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

69%

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

80%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 lean, well-structured instruction-only triage skill with concrete output guidance and clean sectioning. Its main weakness is the absence of validation checkpoints for a batch state-file write, which caps workflow clarity.

Suggestions

Add an explicit validation step after producing the report, e.g. confirm the state file was written and that findings are deduplicated across CI/issue/commit sources.

Specify how to handle ambiguous inputs (e.g. when a CI failure and an issue reference the same problem) so the loop gets deterministic output.

Optionally show the expected state-file write target or format so the structured output is reproducible across runs.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanation of concepts Claude already knows; every section (Inputs, Output Format, Rules) earns its tokens and assumes Claude's competence.	5 / 5
Actionability	Provides concrete, specific guidance — explicit output sections with required sub-fields ('Why it matters', 'Suggested next action', 'Rough effort estimate') and a concrete example action ('draft minimal fix in isolated worktree') — but as an instruction-only skill it lacks executable code, which is acceptable yet keeps it just below fully copy-paste-ready.	4 / 5
Workflow Clarity	The single-pass sequence (Inputs → Output Format → Rules) is clear, but this is a batch operation aggregating multiple sources and writing a state file with no validation checkpoint (e.g. confirm the state file wrote, dedupe items across sources), so workflow_clarity is capped at 3 per the destructive/batch feedback-loop guidance.	3 / 5
Progressive Disclosure	The skill is under 50 lines, has no bundle files, and is organized into well-signaled sections (Inputs, Output Format, Rules), meeting the simple-skill exception that allows progressive_disclosure to score 5 without external references.	5 / 5
	Total	17 / 20 Passed

Description

58%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 clearly states what the skill does across multiple concrete actions but omits an explicit 'when to use it' trigger clause, which caps completeness. Trigger terms are domain-relevant but framed for an internal loop rather than natural user speech.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the loop needs to triage recent CI failures, open issues, or chat threads before deciding what to act on.'

Include natural user-spoken trigger phrases and synonyms (e.g. 'review failures', 'go through open issues') rather than only loop-consumer framing.

Name the prioritization capability explicitly (e.g. 'prioritizes findings into high-priority, watch, and noise buckets') to round out the action list.

Dimension	Reasoning	Score
Specificity	Names the triage domain and several concrete actions ('Triage recent changes, CI failures, issues, and conversations', 'Produces a concise, actionable findings report', 'Writes structured output to a state file or Linear board'), with only a minor gap (prioritization is implied but not stated as a capability).	4 / 5
Completeness	The 'what' is clear (triage inputs, produce report, write structured output) but there is no explicit 'Use when...' clause; the 'when' is only weakly implied by 'suitable for a loop to consume', capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant keywords like 'CI failures', 'issues', 'conversations', and 'Linear' appear, but the framing targets a 'loop' consumer rather than natural user phrasing, and common variations ('review failures', 'go through open issues') are missing.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct (loop-oriented triage producing a state-file/Linear report) with minimal overlap risk against unrelated skills; only minor overlap with general issue-management skills keeps it below 5.	4 / 5
	Total	14 / 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: cobusgreyling/loop-engineering
Path: skills/loop-triage/SKILL.md
Commit: 804a4e9

Reviewed: about 13 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.