triage

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

1.42x

Quality

—

Does it follow best practices?

Impact

100%

1.42x

Average score across 2 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, lean, highly actionable workflow with clear sequencing and validation checkpoints, undermined by progressive disclosure that points to two bundle files (AGENT-BRIEF.md, OUT-OF-SCOPE.md) which are not actually present in the skill bundle.

Suggestions

Add the missing AGENT-BRIEF.md and OUT-OF-SCOPE.md bundle files (or move their content inline / remove the references) so the one-level-deep pointers resolve.

If those details are short, consider inlining them rather than relying on external files that may drift out of sync with SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding, no explaining of basic concepts — and every line (roles, states, transitions, templates) earns its place.	3 / 3
Actionability	It gives concrete, executable guidance: canonical role names, exact state transitions, a copy-paste needs-info template, and the AI-disclaimer block, all specific rather than abstract.	3 / 3
Workflow Clarity	The triage flow is a clearly numbered sequence with explicit checkpoints (gather context, verify before grilling, confirm before acting) and feedback loops (redundancy and prior-rejection checks, re-evaluation on reporter replies).	3 / 3
Progressive Disclosure	The body references [AGENT-BRIEF.md](AGENT-BRIEF.md) and [OUT-OF-SCOPE.md](OUT-OF-SCOPE.md), but neither file exists in references/, scripts/, assets/, or the skill root — the links are broken, so the disclosed content is unreachable.	1 / 3
	Total	10 / 12 Passed

Description

67%

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 a distinct niche, but it omits any explicit "when to use" trigger guidance, which caps completeness and leaves trigger-term coverage partial.

Suggestions

Add a 'Use when...' clause naming the natural phrasings a maintainer would say (e.g. 'Use when triaging issues or reviewing external PRs on the project tracker').

Include common trigger variations such as 'review PRs', 'go through issues', or 'what needs my attention' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "categorise, verify, grill if needed, and write agent-ready briefs" — rather than vague language, matching the multi-action anchor.	3 / 3
Completeness	It clearly answers what the skill does but has no "Use when..." clause or equivalent trigger guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes some natural terms users would say ("issues", "external PRs", "triage") but misses common variations like "review PRs" or "go through issues", so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The triage-of-issues-and-PRs niche with "state machine of triage roles" is a distinct, narrow trigger unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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
relative_links	Relative link issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: coder/agent-tty
Commit: fae02cb

Reviewed: 3 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.