Fix a bug
with agent skills.
Start with the failing behavior. These skills cover different parts of debugging, from collecting a reproduction to checking whether a repair holds. Choose one that fits the evidence you already have.
Filter these skills by stack and access
Choose a skill
If you cannot reproduce the problem, look for diagnosis and investigation. If the failure is understood, look for a focused repair workflow. Browser testing, error recovery and final verification address different jobs; read the source note before choosing.
Follow the guided Bug huntBefore you install
Give the agent the failing command or user journey, the expected result, the actual result and any relevant logs with secrets removed. State which files it may edit and which systems it must leave alone.
Open a listing to read its source, access labels and review evidence before copying its install command. The automated scan covers SKILL.md, not referenced files or runtime behavior. Read the review limits.
Skills for this task
12 available skills, listed A to Z. Task labels help narrow the choice; they do not establish fit for your project.
AI regression testing
Adds targeted regression tests for recurring blind spots in AI-assisted code changes.
What it can touch: Edits code · Runs commands
Last good scan retained · evidence and limits
- Automated scan: Latest fetch failed. Last successful scan: 8 Nov 2026. Current upstream content is unverified.
- Source revision: No repository commit recorded. Install command is unpinned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Installs the upstream repository’s current version, not a pinned reviewed revision. The source may have changed since the check. What the review covers.
—not counted yet
npx skills@latest add affaan-m/everything-claude-code --skill ai-regression-testingAzure Diagnostics
Triages Azure production failures with health, logs, metrics, AppLens, and KQL.
What it can touch: Writes docs · Runs commands · Needs MCP · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: f03ec5392f7a (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
—not counted yet
npx skills@latest add https://github.com/microsoft/skills/tree/f03ec5392f7a0f3aca12af47477e92f1edf7b44c --skill azure-diagnosticsDebugging and error recovery
A triage checklist: reproduce, localise, fix, then guard against the regression.
What it can touch: Runs commands · Uses git
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 39b723ceebf8 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
76Kinstalls+560 today
npx skills@latest add https://github.com/addyosmani/agent-skills/tree/39b723ceebf81474d0557c1fecd01eddab585563 --skill debugging-and-error-recoveryDiagnose CI failures
Pulls a pull request's CI logs with the GitHub CLI and plans the fixes.
What it can touch: Uses git · Runs commands · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 8792394ff1b6 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
29Kinstalls+5 today
npx skills@latest add https://github.com/warpdotdev/common-skills/tree/8792394ff1b655e0af451b8fabb68ef0cfcbd208 --skill diagnose-ci-failuresDiagnosing bugs
Builds a fast failing feedback loop first, then narrows to the cause.
What it can touch: Edits code · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 5863806dd4e1 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
936Kinstalls+2.5K today
npx skills@latest add https://github.com/mattpocock/skills/tree/5863806dd4e15c63174bee4e7515a4256792ecfa --skill diagnosing-bugsGitHub CI Fix
Investigates failed GitHub Actions checks and prepares a focused fix.
What it can touch: Edits code · Runs commands · Uses git · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 49f948faa925 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
12Kinstalls+35 today
npx skills@latest add https://github.com/openai/skills/tree/49f948faa9258a0c61caceaf225e179651397431 --skill gh-fix-ciLean Engineering
Small changes, bounded workers, and real evidence. Give every edit a clear owner.
What it can touch: Edits code · Runs commands · Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: b2b8f4e7f947 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: Full reading recorded 25 Sept 2026; not bound to the current source revision.
- Runtime evidence: Published evaluation notes (opens in a new tab). Evaluation date not recorded here; see the notes for dates, scope and limitations. Not a test of every upstream revision.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
—not counted yet
npx skills@latest add https://github.com/AaravKashyap12/lean-engineering/tree/b2b8f4e7f9477f998ca3c1416706987cc9351f53 --skill lean-engineeringMongoDB Query Optimizer
Diagnoses slow MongoDB queries and recommends high-impact index and query changes.
What it can touch: Needs MCP · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 776c47f6f705 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
7.6Kinstalls+11 today
npx skills@latest add https://github.com/mongodb/agent-skills/tree/776c47f6f705b19f1c0ef54d912a59066bef29a7 --skill mongodb-query-optimizerNext.js Development Loop
Verifies Next.js edits through framework diagnostics and a real browser session.
What it can touch: Edits code · Runs commands · Browser · Needs MCP · Network
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 18e5d00b6048 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
26Kinstalls+138 today
npx skills@latest add https://github.com/vercel/next.js/tree/18e5d00b6048da0ba9ddbf2af437ce802f541399 --skill next-dev-loopPost-patch validation
Validates a security patch with pinned baseline, exploit, variant, behavior, and regression evidence.
What it can touch: Edits code · Writes docs · Runs commands · Uses git · Subagents
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 149d7b21f406 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
1.3Kinstalls+25 today
npx skills@latest add https://github.com/trailofbits/skills/tree/149d7b21f4067765b82e67029730b42d228ef4b4 --skill post-patch-validationTest-driven development
Strict test-first discipline: watch it fail, make it pass, then refactor.
What it can touch: Edits code · Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 22f0b463e7a5 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
282Kinstalls+1.3K today
npx skills@latest add https://github.com/obra/superpowers/tree/22f0b463e7a5e579904dd6211a520321035526f7 --skill test-driven-developmentVerification before completion
No claim of done until the checks have run and the output has been read.
What it can touch: Runs commands
Automated scan recorded · evidence and limits
- Automated scan: Checked 16 Nov 2026. Checks SKILL.md patterns and frontmatter; does not run the skill.
- Source revision: 22f0b463e7a5 (opens in a new tab). The install command targets this commit. Only SKILL.md was scanned.
- Human reading: No full human-reading date recorded.
- Runtime evidence: No runtime-test evidence recorded here.
A review is not a security audit or a guarantee.
Commands target the repository commits recorded with the automated scans. Scans cover only SKILL.md, not referenced files or runtime behavior. What the review covers.
278Kinstalls+1.5K today
npx skills@latest add https://github.com/obra/superpowers/tree/22f0b463e7a5e579904dd6211a520321035526f7 --skill verification-before-completion
Check the result
- 01
Reproduce the original failure before changing code. Record the smallest case that still fails.
- 02
Test one explanation at a time, then make a focused change at the cause.
- 03
Repeat the original reproduction and relevant regression tests. Report any behavior that could not be checked.