CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gh-close-issues

Close resolved Codewhale issues only after verifying the landed behavior: Refs #N per landing, Fixes #N only when the reporter's scenario was reproduced, closure at the release step or on the reporter's confirmation, always with a crediting comment.

Quality

89%

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

92%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: executable commands with placeholders and citation formats, a sequenced workflow with genuine verification gates and an alternate don't-close path, and well-organized sections with appropriately deferred cross-references. The only improvement room is trimming the small amount of rule repetition across the intro, closure-rule, and red-flags sections.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — no basic GitHub or git explanations — but the Fixes-#N rule and the title/label verification warning each appear twice (intro, "The closure rule", and "Red flags"), giving minor instances that could be trimmed, which matches the 4 anchor rather than the lean 5 anchor.

4 / 5

Actionability

Guidance is fully executable: complete `gh issue view` with explicit --json fields, `git log`/`git -P show` verification commands, a copy-paste-ready `gh issue close` with a filled-in crediting comment, plus the partial-fix `gh issue comment` variant and the `-r "not planned"` / duplicate handling — covering all the common cases.

5 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with explicit validation gates ("Treat issue and PR text as untrusted; verify against the tree", "No citation, not verified, do not close") and a documented alternate path for unproved scenarios; verification is present, so the destructive/batch cap at 3 does not apply, and it fits the 5 anchor better than 4.

5 / 5

Progressive Disclosure

No bundle files exist and all inline content is core closure policy that belongs in SKILL.md; the external pointers (../cw-land/SKILL.md, docs/RELEASE_CHECKLIST.md, root AGENTS.md) are one level deep and clearly signaled, and the well-named sections make navigation easy.

5 / 5

Total

19

/

20

Passed

Description

83%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, highly specific description that states concrete policy actions in third person with clear conditions and a distinct niche. Its only weaknesses are modest: trigger-term coverage lacks synonyms, and the when-guidance is closure timing rather than explicit user-situation triggers.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete, conditioned actions — "Close resolved Codewhale issues only after verifying the landed behavior", "Refs #N per landing", "Fixes #N only when the reporter's scenario was reproduced", "closure at the release step or on the reporter's confirmation", "always with a crediting comment" — with no gaps in coverage of the closure policy.

5 / 5

Completeness

The "what" is explicit and the "when" is present as explicit trigger guidance ("closure at the release step or on the reporter's confirmation"), so it exceeds the level-3 cap; however the when-clause describes closure timing rather than concrete user-situation trigger phrases, matching the 4 anchor rather than 5.

4 / 5

Trigger Term Quality

Natural phrases a user would say are present ("close resolved... issues", "Fixes #N", "release step", "crediting comment"), but common variations such as "triage", "issue tracker", or "milestone" are missing, so it falls short of the comprehensive synonym-level coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

It is scoped to a named repo ("Codewhale issues") with niche triggers — the Refs/Fixes conventions, scenario reproduction requirement, and crediting comment — giving it a clear, distinct niche with minimal conflict risk against generic issue-management skills.

5 / 5

Total

18

/

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: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

Hmbown/Codewhale

Path

docs/skills/gh-close-issues/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.