CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./starters/minimal-loop/.grok/skills/loop-triage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, well-structured, instruction-only skill: lean on tokens, concrete about the deliverable, with sound prioritization rules and a valuable untrusted-input safety block. Its main weaknesses are minor: implicit step sequencing, no dedupe guidance against the state file, and a referenced maintenance script that is absent from the bundle.

Suggestions

Add one line telling the agent how to treat items already recorded in the state file (e.g. 'Do not re-report items the state file already tracks; only surface changes to them').

Either ship the referenced scripts/sync-untrusted-input.mjs in the bundle or drop the path from the generated-block comment so no referenced path is dangling.

Give a concrete scale for 'Rough effort estimate' (e.g. S/M/L with one-line definitions) to make the per-item format fully copy-paste ready.

DimensionReasoningScore

Conciseness

The ~50-line body is lean and assumes Claude's competence: inputs, a tightly specified output format, decision rules, and a dense safety block, with no concept over-explanation or padding. Every section earns its place, matching the anchor for lean, efficient content.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: exact report sections, a per-item format ('Clear, one-line description', 'Why it matters', 'Suggested next action', 'Rough effort estimate'), and a concrete example state update ('PR #1234 now has 2 approvals'). Minor gaps — no effort-estimate scale and the 'reasonable engineer would want to know about it today' threshold is left to judgement — keep it below fully copy-paste-ready.

4 / 5

Workflow Clarity

The flow (review the listed inputs, categorize items into High-Priority/Watch/Noise, emit State Updates) is clear and unambiguous for a single-deliverable skill, and the read-only nature means the destructive/batch validation cap does not apply. It falls short of 5 because sequencing is implicit and there is no guidance on deduplicating against what the state file already knows.

4 / 5

Progressive Disclosure

Sections are well organized (Inputs, Output Format, Rules, Untrusted input) and the skill is short and single-topic enough that no external references are needed. However, the generated-block comment cites 'scripts/sync-untrusted-input.mjs', which does not exist in the bundle — a dangling referenced path that is a minor organization defect.

4 / 5

Total

17

/

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.

A specific, third-person description with concrete actions and good natural trigger terms, but it lacks any explicit 'when to use' guidance, which caps its completeness. Adding a 'Use when...' clause tied to its existing keywords would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the loop needs to triage CI/test failures, new issues, or recent activity before deciding what to act on.'

Include a few more natural synonyms in the description, such as 'failing tests', 'flaky tests', or 'incident triage', to broaden keyword coverage.

Sharpen the distinction from generic triage/review skills by naming the consumer explicitly earlier (e.g. lead with 'loop triage' framing rather than only 'recent changes').

DimensionReasoningScore

Specificity

The description lists 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 minor gaps in coverage. It does not reach 5 because it stops short of comprehensively describing what the triage covers for each input type.

4 / 5

Completeness

It clearly answers 'what' (triage inputs, produce a findings report, write structured output) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is above 2 because the 'what' is specific and multi-part rather than vague.

3 / 5

Trigger Term Quality

Natural keywords like 'triage', 'CI failures', 'issues', 'conversations', 'Linear board', and 'state file' are present and would be said by a user needing this skill. A few natural variations are missing (e.g. 'failing tests', 'flaky tests', 'incidents'), keeping it below comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The loop-oriented framing ('suitable for a loop to consume', 'state file or Linear board') carves a distinct niche with minor overlap risk against generic issue-triage or code-review skills. It is not 5 because 'Triage recent changes, CI failures, issues' alone could plausibly trigger adjacent triage-style skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

starters/minimal-loop/.grok/skills/loop-triage/SKILL.md

Reviewed

Table of Contents

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.