github-triage

Unified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.

Quality

80%

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 ./skills/github-triage/SKILL.md

Quality

Content

76%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 well-structured, highly actionable orchestration skill with concrete gh commands and clear phase sequencing. Its main weakness is the absence of post-action verification feedback loops for destructive/batch operations, which limits workflow clarity despite strong pre-condition gates.

Suggestions

Add post-action verification steps (e.g. re-check `gh pr view --json state` after merge, or confirm a comment was posted before closing) so batch/destructive actions have explicit validate→fix→retry loops.

Tighten the tone-coaching lines (e.g. 'Be genuinely helpful — imagine you're a senior maintainer...') into concise rules to reduce non-essential tokens.

Consider extracting the long per-handler specs (HANDLE_ISSUE_*, HANDLE_PR_*) into reference files linked from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables, code blocks, and phased structure with little concept over-explanation, but tone coaching like 'Be genuinely helpful — imagine you're a senior maintainer who cares about the community' is mildly fluffy and could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready gh CLI commands appear throughout (issue/PR list, comment, close, merge, api diffs) alongside concrete report schemas, covering the common cases.	5 / 5
Workflow Clarity	Phases 1–5 are clearly sequenced with pre-action gates (the six merge conditions, IF YES/NO and OUTCOME A/B/C branches), but this batch/destructive skill lacks post-action verification feedback loops (e.g. confirm a comment posted or a merge succeeded before proceeding), which caps the score per the rubric's batch-operation rule.	3 / 5
Progressive Disclosure	Single self-contained file with no bundle references, organized into well-labeled sections (ARCHITECTURE, PHASE 1–5, ANTI-PATTERNS, QUICK START); the per-handler specs are long and could arguably live in separate reference files, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

83%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, third-person description that explicitly pairs a concrete capability list with natural trigger phrases. It is comprehensive on the 'what/when' axis with only minor gaps in action granularity and a small overlap risk with adjacent review skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report') but stops short of naming the lower-level operations (commenting, closing, merging) that the skill actually performs, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' (classifies, answers, analyzes, reviews, produces report) and 'when' with an explicit 'Triggers:' clause containing concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Explicit triggers ('triage', 'triage issues', 'triage PRs', 'github triage') are natural phrases a user would say, with good coverage of the triage keyword family, but a few natural variants (e.g. standalone 'issues', 'PRs', 'review PRs') are missing.	4 / 5
Distinctiveness Conflict Risk	The 'github triage' framing and triage-specific triggers carve a clear niche, but there is minor overlap risk with general PR-review or issue-management skills.	4 / 5
	Total	17 / 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: ArabelaTso/Skills-4-SE
Path: skills/github-triage/SKILL.md
Commit: 4f38503

Reviewed: 23 hours 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.