Agent skills that run bash, that ask for Task, in claude-code format
A skill is a Markdown file that tells a coding agent how to do one job. We parse every one we can find — the frontmatter, the outline, the languages in its code blocks — so you can look for the one that fits instead of reading through a repository to find out.
69,865 skills from 9,574 repositories, last read 11 September 2026.
Skills declare what they need inconsistently: 58.8% name the languages they run, 11.2% list the tools they ask for, and 4.6% give themselves a category. Filtering narrows to the ones that said so, never to the ones that are.
- bat-story-evalhomeassistant-ai/ha-mcp
Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.
claude-codebashpythonyamlBashReadWrite - qcmacro-inc/macro
Quality gate. 5 parallel agents review changes. All must pass.
claude-codebashTaskBashRead - release-checklistmaximhq/bifrost
Pre-release safety audit for the Bifrost repo. Scans database migrations changed in a release for high-scale deadlock / lock-contention risks and for work that blocks application b
claude-codebashReadGrepGlob - docs-writermaximhq/bifrost
Write, update, and review Mintlify MDX documentation for Bifrost features. Explores the full codebase (UI, Go backend, config schema), validates config.json examples, places screen
claude-codebashjsonmarkdownmdxReadGrepGlob - harness-test-writermaximhq/bifrost
Add regression test cases to the Bifrost provider harness (the Postman collection run via `make run-provider-harness-test`) based on a merged PR or a GitHub issue. Fetches the PR/i
claude-codebashjavascriptReadGrepGlob - changelog-writermaximhq/bifrost
Write changelogs for Bifrost releases. Reads git history, bumps module versions following the core→framework→plugins→transport hierarchy, writes transports/changelog.md (enterprise
claude-codebashmarkdownReadGrepGlob - api-validatormaximhq/bifrost
Scan Bifrost HTTP controllers/handlers/integrations and validate OpenAPI API coverage, route methods/paths, parameters, request/response docs, and auth/security information. Use wh
claude-codebashmarkdownyamlReadGrepGlob - investigate-issuemaximhq/bifrost
Investigate a GitHub issue by fetching details, analyzing the codebase, researching documentation, and presenting an actionable implementation plan with test guidance. Use when ask
claude-codebashgoReadGrepGlob - gate-checkDonchitos/Claude-Code-Game-Studios
Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts. Use when user says 'are we ready to m
claude-codebashReadGlobGrep - propagate-design-changeDonchitos/Claude-Code-Game-Studios
When a GDD is revised, scans all ADRs and the traceability index to identify which architectural decisions are now potentially stale. Produces a change impact report and guides the
claude-codebashmarkdownReadGlobGrep - test-prnudgebee/nudgebee
Investigate a pull request end-to-end — predict how it could be wrong, run it for real, falsify those predictions with evidence, and report by severity
claude-codebashBashReadEdit - shipnudgebee/nudgebee
Intent-anchored ship pipeline — capture intent, then run challenge → validate → verify → code-review → docs-gap → create-pr, then watch CI and triage review comments, as gated stag
claude-codebashBashReadGlob+4 files - hotfixnudgebee/nudgebee
Create a hotfix PR directly to prod with backmerge instructions
claude-codebashBashReadGlob - my-ticketsnudgebee/nudgebee
Show my pending sprint tickets and help knock them off one by one
claude-codebashBashReadGlob - pr-commentsnudgebee/nudgebee
Fetch PR review comments, display them, and optionally fix code issues raised by reviewers
claude-codebashBashReadEdit - create-prnudgebee/nudgebee
Create a pull request with proper formatting, validation, and conventions for this monorepo
claude-codebashmarkdownBashReadEdit+1 files - review-prnudgebee/nudgebee
Review a pull request in an isolated worktree, post comments on the PR, and clean up
claude-codebashBashReadGlob+1 files - exploreparcadei/Continuous-Claude-v3
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
claude-codebashmarkdownpythonyamlBashTaskRead - skill-upgraderparcadei/Continuous-Claude-v3
Upgrade any skill to v5 Hybrid format using decision theory + modal logic
claude-codebashmarkdownyamlBashReadWrite - tdd-migrateparcadei/Continuous-Claude-v3
TDD workflow for migrations - orchestrate agents, zero main context growth
claude-codebashyamlTaskTodoWriteWrite - research-externalparcadei/Continuous-Claude-v3
External research workflow for docs, web, APIs - NOT codebase exploration
claude-codebashmarkdownyamlBashReadWrite - fixparcadei/Continuous-Claude-v3
Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.
claude-codebashmarkdownyamlBashReadGrep - fix-cillama-farm/llamafarm
Fetch GitHub CI failure information, analyze root causes, reproduce locally, and propose a fix plan. Use `/fix-ci` for current branch or `/fix-ci <run-id>` for a specific run.
claude-codebashmarkdownBashReadGrep - code-reviewllama-farm/llamafarm
Comprehensive code review for diffs. Analyzes changed code for security vulnerabilities, anti-patterns, and quality issues. Auto-detects domain (frontend/backend) from file paths.
claude-codebashmarkdownBashReadEdit - reflectllama-farm/llamafarm
Analyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user corrections after skill usage, or at the end of skill-heavy s
claude-codebashReadWriteEdit - gsdallgpt-co/QuickVoice
Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents
claude-codebashReadWriteEdit - pr-reviewconfluentinc/mcp-confluent
Reviews pull requests for the Confluent MCP server. Use when reviewing PRs, doing self-review before sharing with the team, or when the user mentions "review PR", "help with PR", "
claude-codebashmarkdowntypescriptReadBashGrep - tdd-migratevibeeval/vibecosystem
TDD workflow for migrations - orchestrate agents, zero main context growth
claude-codebashyamlTaskTodoWriteWrite - skill-upgradervibeeval/vibecosystem
Upgrade any skill to v5 Hybrid format using decision theory + modal logic
claude-codebashmarkdownyamlBashReadWrite - fixvibeeval/vibecosystem
Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.
claude-codebashmarkdownyamlBashReadGrep - research-externalvibeeval/vibecosystem
External research workflow for docs, web, APIs - NOT codebase exploration
claude-codebashmarkdownyamlBashReadWrite - explorevibeeval/vibecosystem
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
claude-codebashmarkdownpythonyamlBashTaskRead - issue-queueanthony-chaudhary/fak
One repeatable, evidence-backed pass that manages, prioritizes, and resolves a bounded batch of backlog issues worst-first using specialized subagents. Inspects the issue queue via
claude-codebashjsonReadBashWrite - issue-orchestratoranthony-chaudhary/fak
Plan, partition, and coordinate multi-wave parallel subagent campaigns to resolve and close GitHub issues across the repository. Uses `fak issue-orchestrator --plan-waves` (or `fak
claude-codebashjsonReadBashWrite+2 files - debt-orchestratoranthony-chaudhary/fak
Coordinate bounded, evidence-backed maturity debt work in the current repository, with isolated workers and independent verification. Use for debt burndowns or explicitly requested
claude-codebashReadBashWrite - ci-repairanthony-chaudhary/fak
Diagnose, isolate, and repair broken CI/CD workflows and red trunk gates across GitHub Actions, spine-invariance, ci-fast, architest DAG rules, structural policies, scorecard fresh
claude-codebashReadBashWrite - git-subagent-syncanthony-chaudhary/fak
Synchronize subagent changes to git on shared trunk across all lanes and all untracked WIP by default (or scoped via --lane/--paths). Enforces single-source invariants, safe merge
claude-codebashjsonReadBashWrite - opencode-waveanthony-chaudhary/fak
Spawn and coordinate a wave of user-visible, detached OpenCode leaf worker sessions running with high reasoning effort (--variant high), automated approvals (--auto), and direct le
claude-codebashReadEditWrite - dogfoodoptave/ops-codegraph-tool
Run a full dogfooding session against a codegraph release (stable from npm, or dev from GitHub release tarballs) — install, test all commands, compare engines, find bugs, and write
claude-codebashmarkdownBashReadWrite - bob-diff-reviewvmihalis/hacker-bob
Headless Bob diff-review pipeline — invoked by bob-runner.ts via 'claude --dangerously-skip-permissions --print "/bob-diff-review -- ..."'. Ingests a unified diff, initializes a Bo
claude-codebashjsonReadWriteTask - gan-style-harnessmturac/everything-openai-codex
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on OpenAI's March 2026 harness design paper.
claude-codebashmarkdownReadWriteEdit - hk-compounddeepklarity/harness-kit
Compound a learning into a reusable pattern. Use after solving a non-trivial problem, discovering a principle worth reusing, or hitting a gotcha that would bite someone else. Trigg
claude-codebashmarkdownBashReadEdit - hk-breadcrumb-creatordeepklarity/harness-kit
Traces a workflow end-to-end through the harness-kit monorepo and creates a breadcrumb analysis doc in docs/breadcrumb_analysis/. Use this skill whenever the user wants to document
claude-codebashmarkdownBashReadEdit - hk-changelogdeepklarity/harness-kit
Generate changelog entries from git diffs, prepend to CHANGELOG.md, and optionally commit + PR. Use when the user wants to update the changelog.
claude-codebashmarkdownBashReadEdit - hk-skill-creatordeepklarity/harness-kit
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run ev
claude-codebashBashReadEdit - syncrjmurillo/ai-agents
Detect Spec-to-Code drift by scanning REQ, DESIGN and TASK specs for references to code that no longer exists, then report it for triage. Use when you say `detect spec drift`, `syn
claude-codebashTaskSkillRead - pr-reviewrjmurillo/ai-agents
Respond to review comments on one or more pull requests. Clusters the threads, fixes and pushes, then runs the dispatchable completion gate for a verdict. Use when you say `respond
claude-codebashBash(git:*)Bash(gh:*)Bash(python3:*) - analyzerjmurillo/ai-agents
Systematic multi-step codebase analysis producing prioritized findings with file-line evidence. Covers architecture reviews, security assessments, and code quality evaluations thro
claude-codebashReadGrepGlob+8 files - shiprjmurillo/ai-agents
Run the four pre-flight checks, then create the PR or validate a contributor branch without touching it. Use when you say `ship it`, `ship this branch`, or `run pre-flight and open
claude-codebashTaskSkillRead - subagent-devArman-Kudaibergenov/1c-ai-development-kit
Этот скилл MUST быть вызван когда tasks.md готов и требуется автономное параллельное выполнение субагентами (implementer + reviewer на каждую задачу). SHOULD также вызывать для сло
claude-codebashReadWriteEdit - verify-uiThisIsSadeghi/KMPilot
Verify UI implementation against Stitch design via a token audit (HTML ↔ Code, with X-component default-render checks) and an X-components compliance check.
claude-codebashjsonmarkdownTaskReadWrite - modify-featureThisIsSadeghi/KMPilot
Modify existing KMP features with spec-first workflow. Invoke with /modify-feature.
claude-codebashkotlinmarkdownTaskReadWrite+1 files - create-featureThisIsSadeghi/KMPilot
Creates complete KMP features with Clean Architecture through PRD generation, task breakdown, orchestrated implementation, and spec-driven cleanup. Invoke with /create-feature.
claude-codebashTaskReadWrite+1 files - design-uiThisIsSadeghi/KMPilot
Design UI screens in Google Stitch and produce a Compose Implementation Blueprint with HTML + token inventories persisted for downstream skills.
claude-codebashTaskReadWrite+8 files - ship-featuremergewatch/mergewatch.ai
Drive a feature or non-trivial change from request to shipped — write a phased plan doc in docs/feat or docs/chore, get it approved, then implement in stacked PRs with e2e/RUNBOOK.
claude-codebashBashReadEdit - optimize-testsgetstackit/stackit
Make the test suite faster without losing coverage. A periodic, coverage-guarded cleanup pass that finds slow/redundant tests, applies free structural speedups (parallel, in-proces
claude-codebashBash(bash:*)Bash(go:*)Bash(git:*) - pre-release-checkgetstackit/stackit
Decide whether it's safe to cut a new release. Auto-detects the last release tag, gathers everything merged since, runs a build/test health gate, and fans out parallel review agent
claude-codebashBash(bash:*)Bash(git:*)Bash(gh:*) - improvegetstackit/stackit
Analyze changes in the current stack and provide actionable improvement suggestions using parallel multi-agent analysis. Reviews bugs, simplification opportunities, performance, te
claude-codebashBash(git:*)ReadGrep - implement-issueshaharia-lab/agento
Autonomous workflow that takes a GitHub issue from triage to merged-ready PR. Fetches and validates the issue, creates a git worktree, implements the change via sub-agents, commits
claude-codebashReadGrepGlob - engineeringshaharia-lab/agento
Development agent for implementing features, fixing bugs, refactoring, and all engineering work. Context-aware — knows the project structure, docs, architecture, and conventions. U
claude-codebashReadGrepGlob
Browse all 69,865 skills →200 at a time, grouped by owner. The list above is the skills with the highest standing; this is every one of them.
The whole corpus is one call away through the search API, or ask a question of it on the index itself.