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.

75

1.42x
Quality

79%

Does it follow best practices?

Impact

100%

1.42x

2 of 3 eval scenarios. Add 1 more for a full score.

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

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 tight, well-sequenced instruction skill: lean imperative guidance, explicit validation checkpoints, and a ready-to-use template. Its main defect is that the two referenced deep-dive files (AGENT-BRIEF.md, OUT-OF-SCOPE.md) are missing from the bundle, which both breaks navigation and undercuts the actionability of the brief-writing steps.

Suggestions

Ship the referenced files — add AGENT-BRIEF.md and OUT-OF-SCOPE.md to the bundle (or a references/ directory) so the "Reference docs" links resolve

If the files cannot be bundled, inline a minimal agent-brief skeleton in SKILL.md so the ready-for-agent step is self-sufficient

Consider moving the needs-info template and disclaimer block to a references file once one exists, keeping SKILL.md as a pure overview

DimensionReasoningScore

Conciseness

The body is lean and imperative throughout — "Every triaged issue should carry exactly one category role and one state role", "Wait for direction", "trust them and apply the role directly" — with no explanation of concepts Claude already knows. Dense lines like the PR delta ("a PR is an issue with attached code — same roles, same states, same machine") earn their tokens; nothing reads as padding.

5 / 5

Actionability

Guidance is concrete and executable: the mandatory disclaimer block, the copy-paste needs-info markdown template, named role states, and a worked state-transition map. It falls short of fully copy-paste-ready 5 because key detail is delegated to files that are not present ("post an agent brief comment ([AGENT-BRIEF.md](AGENT-BRIEF.md))") — the actual brief format is unavailable to the executing agent.

4 / 5

Workflow Clarity

The five-step triage sequence is explicit with genuine validation checkpoints: step 2's "Wait for direction", step 3's verification with three reported outcomes ("confirmed (with code path), failed, or insufficient detail (a strong needs-info signal)") forming a feedback loop into state choice, and the override rule "Confirm what you're about to do... then act". Semi-destructive actions (closing issues) are consistently gated on confirmation.

5 / 5

Progressive Disclosure

Sectioning is clean and references are clearly signaled in a dedicated "Reference docs" section, but the two referenced files — AGENT-BRIEF.md and OUT-OF-SCOPE.md — do not exist in the bundle (no references/ directory and no sibling files). Navigation to the detailed material is therefore broken, matching the 'references present but not usable / structure incomplete' level rather than the good-organization 4.

3 / 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, action-verb-rich description with good trigger terms, but it omits any explicit 'when to use this' guidance, which caps completeness. Adding a 'Use when...' clause with concrete trigger phrases would lift it into the top band.

Suggestions

Append an explicit trigger clause, e.g. "Use when the maintainer asks to triage, label, or categorise issues or external PRs, or to prepare issues for agent work"

Include natural synonyms users would say — "label", "categorize" (US spelling), "issue tracker", "close issues" — to broaden trigger coverage

Mention the ready-for-human / wontfix outcomes briefly so the action list is comprehensive, not just agent-brief oriented

DimensionReasoningScore

Specificity

The description lists several concrete actions — "categorise, verify, grill if needed, and write agent-ready briefs" — against a named domain ("issues and external PRs"). It falls short of the 5 anchor only in coverage: adjacent capabilities like posting needs-info questions, closing wontfix issues, or labelling states are absent.

4 / 5

Completeness

The "what" is clear (move issues/PRs through triage states: categorise, verify, grill, write briefs), but there is no "Use when..." clause or equivalent explicit trigger guidance — per the judging guidelines this caps completeness at 3 even though the what is unambiguous.

3 / 5

Trigger Term Quality

Good natural-term coverage: "issues", "external PRs", "triage", "agent-ready briefs" are phrases users would actually say. A few natural variations are missing (e.g., "label", "issue tracker", "close", the American spelling "categorize"), keeping it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The triage/state-machine niche ("state machine of triage roles" over "issues and external PRs") is distinct from general issue-management or code-review skills. Minor overlap risk remains with any skill that works on issue trackers or PRs, so it is mostly distinct rather than a clear 5.

4 / 5

Total

15

/

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

coder/agent-tty

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.