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.
49,395 skills from 2,375 repositories · updated 16 minutes ago
49,393 skills
- flyio-cost-tuningjeremylongshore/tons-of-skills-marketplaceAnalyze Fly.io Machine, volume, network, IP, and Managed Postgres cost drivers without freezing volatile prices. Use when reducing spend or forecasting capacity. Trigger with: "audit Fly bill", "right-size Fly Machines", "reduce Fly idle cost".DataNo warnings★ 2.9K↓ —
- sharpenmichael-denyer/pstack-claudeMake a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.ProductivityNo warnings★ 3.9K↓ —
- swarmmichael-denyer/pstack-claudeFan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.OtherNo warnings★ 3.9K↓ —
- tao-finetune-cosmos-embedNVIDIA/skillsCosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".MediaNo warnings★ 3.8K↓ —
- flyio-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement Fly.io Machines API pacing, per-resource serialization, retry, and reconciliation from the documented action limits. Use when automating Machine or app operations. Trigger with: "handle Fly 429", "throttle Machines API", "batch Fly Machine updates".EngineeringNo warnings★ 2.9K↓ —
- review-workcode-yeongyu/oh-my-openagentPost-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.EngineeringNo warnings★ 70.7K↓ —
- foundationpose-pipelineNVIDIA/skillsAdapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results. Use for dataset runs and result comparisons; environment installation belongs to foundationpose-setup.OtherNo warnings★ 3.8K↓ —
- tao-finetune-kumo-anomalyNVIDIA/skillsKumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune Kumo-Anomaly", "run Kumo-Anomaly inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune Kumo-Anomaly", "use perform_anomaly_analysis_with_diffusion", "automl Kumo-Anomaly", "hyperparameter search Kumo-Anomaly", "hyperparameter optimization" or mentions "curriculum_medium.yaml", "final_model.pth", "kumo-anomaly", "sdk/anomaly_analysis", or "TSDiffuser_Generic".OtherNo warnings★ 3.8K↓ —
- onboarddavepoon/buildwithclaudeSet up CIAgent regression testing for the AI agent in this repo — write a runner, record golden baselines, generate a test spec, and verify it. Use when the user asks to add tests, evals, or regression testing for their AI agent, or to set up CIAgent.TestingNo warnings★ 3.7K↓ —
- arenabacknotprop/pstackSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.ProductivityNo warnings★ 3.5K↓ —
- lcx-report-bugcode-yeongyu/oh-my-openagentCreate a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.EngineeringNo warnings★ 70.7K↓ —
- ketchupbacknotprop/pstackCatch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /ketchup.OtherNo warnings★ 3.5K↓ —
- ml-data-leakage-guardforyourhealth111-pixel/Vibe-SkillsDetects and prevents data leakage in machine learning and mathematical modeling. Use after ML tasks involving data cleaning, feature engineering, data augmentation, algorithm development, normalization, missing value imputation, dimensionality reduction, feature selection, or time series modeling. Checks if features/statistics would be available at prediction time.ProductivityNo warnings★ 3.8K↓ —
- security-researchcode-yeongyu/oh-my-openagentOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.SecurityNo warnings★ 70.7K↓ —
- tddbacknotprop/pstackUse only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.TestingNo warnings★ 3.5K↓ —Also in 3 other repos
- kiro-validate-gapgotalab/cc-sddAnalyze implementation gap between requirements and existing codebase. Use when planning integration with existing systems.PlanningNo warnings★ 3.8K↓ —
- give-me-tipscode-yeongyu/oh-my-openagentExplains any senpi tip in depth, including Tip: lines in the TUI. Use when the user asks about a tip, what a tipped feature does, or which tips they can see.OtherNo warnings★ 70.7K↓ —
- principle-test-behavior-not-implementationbacknotprop/pstackApply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.TestingNo warnings★ 3.5K↓ —Also in 1 other repo
- ad-test-designeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试TestingNo warnings★ 3.1K↓ —
- jetson-customize-mgbeNVIDIA/skillsEnable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.WritingNo warnings★ 3.8K↓ —
- kiro-validate-implgotalab/cc-sddValidate feature-level integration after all tasks are implemented. Checks cross-task consistency, full test suite, and overall spec coverage.TestingNo warnings★ 3.8K↓ —
- jetson-customize-pcieNVIDIA/skillsPer-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane allocation or endpoint-mode bring-up.OtherNo warnings★ 3.8K↓ —
- sales-enablement-kitaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "build battle cards", "prep the sales team for launch", or "write the internal launch FAQ"; produces the internal enablement kit for a sales-led launch — battle cards vs each named alternative (where we win / where they win / trap questions, every fact traceable), a sales talk track derived from the PR-FAQ spine, an objection-handling table (objection → response → evidence), internal FAQ + CS macros, and an internal launch announcement with embargo discipline. Not for the external message house — use message-house-builder; not for competitor tracking itself — use competitor-tracker or competitor-analysis; not for outbound sequences — use cold-outbound-sequencer. 销售赋能/battle card/销售叙事/异议处理/内部FAQWritingNo warnings★ 3.1K↓ —
- designing-experimentsforyourhealth111-pixel/Vibe-SkillsDesign experiments and quasi-experiments before analysis. Use when choosing study design, treatment/control structure, outcomes, assumptions, validation plans after scientific experiment failure, or which of DiD, ITS, synthetic control, or regression discontinuity fits the research question. For fitting models or estimating effects on existing data, use performing-causal-analysis instead.DesignNo warnings★ 3.8K↓ —
gsd:eval-review
davepoon/buildwithclaude
EngineeringUpdated 9 hours ago
From the author
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
Install
npx skills add davepoon/buildwithclaude --skill gsd:eval-review -a claude-code
Installs to .claude/skills/gsd-eval-review/ · 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 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (1)
- SKILL.md