CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

triage

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

Quality

76%

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 ./.agents/skills/triage/SKILL.md

The canonical home for this skill is triage in mattpocock/skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%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, highly actionable workflow document with excellent sequencing and validation checkpoints; its one real defect is that both referenced bundle files are missing, so critical detail (brief structure, out-of-scope KB) is unreachable. Adding the two referenced files — or inlining their essentials — would make this near-perfect.

Suggestions

Add the referenced AGENT-BRIEF.md and OUT-OF-SCOPE.md to the bundle (e.g. under references/), since both links currently point at nonexistent files.

Alternatively, inline a minimal agent-brief skeleton (as done well for the needs-info template) so the primary output format is usable even without the external file.

State where the referenced files live relative to the skill directory if they are meant to be created elsewhere, so navigation does not dead-end.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and free of padding: roles, state transitions, and the disclaimer rule are stated once with no explanation of concepts Claude already knows. Every token earns its place across the ~113 lines.

5 / 5

Actionability

Concrete, executable guidance throughout — named roles, transition rules, invocation examples, a complete needs-info template — but the agent-brief format (the skill's primary output) is deferred to AGENT-BRIEF.md rather than specified, leaving a minor gap.

4 / 5

Workflow Clarity

The five-step sequence (gather, recommend, verify, grill, apply) is clearly ordered with explicit checkpoints: 'Wait for direction', 'flag it and ask the maintainer before doing anything else' on conflicting roles, and confirmation before quick state overrides. Verification outcomes (confirmed / failed / insufficient detail) form a proper feedback loop.

5 / 5

Progressive Disclosure

The body is well-sectioned and its two references ([AGENT-BRIEF.md](AGENT-BRIEF.md), [OUT-OF-SCOPE.md](OUT-OF-SCOPE.md)) are clearly signaled and one level deep — but neither file exists in the bundle (no references/ directory), so both links dead-end and the disclosure chain is broken.

3 / 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 conveys concrete capabilities in a distinctive niche but reads as a capability list rather than a trigger: it has a clear 'what' and no 'when'. Adding an explicit usage clause with natural trigger phrases would lift the completeness and trigger-term dimensions together.

Suggestions

Append a trigger clause such as 'Use when the maintainer asks to triage, categorise, or review issues or external PRs, or wants agent-ready briefs for them.'

Include natural user phrasings and synonyms — e.g. 'triage issues', 'review PRs', 'categorize' (US spelling) — so the skill surfaces when users describe the task in their own words.

Briefly enumerate the remaining capabilities (querying what needs attention, posting needs-info notes, resuming prior triage sessions) for more complete coverage.

DimensionReasoningScore

Specificity

Names several concrete actions — 'categorise, verify, grill if needed, and write agent-ready briefs' — against a specific issue-tracker domain, but 'state machine of triage roles' is abstract and coverage has minor gaps (no mention of querying for attention, needs-info notes, or resuming).

4 / 5

Completeness

The 'what' is clear (move issues/PRs through triage roles, categorise, verify, grill, write briefs) but there is no 'Use when...' clause or equivalent trigger guidance, which the guidelines cap at 3.

3 / 5

Trigger Term Quality

'issues', 'external PRs', and 'triage' are relevant keywords, but natural user phrasings like 'triage issues', 'review bugs', or 'label issues' are absent, and the British 'categorise' misses the common 'categorize' variant.

3 / 5

Distinctiveness Conflict Risk

'triage roles', 'agent-ready briefs', and 'external PRs' carve a clear niche with distinct triggers, with only minor overlap risk against generic issue/PR-review skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

withcoral/coral

Path

.agents/skills/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.