CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

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-structured, highly actionable triage playbook that is token-efficient and free of padding. It falls just short of top marks on workflow clarity (no verification steps like duplicate-checking or label confirmation) and progressive disclosure (response templates inlined in a ~95-line body).

Suggestions

Add a lightweight verification step to the workflow, e.g., before responding: search for existing open issues covering the same report and confirm the applied labels match the category/severity tables.

Move the three response templates into a references/response-templates.md file and link to them from Step 5 to slim the main body below ~50 lines.

DimensionReasoningScore

Conciseness

Every element — category/severity label tables, assignee rules (@dr5hn, @copilot), response templates, and policy rules — is repo-specific knowledge Claude could not infer, with zero concept explanations or padding. Not 4: there is no over-explanation to trim; each table and template earns its tokens.

5 / 5

Actionability

The body provides exact labels (`data-correction`, `priority:high`), concrete category→label and severity tables, specific assignees, and copy-paste-ready response templates with links to the contribution guidelines and update tool. Not 4: guidance is fully executable for the common triage cases; as an instruction-only skill the absence of code is not penalized.

5 / 5

Workflow Clarity

A clear five-step sequence (classify → entity labels → severity → action → respond) with explicit guardrails ("Do not close issues without maintainer approval"), but no validation checkpoints such as checking for duplicate issues or confirming labels were applied. Not 5: no explicit validation/feedback steps exist; not 3: the sequence is complete and the operations (labeling, commenting) are low-risk, so the missing-validation cap does not apply.

4 / 5

Progressive Disclosure

The single-file body is well-organized with clearly headed sections and no buried references (none exist), but at ~95 lines the response templates are inlined content that could be split into a references file. Not 5: it exceeds the under-50-line simple-skill exception and inlines template content; not 3: structure is good, nothing is disorganized or nested.

4 / 5

Total

18

/

20

Passed

Description

96%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 what the skill does and when to use it, with rich natural trigger phrases and repo-specific anchoring. Its only weakness is that several trigger terms (bug reports, feature requests) are generic enough to overlap with broader issue-management skills.

DimensionReasoningScore

Specificity

"Triage and classify new issues", "categorise, label, prioritise, or respond to a GitHub issue", and "deciding whether an issue can be auto-fixed or needs human intervention" list multiple concrete actions with comprehensive coverage of the triage domain. Not 4: there are no minor gaps — the actions span classification, labeling, prioritization, response, and auto-fix decisions.

5 / 5

Completeness

The description explicitly answers 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: …") with concrete trigger phrases. Not 4: the when-clause is explicit and specific, not merely present.

5 / 5

Trigger Term Quality

Natural trigger phrases include "new issue triage", "'classify this issue'", "'what type of issue is this'", "labelling requests", and "data correction reports", covering synonyms and common user phrasings. Not 4: it includes quoted natural-language variations rather than missing a few common terms.

5 / 5

Distinctiveness Conflict Risk

The description is anchored to a specific repository and workflow ("CSC database repository", auto-fix vs. human intervention), but generic terms like "bug reports", "feature requests", and "issue assignment" carry minor overlap risk with general issue-management skills. Not 5: those generic trigger terms could fire for closely related issue-triage skills; not 3: the niche is clearly and consistently defined.

4 / 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
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.