agentleFS
KadirHarmancKadirHarmanc/nazar-skill/skills/fix/SKILL.md

fix

Skill0 starsChanged 8 months agoMITView on GitHub

Auto-fix security and quality issues found by scan. Use when user says 'fix', 'duzelt', 'patch', 'sorunlari coz', 'otomatik duzelt', 'fix issues'.

  • Reads credentials

82 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use feature, frontend-code-review and 8 more.

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.
  • bradtraversySkill

    feature

    Manage current feature workflow - start, review, explain or complete

    Also in 10 projects that use this

  • chendongqiSkill

    frontend-code-review

    Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.

    Also in 4 projects that use this

  • GoogleSkill

    pr-creator

    Also in 4 projects that use this

  • PJuniszewskiSkill

    cook

    Feature development with guardrails. Plan → Review → Code → Ship.

    Also in 3 projects that use this

  • vbrevikSkill

    work

    Use when the user says 'plan', 'todo', 'copy plan', 'append plan', 'resume plan', 'priorities', or 'what's next'.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    test

    Also in 12 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 75 edited versions we read keep these.

  • 9

    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
  1. Distinctive:

    Check if a scan was run in this conversation.

    line 13
  2. Distinctive:

    If no scan results exist, tell the user:

    line 15
  3. Distinctive:

    Do not proceed further without scan results.

    line 19
  4. Distinctive:

    Ask the user how they want to proceed:

    line 47
  5. Distinctive:

    If the user does not specify, default to "review first" mode for critical/high severity and "fix all" for medium/low.

    line 53
  6. Distinctive:

    After fixing, show a summary table:

    line 64
  7. Distinctive:

    After all fixes are applied, suggest:

    line 83
  8. Distinctive:

    Never fix issues without user awareness.

    line 89
  9. Distinctive:

    If a fix requires installing a new dependency (e.g., DOMPurify, bcrypt), inform the user and list the required packages.

    line 90

“Common” is measured: kept by at least 6 in 10 of the 75 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Nazar Fix Skill

This skill auto-fixes security and quality issues found by a previous /nazar:scan.

Workflow

Step 1: Check for Scan Results

Check if a scan was run in this conversation. Look for scan findings in the conversation context.

If no scan results exist, tell the user:

Once /nazar:scan ile tarama yapin, sonra /nazar:fix ile duzeltme yapabilirsiniz.

Do not proceed further without scan results.

Step 2: Analyze Findings

From the scan results, categorize each finding:

  • Auto-fixable: Issues with clear, safe, mechanical fixes (hardcoded secrets, SQL injection, XSS, console.log/print, empty catch, weak crypto)
  • Needs manual review: Issues where the fix might break functionality, requires domain knowledge, or has ambiguous resolution

Step 3: Show Summary

Present to the user:

Tarama Sonuclari:
- Toplam: X sorun bulundu
- Otomatik duzeltilebilir: Y sorun
- Manuel inceleme gerekli: Z sorun

Dagilim:
- Kritik: N
- Yuksek: N
- Orta: N
- Dusuk: N

Step 4: Ask User Preference

Ask the user how they want to proceed:

  • Fix all: Fix all auto-fixable issues at once
  • Select specific: Let user choose which issues to fix
  • Review first: Show each proposed fix before applying

If the user does not specify, default to "review first" mode for critical/high severity and "fix all" for medium/low.

Step 5: Dispatch Fixer Agent

Send the selected findings to the nazar-skill:fixer agent. The agent will:

  • Process findings in severity order (critical first)
  • Apply fixes one by one
  • Report each change made

Step 6: Show Results Table

After fixing, show a summary table:

| Dosya | Sorun | Ciddiyet | Durum |
|-------|-------|----------|-------|
| src/db.js:15 | SQL Injection | Kritik | Duzeltildi |
| src/auth.js:8 | Hardcoded Secret | Kritik | Duzeltildi |
| src/utils.js:42 | console.log | Dusuk | Duzeltildi |
| src/api.js:99 | Deprecated API | Orta | Manuel Inceleme |

Status values:

  • Duzeltildi: Successfully fixed
  • Atlandi: Skipped (not selected by user)
  • Manuel Inceleme: Needs manual review (too risky to auto-fix)
  • Hata: Fix attempted but failed

Step 7: Suggest Verification

After all fixes are applied, suggest:

Duzeltmeleri dogrulamak icin tekrar /nazar:scan calistirmanizi oneririm.

Notes

  • Never fix issues without user awareness. Always show what will change.
  • If a fix requires installing a new dependency (e.g., DOMPurify, bcrypt), inform the user and list the required packages.
  • Group related fixes when possible (e.g., if multiple files have the same hardcoded secret, fix them all together with one .env entry).
  • Track which files were modified so the user can review changes with git diff.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.