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.
48,168 skills from 2,325 repositories · updated 19 hours ago
48,168 skills
- gsd:add-phasedavepoon/buildwithclaudeAdd phase to end of current milestone in roadmapPlanningNo warnings★ 3.7K↓ —
- scientific-brainstormingforyourhealth111-pixel/Vibe-SkillsOpen-ended scientific ideation partner. Use for research gaps, mechanism exploration, interdisciplinary connections, assumptions, possible research directions, and lightweight literature matrix or A+B paper-combination idea mapping. For structured testable hypotheses and validation plans, use hypothesis-generation instead.ScienceNo warnings★ 3.8K↓ —
- terms-generatorjeremylongshore/tons-of-skills-marketplaceDraft service-specific terms from confirmed features, business decisions and scoped applicability review, with clear assumptions and a separate review record. Use when preparing or revising website or app terms. Trigger with "terms-generator" or "create terms of service".PlanningNo warnings★ 2.9K↓ —
- gsd:add-testsdavepoon/buildwithclaudeGenerate tests for a completed phase based on UAT criteria and implementationTestingNo warnings★ 3.7K↓ —
- doca-hardware-safetyNVIDIA/skillsUse this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe rebind / rescan / link-state flip, BlueField cold reboot, or remediation of a BlueField thermal shutdown. Wrap the change in pre-flight inventory, OOB reachability, a maintenance window, replica rehearsal, and rollback. Trigger on implicit phrasing: "flip BlueField mode over SSH", "enable SR-IOV and reboot", "burned firmware but mlxconfig shows old value", "BlueField thermal shutdown". Not for read-only inventory or version queries (doca-version, doca-caps). Refuse orientation (doca-public-knowledge-map), install or env debug (doca-setup), and program-side debug (doca-debug, doca-programming-guide).WritingNo warnings★ 3.8K↓ —
- tao-train-oneformerNVIDIA/skillsOneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TAO OneFormer model. Trigger phrases include "train OneFormer", "universal segmentation", "task-conditioned segmentation", "panoptic / instance / semantic in one model".MediaNo warnings★ 3.8K↓ —
- property-based-testingforyourhealth111-pixel/Vibe-SkillsProperty-based testing with fast-check (TypeScript/JavaScript) and Hypothesis (Python). Generate test cases automatically, find edge cases, and test mathematical properties. Use when user mentions property-based testing, fast-check, Hypothesis, generating test data, QuickCheck-style testing, or finding edge cases automatically.TestingNo warnings★ 3.8K↓ —
- abridge-cost-tuningjeremylongshore/tons-of-skills-marketplaceEvaluate Abridge adoption, workflow value, and avoidable operational friction without inventing prices or vendor billing meters. Use when reviewing an Abridge rollout or renewal. Trigger with "analyze Abridge value".ProductivityNo warnings★ 2.9K↓ —
- spec-writingjeremylongshore/tons-of-skills-marketplaceExecute this skill should be used when the user asks about "writing specs", "specs.md format", "how to write specifications", "sprint requirements", "testing configuration", "scope definition", or needs guidance on creating effective sprint specifications for agentic development. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.WritingNo warnings★ 2.9K↓ —
- gsd:helpdavepoon/buildwithclaudeShow available GSD commands and usage guideOtherNo warnings★ 3.7K↓ —
- gsd:mvp-phasedavepoon/buildwithclaudePlan an MVP-mode phase — captures an "As a / I want to / So that" user story, runs SPIDR splitting, then delegates to plan-phasePlanningNo warnings★ 3.7K↓ —
- subtitle-translateZJU-REAL/Easel字幕翻译 / 双语字幕：把已有字幕（SRT/VTT/ASS）翻译成目标语言，生成双语（原文+译文）或纯译文字幕，并可软挂载 / 硬烧录进视频。当用户说 字幕翻译、翻译字幕、双语字幕、中英字幕、给视频加翻译、SRT 翻译、字幕本地化、把字幕翻成中文/英文、字幕转双语 时使用。翻译由 LLM 完成，时间轴/格式/烧录由 shared/scripts/subtitle_ops.py 确定性处理。与 auto-subtitle 区别：auto-subtitle 是语音识别生成字幕，本 SKILL 是把已有字幕翻译成双语。OtherNo warnings★ 4.2K↓ —
- gsd:plant-seeddavepoon/buildwithclaudeCapture a forward-looking idea with trigger conditions — surfaces automatically at the right milestonePlanningNo warnings★ 3.7K↓ —
- reasoningjeremylongshore/tons-of-skills-marketplaceUse BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare these approaches". Also fires on cross-domain analysis, strategy questions, architecture decisions, or anything requiring multiple factors to be weighed before responding. The skill calls the reasoning MCP tool to retrieve a cognitive scaffold (named failure pattern, executable procedure, suppression vectors, falsification test) the model absorbs internally before generating its response. Catches causal shortcuts, premature conclusions, generic templates, and surface pattern matching that produce confidently-wrong answers. Do NOT trigger for simple factual lookups, syntax questions, file reads, code execution, or restating the user's input.TestingNo warnings★ 2.9K↓ —
- metric-calculatorforyourhealth111-pixel/Vibe-SkillsCompute well-defined metrics from existing formulas, datasets, or test outputs. Use as an explicit/manual helper when the metric definition is already known, not for choosing the overall analysis owner or dashboard strategy.TestingNo warnings★ 3.8K↓ —
- testingdavepoon/buildwithclaudeTesting strategies and methodologies including TDD, E2E testing, and multi-framework supportTestingNo warnings★ 3.7K↓ —
- gsd:audit-fixdavepoon/buildwithclaudeAutonomous audit-to-fix pipeline — find issues, classify, fix, test, commitTestingNo warnings★ 3.7K↓ —
- comparison-cardZJU-REAL/Easel对比图/一图流：生成 A vs B 参数对比图、优劣势对比表、产品参数一图流。 用 HTML+CSS 渲染成可截图的视觉卡片，适合小红书/微博等平台分享。 使用时机：用户说"做个对比图"、"A vs B"、"参数对比"、"优劣对比"、 "一图流"、"对比表"、"哪个好"、"对比一下"。 和 chart-visualization 的区别：chart 做数据图表（柱状图/折线图），comparison-card 做对比表/一图流。 和 infographic 的区别：infographic 做多维信息图，comparison-card 专注 A vs B 对比。DesignNo warnings★ 4.2K↓ —
- optimizing-promptsjeremylongshore/tons-of-skills-marketplaceExecute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more conci... Use when optimizing performance. Trigger with phrases like 'optimize', 'performance', or 'speed up'.OtherNo warnings★ 2.9K↓ —
- gsd:spec-phasedavepoon/buildwithclaudeSocratic spec refinement — clarify WHAT a phase delivers with ambiguity scoring before discuss-phase. Produces a SPEC.md with falsifiable requirements locked before implementation decisions begin.PlanningNo warnings★ 3.7K↓ —
- writing-defect-reportskajisho5/ffmpeg-skillEstablish a finding before you publish it, and correct it after — headlines that overstate what actually reproduces at the layer a user sees, reporting code that no entry point can reach or that is already dead, filing a caveat the project's own records already answered, re-verifying your prior notes against the tree instead of against the note, choosing the narrowest injection point that reproduces a failure without breaking the run first, capturing probe output a harness swallows, and withdrawing a published claim in the thread where you published it. Use when filing an issue, writing the body of a PR or code review that asserts a defect, triaging someone else's report, or deciding whether a suspicious observation is reportable at all.WritingNo warnings★ 4.1K↓ —
- press-media-relationsaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "build a media list for my launch", "write a launch press release", or "pitch press under embargo"; produces a three-tier media and analyst list (Tier 1 exclusive candidates, Tier 2 vertical press, Tier 3 communities and newsletters), an embargo pitch timing skeleton keyed to the launch-registry date, a press-release draft in standard structure with no fabricated quotes or numbers, and an analyst briefing outline. Not for press-kit assets — use launch-asset-packager; not for follow-up sequence mechanics — use outreach-manager; not for post-launch news-echo monitoring — use launch-monitor. 媒体名单/禁运期pitch/新闻稿/分析师简报WritingNo warnings★ 3K↓ —
- cold-outbound-sequenceraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a warmup + send-throttle ramp schedule, jurisdiction opt-in/CAN-SPAM guardrails (guidance, not legal advice), and a SEND S-dimension read. Not for B2C lifecycle flows — use email-sequence-designer; not for the consent record — use consent-registry; not for computing EQS — use email-quality-auditor. B2B冷启动外联序列/回复分流/域名预热DesignNo warnings★ 3K↓ —
- benchmark-checklistmichael-denyer/pstack-claudeVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.OtherNo warnings★ 3.7K↓ —
principle-guard-the-context-window
backnotprop/pstack
ProductivityUpdated 3 days ago
From the author
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Install
npx skills add backnotprop/pstack --skill principle-guard-the-context-window -a claude-code
Installs to .claude/skills/principle-guard-the-context-window/ · 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
Provenance82
Maintenance100
Licence100
Adoption56
Files (1)
- SKILL.md