focused-fix
Constrain a bugfix to the smallest reviewable change: reproduce, patch, add a regression test, check the diff for scope creep
Install / Use
npx skills add borghei/Claude-Skills --skill focused-fixInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of focused-fix
focused-fix scores 87/100 on our quality scale, 2218th of 4,702 Development & Engineering skills we index (top 48%).
Its SKILL.md is 6.0 KB long, well organised into 18 sections with 1 code example: a thorough specification that gives an agent plenty to work with.
It has 817 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so focused-fix is actively maintained.
- Our last check on 2026-11-02 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
focused-fix compared with similar skills
All 4 of these similar skills score higher than focused-fix; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| focused-fix (this skill)by borghei | 87 | 817 | 57d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 117.6k | 9d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.3k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.4k | 3d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.7k | today | MCP Server |
Frequently asked questions
- How do I install focused-fix?
- Run
npx skills add borghei/Claude-Skills --skill focused-fix. The install tabs above show the steps for each supported agent. - Which AI agents does focused-fix work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is focused-fix safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is focused-fix still maintained?
- The repository was last updated about 2 months ago, so focused-fix is actively maintained.
Skill content
View source on GitHubname: focused-fix description: > This skill should be used when the user asks to "fix a bug with minimal changes", "analyze change scope for a bugfix", "find the minimal set of files to change", "do a focused bugfix", or "scope a minimal repair". license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: engineering domain: debugging updated: 2026-04-02 tags: [bugfix, minimal-change, scope-analysis, debugging, focused-fix]
Focused Fix
Category: Engineering Domain: Debugging & Maintenance
Overview
The Focused Fix skill enforces a disciplined minimal-change approach to bug fixing. Instead of refactoring or improving code during a bugfix, it identifies the smallest possible change set that resolves the issue. This reduces risk, simplifies code review, and prevents scope creep.
Use when
- The user asks to "fix a bug with minimal changes", "do a focused bugfix", or "scope a minimal repair"
- A bug report needs triage to identify the smallest set of files to touch
- A PR is at risk of scope creep (unrelated refactors, style changes, "nearby" fixes)
- A hotfix or release-blocker needs a low-risk, reviewable change set
- The user asks "what is the minimal change to fix X?" or "which files do I need to touch for this bug?"
Clarify First
Before scoping the fix, confirm these inputs. If any is unknown or vague, ASK — do not assume:
- [ ] Observable failure — the exact symptom, repro steps, and expected vs actual behavior (the bug description the analyzer matches against, and what the fix must resolve — not a guess at the cause)
- [ ] Codebase path & file types — which directory and extensions to search (sets
--path/--extensions) - [ ] Minimal vs structural — confirm this is a focused fix, not a refactor (determines whether out-of-scope "while I'm here" changes are rejected)
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Quick Start
# Analyze a bug description to identify minimal change scope
python scripts/change_scope_analyzer.py --bug "Login fails when email has + character" --path ./src
# Analyze with JSON output
python scripts/change_scope_analyzer.py --bug "API returns 500 on empty array input" --path ./src --format json
# Analyze with specific file extensions
python scripts/change_scope_analyzer.py --bug "CSS overflow on mobile" --path ./src --extensions .css .scss .html
Tools Overview
| Tool | Purpose | Key Flags |
|------|---------|-----------|
| change_scope_analyzer.py | Identify minimal files to change for a bugfix | --bug, --path, --extensions, --format |
change_scope_analyzer.py
Analyzes a bug description against a codebase to identify:
- Files most likely related to the bug (keyword matching, import tracing)
- Estimated change scope (number of files, lines)
- Risk assessment for the change
- Recommended fix approach (minimal vs. structural)
Workflows
Focused Bugfix Workflow
- Write a clear bug description — reproduction steps, expected vs actual behavior
- Validate: the description names the observable failure, not a guess at the cause
- Run
change_scope_analyzer.pyto identify scope- Validate: analyzer output lists concrete files and an estimated line count
- Review the recommended files and approach
- Validate: recommended approach is "minimal" — if it says "structural", stop and scope a refactor PR separately
- Make ONLY the changes needed to fix the bug
- Validate:
git diff --statmatches (or is smaller than) the analyzer's recommendation
- Validate:
- Verify no unrelated changes leaked in
- Validate:
git diffshows no formatting-only changes, no unrelated imports, no "while I'm here" edits
- Validate:
- Submit PR with focused change set
- Validate: commit message states the exact bug fixed, and a regression test is included
Scope Validation
- After making changes, re-run analyzer
- Compare actual changes against recommended scope
- Flag any out-of-scope modifications for separate PRs
- Validate: any file touched that was not in the analyzer recommendation has a one-line justification or is reverted
Reference Documentation
- Focused Fix Methodology - Principles, anti-patterns, and decision framework
Common Patterns
Do
- Fix the exact bug reported
- Add a regression test for the fix
- Document why the fix works in the commit message
- Keep the diff as small as possible
Don't
- Refactor surrounding code during a bugfix
- Fix "nearby" issues in the same PR
- Change formatting or style in touched files
- Add features disguised as bugfixes
Anti-patterns
| Anti-pattern | Failure mode | Fix |
|--------------|--------------|-----|
| "While I'm here" refactors in the bugfix PR | Blast radius explodes; review time multiplies; unrelated regressions masked by the real fix | Open a separate PR for the refactor, tagged as refactor: not fix: |
| Reformatting or auto-save style changes in touched files | Diff becomes unreadable; real fix hidden in 200 lines of whitespace | Revert style changes before committing; configure the editor to format-on-save only for new files |
| Fixing the symptom in the wrong layer | Bug returns in a new form; accumulates workaround debt | Trace to the root layer — analyzer's keyword-match output is a hint, not an answer |
| Skipping the regression test "because the fix is obvious" | Bug silently returns on a refactor 6 months later | Every fix: commit adds at least one failing-then-passing test |
| Treating change_scope_analyzer.py output as authoritative | Analyzer is keyword/import-based, not semantic — misses dynamic dispatch, reflection, config-driven paths | Use it as a starting set; grep for callers and tests before committing to the scope |
| Bundling the fix with a dependency upgrade | Two risk profiles in one PR; if rollback is needed, both are lost | Land the upgrade separately, then the fix against the upgraded baseline |
Related Skills
taste-skill
117.6kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.3kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.4kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.7k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
