investigate-issue

Investigate a GitHub issue end to end — reproduce the reporter's repo or code snippet in an isolated sandbox outside the monorepo, trace the root cause in the source, and draft a reply back to the reporter for the maintainer to confirm before posting. Use when the user says "investigate issue <n>", "look into issue <n>", "can you reproduce this", or wants a triage answer rather than a fix.

Quality

90%

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

88%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.

A high-quality, actionable skill body with executable commands, a clear numbered workflow, and strong validation gates. It is concise and well-structured, with only minor trimming and structural opportunities.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence, with executable commands throughout; a few explanatory asides (e.g. the Projects-classic GraphQL rationale, the pnpm-workspace absorption warning) earn their place but could be trimmed slightly.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands for every step (gh issue view --json, git clone --depth 1, npm pack, gh issue comment --body-file) covering the common reproduction paths.	5 / 5
Workflow Clarity	A clearly numbered 7-step sequence with explicit validation checkpoints (record the verdict, vary one variable at a time, confirm via packed tarball, label hypotheses), feedback loops, and a final approval gate before posting.	5 / 5
Progressive Disclosure	Well-organized into focused numbered sections with no bundle files needed; the single-file body is appropriately structured, though it inlines guidance that a larger skill might split out, keeping it just short of a 5.	4 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong, specific description with clear what/when coverage and a distinct niche from sibling skills. Trigger terms are natural and concrete, with only minor synonym coverage missing.

Dimension	Reasoning	Score
Specificity	Names three concrete end-to-end actions — reproduce the reporter's repo in an isolated sandbox, trace the root cause in source, and draft a reply — which is comprehensive and specific rather than vague.	5 / 5
Completeness	Explicitly answers both 'what' (reproduce, root-cause, draft reply) and 'when' with concrete trigger phrases in the 'Use when...' clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('investigate issue <n>', 'look into issue <n>', 'can you reproduce this') but lacks synonyms like 'triage issue' beyond the single 'triage' mention and omits issue-URL phrasing.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche distinct from fix-issue, explicitly stating it does not fix or post, with trigger phrases unlikely to fire the wrong skill.	5 / 5
	Total	19 / 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/investigate-issue/SKILL.md
Commit: 8a11ca9

Reviewed: 4 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.