CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

triage-issue

Triage and classify new issues for the CSC database repository. Use this skill whenever an issue is opened, assigned to you, or needs classification. Trigger on: new issue triage, "classify this issue", "what type of issue is this", labelling requests, issue assignment, data correction reports, data addition requests, bug reports, feature requests, or any time you need to categorise, label, prioritise, or respond to a GitHub issue. Also use when deciding whether an issue can be auto-fixed or needs human intervention.

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 well-crafted, highly actionable single-file skill with tight tables, exact labels and assignees, and copy-paste response templates. It scores slightly below top on workflow clarity (no explicit validation/ambiguity-handling checkpoint) and progressive disclosure (full templates inline in a ~95-line body rather than split into a references file).

Suggestions

Add a brief validation checkpoint to Step 1 or Step 4 (e.g., what to do when an issue fits multiple categories or when classification is uncertain) to strengthen workflow clarity.

Move the full response templates into a references file (e.g., references/templates.md) and keep one-line summaries inline, reducing SKILL.md length and improving progressive disclosure.

DimensionReasoningScore

Conciseness

Uses compact category/severity tables and terse bullet lists, never explaining concepts Claude already knows (e.g., no "what a GitHub issue is" preamble), and the response templates carry only needed content. Lean and efficient throughout, so not a 4.

5 / 5

Actionability

Provides exact label strings (`data-correction`, `priority:high`), specific assignees (@dr5hn), and copy-paste-ready response templates with links covering the three common cases (corrections, additions, bug reports). Fully actionable instruction-only guidance with no gaps in common flows, so not a 4.

5 / 5

Workflow Clarity

Presents a clear 5-step sequence (Classify → Entity labels → Severity → Action → Respond) with explicit decision branches (auto-fix / needs contributor / needs maintainer). Not a 5 because there is no explicit validation checkpoint (e.g., guidance for issues fitting multiple categories or uncertain classification); not a 3 because the sequence is complete, well-defined, and does not involve destructive or batch operations requiring a validation cap.

4 / 5

Progressive Disclosure

Well-organized sections with headers and tables, no nested or buried references, and no bundle files — all content appropriately inline. Not a 5 because at ~95 lines it exceeds the under-50-line simple-skill exception and the full response templates could be split into a references file; not a 3 because structure and navigation are clear.

4 / 5

Total

18

/

20

Passed

Description

95%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 strong description that clearly states the skill's purpose, provides comprehensive natural trigger phrases including quoted user utterances, and defines a distinct niche with minimal conflict risk. The only deduction is a second-person phrase ("assigned to you") that violates the third-person voice guideline and reduces specificity by one point.

Suggestions

Rephrase "assigned to you" in third person (e.g., "assigned to the agent") to comply with the third-person voice guideline and recover the specificity penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Triage and classify new issues", "categorise, label, prioritise, or respond to a GitHub issue", "deciding whether an issue can be auto-fixed or needs human intervention" — which is comprehensive coverage (base 5), but the second-person phrasing "assigned to you" triggers the rubric's 1-point voice penalty. It is not a 3 because it names far more than 1-2 actions, and not a 5 because of the voice penalty.

4 / 5

Completeness

Explicitly answers both what ("Triage and classify new issues for the CSC database repository") and when ("Use this skill whenever an issue is opened, assigned to you, or needs classification. Trigger on: ... Also use when deciding whether an issue can be auto-fixed"). Matches the anchor-5 pattern with concrete trigger phrases, so not a 4.

5 / 5

Trigger Term Quality

Includes verbatim natural user utterances ("classify this issue", "what type of issue is this") plus synonyms across all issue types ("new issue triage", "labelling requests", "data correction reports", "data addition requests", "bug reports", "feature requests"). Comprehensive natural-term coverage; nothing meaningful missing, so not a 4.

5 / 5

Distinctiveness Conflict Risk

Clearly niched to "the CSC database repository" GitHub issue triage with distinct, domain-specific triggers (data correction/addition reports, entity labelling), minimizing conflict risk with generic issue-management skills. Not a 4 because the repository-specific framing leaves only minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dr5hn/countries-states-cities-database

Path

.github/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.