loop-triage

Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.

Quality

67%

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/loop-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 body is concise and actionable with a concrete output template and clear decision rules, but the triage workflow is implicit rather than explicitly sequenced and it references a script path that is not present in the bundle. Adding an explicit step sequence with a self-check checkpoint would most improve the lowest dimension.

Suggestions

Replace the implicit Inputs/Output/Rules layout with a numbered triage workflow (ingest inputs -> classify against rules -> draft the 4-section report -> record state updates) and add a validation/self-check step, e.g. confirm every High-Priority item meets the 'reasonable engineer would want to know today' threshold before finalizing.

Define or link the 'Loop Ready score of 100' and the state-file format so the output guidance is fully executable rather than relying on unstated conventions.

Resolve the dangling scripts/github-triage.mjs reference: either ship the script in a scripts/ bundle file with a clear pointer, or reword it as a contextual note about the triaged repo so it is not mistaken for a skill resource.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining what CI/PRs/issues are; only minor conversational padding ("The loop (and the human reading the state) will thank you.") could be trimmed, fitting the efficient-with-minor-over-explanation anchor.	4 / 5
Actionability	Concrete output template with per-item fields ("Why it matters", "Suggested next action", "Rough effort estimate") and specific decision rules ("Only put something in High-Priority if a reasonable engineer would want to know about it today") give mostly executable guidance, with minor gaps such as the undefined "Loop Ready score of 100".	4 / 5
Workflow Clarity	Content is organized by Inputs / Output Format / Rules rather than as an explicit ordered workflow, so the triage sequence (ingest, classify, emit, record state) is only implicit and lacks validation checkpoints, matching the anchor for sequence-present-but-checkpoints-implicit.	3 / 5
Progressive Disclosure	A single well-organized SKILL.md under 50 lines with clear sections needs no external references, but the body references scripts/github-triage.mjs (via .github/workflows/daily-triage.yml) as a mechanical source while no scripts/ bundle directory exists, a minor dangling-reference navigation gap.	4 / 5
	Total	15 / 20 Passed

Description

66%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 and uses natural trigger terms within a distinct loop-triage niche, but it omits an explicit 'Use when...' clause, which caps its completeness. Adding concrete trigger guidance would raise the strongest dimension (completeness) that currently lags.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when triaging recent CI failures, open PRs, stale issues, or chat threads for a loop to act on.'

Add common synonyms such as 'alerts', 'incidents', or 'tickets' alongside 'issues' to broaden natural keyword coverage.

Make the 'when' explicit by tying activation to the loop's run cadence (e.g. daily triage) rather than leaving it implied.

Dimension	Reasoning	Score
Specificity	Names the domain ("CI failures, issues, and conversations") and several concrete actions ("Triage", "Produces a concise, actionable findings report", "Writes structured output to a state file or Linear board"), matching the anchor for several specific actions with minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does but provides no "Use when..." clause or equivalent explicit trigger guidance; the judging guideline caps completeness at 3 in that case, matching the clear-'what'/missing-'when' anchor.	3 / 5
Trigger Term Quality	Includes natural phrases an engineer would say ("triage CI failures", "triage issues", "Linear board", "state file", "findings report") with good coverage, though synonyms like "alerts", "incidents", or "tickets" are missing.	4 / 5
Distinctiveness Conflict Risk	The loop-consumption framing ("suitable for a loop to consume", "state file or Linear board") gives it a clear niche with only minor overlap risk against general issue-triage or CI-monitoring skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: cobusgreyling/loop-engineering
Path: skills/loop-triage/SKILL.md
Commit: 0dc0f3f

Reviewed: 2 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.