CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

triage-issue

Assess community issues, validate technical claims, request missing evidence, and prepare valid work for human disposition.

Quality

80%

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-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary instruction-only skill body: lean, dense with project-specific policy, fully actionable with concrete commands and an exact output format, and a well-gated workflow with authorization checkpoints and feedback loops. External detail is appropriately deferred to one-level references.

DimensionReasoningScore

Conciseness

The ~30-line body is pure directive with no concept explanations; every line carries project-specific policy such as "the general issue lifecycle uses `state:*` labels, but their exact names may change" and "Do not infer that a label alone authorizes bulk changes." It assumes Claude's competence and every token earns its place.

5 / 5

Actionability

The guidance is fully executable for an instruction-only skill: a copy-paste-ready `gh issue view <id> --json number,title,body,state,labels,author,comments` command, an exact comment prefix `> **📋 triage-agent**`, per-type checks for bugs/features/UX proposals, and an enumerated outcome taxonomy (confirmed bug, feasible feature, missing evidence, duplicate, already-fixed, expected). Common cases are concretely covered.

5 / 5

Workflow Clarity

A clear 7-step sequence with explicit validation and feedback loops: authorization gate before batch label/comment changes ("show the issue count and a sample of titles and obtain explicit authorization"), conditional handling for absent user stories and failed reproductions, and an uncertainty branch recommending `create-spike`. The batch-operation cap does not apply because validation checkpoints are present.

5 / 5

Progressive Disclosure

Under 50 lines with well-organized sections ("Scope and authorization", "Assess one issue") and clearly signaled one-level-deep references to CONTRIBUTING.md's labeling section and the `/label-issue` skill; no nested reference chains and no content that should be split out.

5 / 5

Total

20

/

20

Passed

Description

55%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 names several concrete capabilities in third person but lacks any explicit trigger guidance, so it answers "what" without "when". It also omits the natural vocabulary of its domain (triage, GitHub issues, bug reports), weakening both trigger matching and distinctiveness against sibling issue-handling skills.

Suggestions

Add a 'Use when...' clause, e.g. "Use when asked to triage or assess a GitHub issue, bug report, or feature request in the OpenShell repo."

Include natural trigger terms such as "triage", "GitHub issues", "bug reports", and "feature requests" so the description matches how users actually phrase the request.

Replace the abstract "prepare valid work for human disposition" with a concrete action like "summarize assessment outcomes for maintainer decision".

DimensionReasoningScore

Specificity

"Assess community issues", "validate technical claims", and "request missing evidence" are concrete actions, matching the several-specific-actions anchor; however "prepare valid work for human disposition" is comparatively abstract, keeping it below the comprehensive 5 anchor.

4 / 5

Completeness

The "what" is clear (assess, validate, request evidence, prepare for disposition) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"community issues", "technical claims", and "evidence" are relevant keywords, but the natural phrases a user would actually say are missing: "triage", "GitHub issues", "bug reports", "feature requests". This matches the some-relevant-keywords-but-missing-variations anchor.

3 / 5

Distinctiveness Conflict Risk

The issue-assessment focus is somewhat specific, but in a repo with closely related sibling skills (label-issue, build-from-issue, create-spike) and without "triage" or "GitHub" terms, it could still overlap with those similar skills.

3 / 5

Total

13

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

13

/

16

Passed

Repository

NVIDIA/OpenShell

Path

.agents/skills/triage-issue/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.