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.
46,700 skills from 2,243 repositories · updated 5 hours ago
10,031 skills
- glm-calibrationcxcscmu/SkillLearnBenchCalibrating the General Lake Model (GLM) by modifying parameter bounds for lake simulation.OtherNo warnings★ 91↓ —
- premortemparcadei/Continuous-Claude-v3Identify failure modes before they occur using structured risk analysisOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- d3-interactive-tablecxcscmu/SkillLearnBenchBuild a sortable, highlightable HTML data table linked to a D3 chart so clicking a chart element highlights the matching table row and vice versa.OtherNo warnings★ 91↓ —
- math-helpparcadei/Continuous-Claude-v3Guide to the math cognitive stack - what tools exist and when to use eachOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- run3_skill-1cxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- deal-intake-2ThomasMoreAI/legal-skills-openFür Deal-Intake: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Corporate-Kanzlei. Route: deal-intake.OtherNo warnings★ 95↓ —
- wiringparcadei/Continuous-Claude-v3Wiring VerificationOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- onboardparcadei/Continuous-Claude-v3Analyze brownfield codebase and create initial continuity ledgerOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- run1_skill-1cxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- integration-hubserac-labs/seracBuild ServiceNow IntegrationHub spokes — sn_ih_spoke definitions, sn_ih_action with inputs/outputs, REST/script steps, connection and credential aliases (sys_alias), and retry logic for transient failures.OtherNo warnings★ 78↓ —
- using-godmodeNewNoobyGains/godmodeUse when starting any conversation, before the first response or action, including clarifying questions, to find which GodMode skill applies and how to invoke it on the current harnessOtherNo warnings★ 114↓ —
- approval-workflowsserac-labs/seracConfigure ServiceNow approval rules and sysapproval_approver records — manager/group/script approvers, multi-level routing, delegation via sys_user_delegate, and parent-record state rollup.OtherNo warnings★ 78↓ —
- alterlab-scvi-toolsAlterLab-IEU/AlterLab-Academic-SkillsTrain deep generative models for single-cell omics with scvi-tools — probabilistic batch correction and integration (scVI), reference-mapping transfer learning (scArches), differential expression with uncertainty, and multimodal models (totalVI for CITE-seq, MultiVI for multiome). Use when correcting batch effects, integrating multimodal data, or doing advanced probabilistic single-cell modeling — for standard analysis pipelines use scanpy. Part of the AlterLab Academic Skills suite.OtherNo warnings★ 78↓ —
- mint-unittonone-ai/tononeAudit and improve unit economics — LTV, CAC, payback period, gross margin, contribution margin. Use when asked to "are our unit economics good", "what is our LTV/CAC", or "how do we improve gross margin".OtherNo warnings★ 76↓ —
- axe-recontonone-ai/tononeSurvey a codebase for accessibility debt — missing ARIA, broken keyboard patterns, and contrast issues. Use when asked "how accessible is our codebase", "find accessibility debt", or "where are our a11y gaps".OtherNo warnings★ 76↓ —
- copy-recontonone-ai/tononeSurvey all user-facing strings in a codebase — map coverage and find gaps. Use when asked "what user-facing strings do we have", "map our copy coverage", or "find hardcoded strings".OtherNo warnings★ 76↓ —
- spine-perftonone-ai/tononeFind and fix performance bottlenecks — N+1 queries, missing indexes, sync bottlenecks, caching gaps. Use when asked "why is this slow", "performance issue", "optimize this endpoint", or "N+1 queries".OtherNo warnings★ 76↓ —
- deal-recontonone-ai/tononeRevenue reconnaissance — audit current sales pipeline, deal patterns, ICP definition, and revenue motion to understand what's working and where the constraint is. Use when asked to "audit our sales", "where is revenue stuck", "what's our pipeline state", "before designing a playbook".OtherNo warnings★ 76↓ —
- virtual-agentserac-labs/seracBuild ServiceNow Virtual Agent — sys_cs_topic conversations, topic blocks (text/prompt/script/decision/handoff), NLU utterances and custom entities, quick replies, and KB/incident integration scripts.OtherNo warnings★ 78↓ —
- move-recontonone-ai/tononeAudit existing animations in a codebase — find inconsistencies, missing reduced-motion support, and performance issues. Use when asked to "audit our animations", "check reduced-motion support", or "our animations are janky".OtherNo warnings★ 76↓ —
- keel-audittonone-ai/tononeOperational efficiency audit — identify waste, redundancy, and friction across processes, tools, and team workflows. Use when asked to "audit our operations for waste", "where are we inefficient", "what tools are we paying for but not using", or "reduce operational overhead".OtherNo warnings★ 76↓ —
- materialsarjun988/blender-skillsBlender PBR and stylized material creation for metal, wood, concrete, fabric, glass, dirt, rust, and procedural shaders. Use for look development, material reuse, and production shading in Blender via MCP.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- embedded-iottravisjneuman/.claudeEmbedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.OtherNo warnings★ 106↓ —
- scheduled-jobsserac-labs/seracCreate ServiceNow scheduled jobs on sysauto_script — daily/weekly cron patterns, batch processing with time/runtime limits, conditional execution, error notifications, and metrics recording.OtherNo warnings★ 78↓ —
trace-harness-launch-failure
ashutoshsinghpr7/wikiskill
OtherUpdated Sep 15, 2026
From the author
Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.
Install
npx skills add ashutoshsinghpr7/wikiskill --skill trace-harness-launch-failure -a claude-code
Installs to .claude/skills/trace-harness-launch-failure/ · 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 83
Security100
Provenance69
Maintenance85
Licence100
Adoption41
Files (1)
- SKILL.md