper between the 8-page main part, the unlimited in-PDF appendix for proofs and protocols, and the optional 50 MB supplementary ZIP, deciding what reviewers must see in the body versus what may sit in material they are not required to read, all under double-blind and single-file constraints.DocumentsNo warnings★ 1.4K↓ —
- pitch-vs-teachmohitagw15856/pm-claude-skillsKnow which talk you're giving — the pitch (drive one decision) vs. the teach (build understanding) — because mixing their structures fails both, and most bad presentations are one wearing the other's clothes. Use when asked is this a pitch or a training, my informative deck didn't land the ask, my pitch felt like a lecture, or structure this talk for the right job. Produces the mode diagnosis, the structural implications, the mixed-mandate split, and the mode-check on an existing deck.DocumentsNo warnings★ 1.5K↓ —
- agentlas-cloudagentlas-ai/Agentlas-OSUse when the user types /agentlas-cloud, /agentlas cloud, or /hep-cloud to staff only from the signed-in owner's private Cloud packages.OtherNo warnings★ 1.6K↓ —
- add-geolocationmicrosoft/power-platform-skillsInternal implementation skill invoked by /add-native for native background GPS tracking with durable storage and Dataverse sync using @microsoft/power-apps-native-bglocation.OtherNo warnings★ 1.1K↓ —
- pnas-databrycewang-stanford/Awesome-Journal-SkillsUse to build PNAS's Data Availability Statement and deposition plan — mandatory deposition of data in an approved repository at submission, accession numbers/DOIs, public + archived code, and materials sharing. "Available on request" is not sufficient for primary data.PlanningNo warnings★ 1.4K↓ —
- podc-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when building the evidence for an ACM PODC paper — where "evidence" is a proof, not a benchmark. Covers matching upper and lower bounds, tightness arguments, model and assumption stress-tests, adversary-strength calibration, and the honest, clearly-optional role of any simulation in a distributed-computing-theory paper.TestingNo warnings★ 1.4K↓ —
- agy-nativehashgraph-online/awesome-codex-pluginsRun a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.ProductivityNo warnings★ 1.5K↓ —Also in 2 other repos
- iros-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing IROS experiments — real-robot trial counts, success criteria set in advance, reset procedures, failure taxonomies, baseline fairness on matched hardware, sim-to-real gap reporting, small-n statistics, and the claim-to-evidence ladder that embodied-systems reviewers apply before they trust a demo.OtherNo warnings★ 1.4K↓ —
- financial-analystalirezarezvani/claude-skillsUse for financial statement analysis, DCF valuation, budget variance or rolling forecasts. Runs ratio_calculator.py, dcf_valuation.py, budget_variance_analyzer.py and forecast_builder.py.FinanceNo warnings★ 29.2K↓ —
- icdt-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when deciding what counts as evidence for an ICDT (International Conference on Database Theory) result — matching-bound complexity analysis as the primary evidence, worked examples and counterexamples that establish separations, and, only for papers with an algorithmic contribution, a proportional and honestly-scoped experimental evaluation that does not pretend to be the contribution.DataNo warnings★ 1.4K↓ —
- run-organic-social-platform-researchgooseworks-ai/goose-skillsResearches how one social platform works right now from dated sources (what gets reach, formats rising and fading, how small accounts get seen, recent changes) and finds what is getting watched in a given niche there, with linked examples and engagement read against each author's baseline. Use alone when you already have the platform and niche; otherwise run run-organic-social.ScienceNo warnings★ 1.3K↓ —
- corl-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when converting an accepted CoRL paper into its final form — the 9-page camera-ready main text with the extra page for review feedback, the final-mode corl LaTeX template, appendix merged into one PDF, de-anonymization, external hosting for videos because PMLR accepts none, and the October deadline into the PMLR volume.DocumentsNo warnings★ 1.4K↓ —
- sno-mem-claudesno-ai/sno-stationUse Sno memory from Claude through four explicit commands.ProductivityNo warnings★ 1.1K↓ —
- uai-workflowbrycewang-stanford/Awesome-Journal-SkillsUse when planning a UAI cycle end to end, from venue-fit confirmation through the winter submission deadline, the spring review and author-response phases, the June decision, the July PMLR camera-ready, and the August conference, as one backward-planned calendar with named owners for anonymity, evidence, and packaging tasks.ProductivityNo warnings★ 1.4K↓ —
- vpe-advisoralirezarezvani/claude-skillsUse when delivery is slowing, eng hiring is broken, team structure is unclear or you need to decide when to add an eng manager. Runs delivery_throughput_analyzer.py (DORA), eng_hiring_funnel_calculator.py and eng_team_structure_designer.py.OtherNo warnings★ 29.2K↓ —
session-report
hoangsonww/Claude-Code-Agent-Monitor
PlanningUpdated yesterday
From the author
Generate a comprehensive session report with per-model token usage (input, output, cache_read, cache_write including compaction baselines), cost breakdown via the pricing engine, tool invocations, agent hierarchy, compaction events, API errors, turn durations, and thinking block counts. Use when reviewing a specific session or summarizing activity over a date range.
Install
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill session-report -a claude-code
Installs to .claude/skills/session-report/ · 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
Provenance77
Maintenance100
Licence100
Adoption49
Files (2)
- SKILL.md
- agents/openai.yaml