fix-issue 100/100 — SaferSkills

Is fix-issue safe to install?

SaferSkills independently audited fix-issue (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/fix-issue/SKILL.md · 1 file

skills/fix-issue/SKILL.md2.1 KB · Markdown

name: fix-issue

description: "Investigate and fix a GitHub issue. Use when given an issue number or URL, or when the user says 'fix issue'."

Fix the GitHub issue: $ARGUMENTS

Follow this workflow:

why-not-mechanizable: skill workflow guidance; each step requires understanding the issue, the codebase, and the prior state of the work.

Fetch: run gh issue view $ARGUMENTS --json title,body,labels,assignees,comments to get full issue details (review-time: see section note)
Load agents: based on the issue domain, load the relevant expert agents from ~/.claude/agents/ (see rules/agent-routing.md). Their guardrails apply throughout the fix. (review-time: see section note)
Research: use subagents to explore the codebase and understand the problem area. Read linked files, related tests, and recent git history. Save findings to .claude/state/research/YYYY-MM-DD-issue-<number>.md. (review-time: see section note)
Reproduce: if possible, write a failing test that reproduces the issue (review-time: see section note)
Scope check: before planning the fix, state the minimal change that would resolve the issue (ideally 1-5 lines). If a larger change is needed, explain why the minimal fix is insufficient. The plan must build from this minimal baseline. (review-time: see section note)
Plan: propose a fix plan and save to .claude/state/plans/YYYY-MM-DD-fix-issue-<number>.md with: (review-time: see section note)

Root cause analysis
Files to change (with specific line ranges)
Risks and edge cases
Wait for user approval before implementing

Implement: make the changes following the approved plan (review-time: see section note)
Test: write or update tests verifying the fix. Run the test suite. (review-time: see section note)
Verify: run typecheck (npx tsc --noEmit), lint, and full test suite (hook)
Commit: create a conventional commit (e.g., fix(scope): description) referencing the issue (hook)
PR: push the branch and create a PR linking the issue with gh pr create (hook)

fix-issue— agent skill

Is fix-issue safe to install?

Audit the pieces. Scan the whole. Decide.