focused-fix
Skill1 starsChanged 31 days agoMITView on GitHub
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".
8 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- DROOdotFOO/agent-skillstheir own version, first seen Sep 1, 2026
- Hassaan146/claude-skillstheir own version, first seen Jul 25, 2026
- mahiunfiltered/claude-code-skillstheir own version, first seen Jul 8, 2026
- Hussain-Elfalah/Agentic-Skillstheir own version, first seen Jun 4, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- Hassaan146/claude-skills★ 18same name
- csiddhant796-blip/claude-skills-collection★ 2same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- DROOdotFOO/agent-skills★ 1same name
- kazemcodes/skill-tree★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
- Arnav-0/claude-code-setup★ 0same name
- darkweb19/skills★ 0same name
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 repository121 other files it gives its agents.
- analysis-documentationSkill
- browser-automationSkill
- business-metrics-calculatorSkill
- chat-attachment-is-not-a-fileSkill
- claude-code-masterySkill
- codebase-designSkill
- codex-cli-specialistSkill
- cohort-analysisSkill
- cut-the-curveSkill
- data-narrative-builderSkill
- data-quality-auditSkill
- domain-modelingSkill
- funnel-analysisSkill
- gate-must-derive-its-criterionSkill
- grill-with-docsSkill
- gsd-add-testsSkill
- gsd-ai-integration-phaseSkill
- gsd-audit-fixSkill
- gsd-audit-milestoneSkill
- gsd-audit-uatSkill
- gsd-autonomousSkill
- gsd-captureSkill
- gsd-cleanupSkill
- gsd-code-reviewSkill
- gsd-complete-milestoneSkill
- gsd-configSkill
- gsd-debugSkill
- gsd-discuss-phaseSkill
- gsd-docs-updateSkill
- gsd-eval-reviewSkill
- gsd-execute-phaseSkill
- gsd-exploreSkill
- gsd-extract-learningsSkill
- gsd-fastSkill
- gsd-forensicsSkill
- gsd-graphifySkill
- gsd-healthSkill
- gsd-helpSkill
- gsd-importSkill
- gsd-inboxSkill
- gsd-ingest-docsSkill
- gsd-managerSkill
- gsd-map-codebaseSkill
- gsd-milestone-summarySkill
- gsd-mvp-phaseSkill
- gsd-new-milestoneSkill
- gsd-new-projectSkill
- gsd-ns-contextSkill
- gsd-ns-ideateSkill
- gsd-ns-manageSkill
- gsd-ns-projectSkill
- gsd-ns-reviewSkill
- gsd-ns-workflowSkill
- gsd-pause-workSkill
- gsd-phaseSkill
- gsd-plan-phaseSkill
- gsd-plan-review-convergenceSkill
- gsd-pr-branchSkill
- gsd-profile-userSkill
- gsd-progressSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Before scoping the fix, confirm these inputs.
- Distinctive: line 42
Stop rule: ask only the 2-3 that most change the output.
- Distinctive: line 88
After making changes, re-run analyzer
- Distinctive: line 101
Add a regression test for the fix
- Distinctive: line 102
Document why the fix works in the commit message
- Distinctive: line 103
Keep the diff as small as possible
- Distinctive: line 109
Add features disguised as bugfixes
“Common” is measured: kept by at least 6 in 10 of the 8 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
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 .htmlTools 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 |
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.

