quick-fix
Skill15 starsChanged 5 months agoMITView on GitHub
Fix small bugs and issues in 1-3 files following existing patterns. Use proactively for simple bug fixes.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- aniketshukla1/sdlc-kittheir own version, first seen Nov 8, 2026
- danielvm-git/bigpowerstheir own version, first seen Nov 6, 2026
- osac-project/osac-ai-skillstheir own version, first seen Oct 13, 2026
- vishalguptax/agent-engineering-kittheir own version, first seen Oct 11, 2026
- SgtPooki/skillstheir own version, first seen Oct 11, 2026
- gittower/git-flow-nexttheir own version, first seen Oct 8, 2026
Used with
Projects with it also use security-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SentrySkillsecurity-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
Also in 3 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- gittower/git-flow-next★ 458same name
- danielvm-git/bigpowers★ 288same name
- charliehzm/medharness★ 85same name
- jasonmichaelbell78-creator/sonash-v0★ 2same name
- sumulige/sumulige-claude★ 2same name
- aniketshukla1/sdlc-kit★ 1same name
- iabhisekbosepm/claude-god-setup★ 1same name
- Nexus-Organization-Infosec/ClaudeSkills★ 1same name
- SgtPooki/skills★ 1same name
- acevinh/claude-skills★ 0same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- public/llms-full.txtllms.txt
- public/llms.txtllms.txt
- add-componentSkill
- add-diagram-componentSkill
- add-languageSkill
- add-pageSkill
- ai-diff-reviewerSkill
- dailybotSkill
- deepworkplanSkill
- doc-editSkill
- fix-lintSkill
- git-commit-pushSkill
- pr-review-liteSkill
- refactor-safeSkill
- responsive-lighthouse-auditSkill
- security-checkSkill
- translate-syncSkill
- type-fixSkill
- update-stylesSkill
- write-testsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 12 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Does NOT refactor large sections of code
- Distinctive: line 25
Does NOT add new features
- Distinctive: line 26
Does NOT change architectural patterns
- Distinctive: line 27
Does NOT modify more than 3 files
- Distinctive: line 28
Does NOT handle security-sensitive code
- Distinctive: line 49
Before running this skill, ensure:
- Distinctive: line 59
Read the issue description
- Distinctive: line 65
Read the affected file(s)
- Distinctive: line 72
Follow existing code patterns exactly
- Distinctive: line 78
Run validation commands for this repo:
- Distinctive: line 157
Escalate to Tier 2: if:
- Distinctive: line 166
If not possible, escalate to executor agent or feature-implement skill
- Very specific: line 182
Run pnpm run biome:check and pnpm run astro:check
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: Quick Fix
Objective
Fix small bugs, typos, or issues in 1-3 files by following existing code patterns. This skill handles simple, mechanical fixes that don't require architectural decisions. Adapted for this repo: Astro, Svelte, TypeScript; follow AGENTS.md conventions.
Non-Goals
- Does NOT refactor large sections of code
- Does NOT add new features
- Does NOT change architectural patterns
- Does NOT modify more than 3 files
- Does NOT handle security-sensitive code
Tier Classification
Tier: 1 - Light/Cheap
Reasoning: Small scope (1-3 files), low risk (follows patterns), mechanical task (no complex reasoning), quick execution.
Inputs
Required Parameters
$ISSUE: Description of the bug or issue to fix$FILES: File(s) to examine/modify (optional - will search if not provided)
Optional Parameters
$PATTERN: Existing pattern to follow (default: infer from codebase)
Prerequisites
Before running this skill, ensure:
- Working directory is clean (no uncommitted changes)
- Issue is clearly defined and small in scope
- No ongoing work on the same files
Steps
Step 1: Understand the Issue
- Read the issue description
- Identify the expected vs actual behavior
- Locate the relevant file(s)
Step 2: Analyze the Code
- Read the affected file(s)
- Understand the existing pattern
- Identify the root cause
Step 3: Implement the Fix
- Make the minimal change needed
- Follow existing code patterns exactly
- Preserve formatting and style
- Support dark mode if UI-related (use Tailwind's
dark:variant)
Step 4: Validate Changes
Run validation commands for this repo:
pnpm run biome:check
pnpm run astro:checkOutput Format
Success Output
## ✅ Quick Fix Complete
### Issue
{Brief description of what was fixed}
### Changes
- `{file1}`: {what changed}
- `{file2}`: {what changed}
### Validation
- Biome: ✅ Clean
- TypeScript: ✅ Passing
### Commit Message
fix: {description}Failure Output
## ❌ Quick Fix Not Possible
### Reason
{Why this can't be fixed with quick-fix}
### Recommendation
{Escalate to Tier 2 or provide alternative}Guardrails
Scope Limits
- Maximum files: 3
- Maximum LOC: 100
- Allowed: Any directory in src/
- Forbidden: Security-sensitive files
Safety Checks
Before making changes:
- Change is minimal and targeted
- No architectural modifications
- Follows existing patterns (see AGENTS.md, docs/STANDARDS.md)
- No new dependencies added
Stop Conditions
Stop immediately if:
- Issue requires more than 3 files
- Change exceeds 100 LOC
- Requires understanding complex business logic
- Requires adding new dependencies
- Existing patterns are unclear
Definition of Done
- Issue is resolved
pnpm run biome:checkpassespnpm run astro:checkpasses- Change follows existing patterns
- Change is minimal (no over-engineering)
Escalation Conditions
Escalate to Tier 2 if:
- Scope exceeds 3 files
- Root cause is complex
- Fix requires new patterns
- Tests need to be written (testing not configured)
Escalation Path:
- Try to break into smaller fixes
- If not possible, escalate to executor agent or feature-implement skill
Examples
Example 1: Fix a Typo
Context: Typo in component text
Input:
$ISSUE: Hero section says "Wellcome" instead of "Welcome"
$FILES: src/components/home/HeroSection/HeroSection.astroExecution:
- Open file, find typo, replace
- Run
pnpm run biome:checkandpnpm run astro:check - Commit with
fix: correct typo in hero section
Example 2: Fix Dark Mode Issue
Context: Component doesn't support dark mode
Input:
$ISSUE: Footer text is invisible in dark mode
$FILES: src/components/Footer.astroExecution:
- Open file, add
dark:text-gray-100classes - Run
pnpm run biome:check - Commit with
fix: add dark mode support to footer
Example 3: Escalation
Context: Bug affects multiple components
Input:
$ISSUE: Methodology reader navigation is broken across all sections
$FILES: src/components/pages/MethodologyPage.astro + reader componentsResult: Escalate — involves multiple files and complex rendering logic; use Tier 2.
Related
- doc-edit - Documentation-only fixes
- type-fix - TypeScript type errors only
- reviewer - For reviewing fixes
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

