CtrlK
BlogDocsLog inGet started
Tessl Logo

triage

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

68

1.42x
Quality

64%

Does it follow best practices?

Impact

100%

1.42x

Average score across 2 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/triage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 a well-structured, actionable triage workflow with explicit validation checkpoints, a copy-paste needs-info template, and clean shallow references to per-topic docs. It is concise without padding and assumes Claude's competence, losing only minor points for a few implicit checkpoints and unverifiable bundle references.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no beginner-level padding about what issues or PRs are), with each section earning its place; only a few sentences could be trimmed, so it sits above the midpoint but short of fully lean.

4 / 5

Actionability

It gives concrete, executable guidance — the needs-info template is copy-paste ready, states are named explicitly, and steps like 'check out the diff, run the relevant tests' are specific — with only minor gaps (e.g. exact tracker query commands are delegated elsewhere).

4 / 5

Workflow Clarity

The 'Triage a specific issue or PR' section is a clearly numbered sequence with explicit validation checkpoints (redundancy check, prior-rejection check, 'Verify the claim' before grilling, 'Wait for direction'), plus a separate quick-override path; a couple of checkpoints are implicit rather than enforced, keeping it just below 5.

4 / 5

Progressive Disclosure

The SKILL.md is a well-organized overview with clearly signaled one-level-deep references ([AGENT-BRIEF.md], [OUT-OF-SCOPE.md]) and a dedicated Reference docs section; the referenced bundle files are not present in the working tree to verify, but the in-body navigation is clean and shallow, placing it just above the midpoint.

4 / 5

Total

16

/

20

Passed

Description

57%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 conveys what the skill does and names several concrete actions, giving it solid specificity and distinctiveness. Its main weakness is the absence of an explicit 'Use when...' trigger clause and thinner natural-keyword coverage, which cap completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when triaging issues or external pull requests on the project tracker, or when the maintainer asks what needs attention.'

Include natural user-facing keywords and synonyms such as 'bugs', 'feature requests', 'GitHub issues', and 'issue tracker' so the description matches how users actually phrase the request.

Consider naming the terminal states (e.g. 'mark ready-for-agent, needs-info, or wontfix') to round out the concrete actions and improve distinctiveness.

DimensionReasoningScore

Specificity

The phrase 'categorise, verify, grill if needed, and write agent-ready briefs' lists several concrete actions (categorise, verify, grill, write briefs) over the domain, with only minor gaps in coverage of the full state-machine outcomes.

4 / 5

Completeness

The 'what' is clearly stated (move issues/PRs through triage roles), but there is no 'Use when...' clause or equivalent trigger guidance, so the 'when' is only weakly implied — the rubric caps this at 3.

3 / 5

Trigger Term Quality

It surfaces natural terms like 'issues', 'PRs', and 'triage' but omits common synonyms a user would actually say ('bugs', 'feature requests', 'issue tracker', 'GitHub issues') and any canonical trigger phrasing.

3 / 5

Distinctiveness Conflict Risk

The triage/issue-tracker state-machine framing is a fairly clear niche that is unlikely to fire for unrelated skills, with only minor overlap risk against general issue-management or grilling 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
coder/agent-tty
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.