github-issue-triage

Use this skill when you want to automatically triage GitHub issues — classify type, add labels, route to teams, and draft initial responses.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./external/goose-recipes/github-issue-triage/SKILL.md

Quality

Content

68%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 content is a tight, mostly-executable recipe with clean sectioning, but the automated webhook pipeline mutates live GitHub issues without validation or feedback loops, which caps workflow clarity. Minor executable gaps (missing import, hardcoded model version) and an inlined structure keep the other dimensions just below top marks.

Suggestions

Add a validation checkpoint before posting: verify the classification is non-empty and the type is a known value before adding labels or commenting on live issues.

Include an error-recovery feedback loop (e.g., log and skip the issue on API errors, or re-run classification when 'needs_more_info' is ambiguous) so the batch webhook flow is safe to run unattended.

Fix executable gaps: add the missing 'import os' and replace the hardcoded 'claude-opus-4-6' with a documented/default model so the code runs as-is.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and efficient with no padding about concepts Claude already knows; only minor trimmable elements remain (the Quick Reference table restates code behavior), matching the score-4 anchor rather than the fully-lean score-5 anchor.	4 / 5
Actionability	Three substantial, largely copy-paste-ready Python blocks (classifier, processor, FastAPI webhook) give concrete executable guidance, but minor gaps — a missing 'import os' and a hardcoded model id 'claude-opus-4-6' — keep it at the score-4 anchor rather than score 5.	4 / 5
Workflow Clarity	The classify -> label -> respond -> request-info sequence is coherent and concrete, but there are no validation checkpoints before mutating live GitHub issues (adding labels, posting public comments) in this batch/automated webhook flow, so the rubric's batch-operation cap holds it at 3.	3 / 5
Progressive Disclosure	Sections are clearly headed and well-organized in a single SKILL.md with no bundle files to navigate; being above the 50-line simple-skill threshold and monolithic rather than split across reference files, it fits the score-4 anchor instead of score 5.	4 / 5
	Total	15 / 20 Passed

Description

75%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 clear and specific with a proper 'Use when' trigger and four concrete actions, but the 'when' clause mirrors the 'what' rather than enumerating distinct scenarios, keeping it just below top marks. It is distinguishable and largely free of fluff.

Suggestions

Differentiate the 'when' from the 'what' by naming concrete trigger scenarios, e.g. 'Use when issues are opened or when you need to categorize and label a backlog of incoming issues.'

Add a couple of natural synonyms (e.g. 'categorize', 'label') to widen trigger-term coverage.

Optionally note the scope boundary (e.g. 'for GitHub issues, not pull requests') to reduce overlap with adjacent GitHub skills.

Dimension	Reasoning	Score
Specificity	Names the domain (GitHub issue triage) and lists several concrete actions — 'classify type, add labels, route to teams, and draft initial responses' — giving broad coverage with only minor gaps, matching the score-4 anchor.	4 / 5
Completeness	Both 'what' (classify, label, route, draft responses) and 'when' ('Use this skill when you want to automatically triage GitHub issues') are present, but the 'when' largely restates the action rather than naming distinct trigger scenarios, so it falls short of the score-5 anchor.	4 / 5
Trigger Term Quality	Natural user-facing phrases like 'GitHub issues', 'triage', 'classify', 'add labels', and 'route to teams' are present and likely to be spoken verbatim, though a few common synonyms are missing, fitting the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	The GitHub-issue-triage automation niche is distinct and unlikely to fire for unrelated skills, with only minor overlap risk against general GitHub helpers, matching the score-4 anchor.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ProwlrBot/prowlr-marketplace
Path: external/goose-recipes/github-issue-triage/SKILL.md
Commit: 32f0050

Reviewed: 3 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.