fix-issue

End-to-end flow for resolving a GitHub issue — fetch and understand the issue, create a feature branch off `beta`, implement and verify the fix, then hand off to the open-pr skill. Use when the user says "fix issue <n>", "work on issue <n>", or wants to take an issue from investigation through to a PR.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean, highly actionable, and well-sequenced with explicit guardrails (sync base, ff-only, no edits on base branch). It earns top marks on conciseness and actionability; workflow clarity sits at 4 because verification is conditional rather than a hard feedback loop, and progressive disclosure at 4 because content is well-structured but self-contained with no bundle references to verify.

Suggestions

Add an explicit verify-fix-retry checkpoint in step 3 (run the affected tests, and if they fail, fix and re-run before handing off) to harden the feedback loop for behavior-changing fixes.

Since destructive-adjacent operations (force/pull) are present, consider a one-line 'verify the branch is off the latest beta tip before editing' check after the branch step.

Dimension	Reasoning	Score
Conciseness	Every section is lean and assumes Claude's competence — concrete commands and short directives with no padding or explanation of concepts Claude already knows (e.g. no 'what a branch is').	5 / 5
Actionability	Provides copy-paste-ready commands (`gh issue view ... --json ...`, the exact git branch sequence) plus a concrete naming example (`fix/2348-dts-in-source`); guidance is fully executable.	5 / 5
Workflow Clarity	Clear four-step sequence with explicit checkpoints (confirm approach before edits, stop if pull fails, verify if deps installed, reason about regressions), but verification is conditional/soft ('if dependencies are installed') rather than a hard validate-fix-retry loop.	4 / 5
Progressive Disclosure	Well-organized into numbered sections with clear scope; it appropriately delegates commit/PR detail to the open-pr skill rather than inlining it. Minor: no external reference files, but the skill is short enough that sections alone suffice.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, uses natural trigger phrases, clearly states both what and when, and carves out a distinct niche with an explicit hand-off boundary. It is concise yet comprehensive. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — fetch/understand the issue, branch off beta, implement and verify, hand off to open-pr — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers what (end-to-end issue resolution with each phase named) and when (a dedicated 'Use when...' clause with concrete trigger phrases), satisfying both requirements.	5 / 5
Trigger Term Quality	Includes the exact natural phrases a user would say ("fix issue <n>", "work on issue <n>") plus a paraphrased intent; these are direct, natural triggers.	5 / 5
Distinctiveness Conflict Risk	The scope is narrowed to investigation/branching/implementation with an explicit hand-off boundary to open-pr, giving it a clear niche and minimal conflict with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: analogjs/analog
Path: .agents/skills/fix-issue/SKILL.md
Commit: 305f9f0

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.