CtrlK
BlogDocsLog inGet started
Tessl Logo

gh-close-issues

Close resolved CodeWhale issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone.

67

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 ./docs/skills/gh-close-issues/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-sequenced workflow skill with strong verification checkpoints and concrete commands throughout. The only real gap is progressive disclosure: it references auto-close-harvested.yml inline but ships no separate bundle files, so all detail lives in SKILL.md.

DimensionReasoningScore

Conciseness

Lean and largely assumes Claude's competence, with executable commands and no padding about what git/gh are; a few phrases ('is how reporters get burned', 'good-faith reports are evidence, not noise') are rhetorical framing that could be trimmed, keeping it just below a 5.

4 / 5

Actionability

Provides copy-paste-ready gh/git commands for every step with concrete flags and example comments, covering the common cases (close, wontfix, partial fix, harvest credit) with specific path:line and SHA citation guidance.

5 / 5

Workflow Clarity

A clearly numbered six-step workflow with explicit verification checkpoints ('No citation -> not verified -> do not close', confirm the fix landed on the cited branch), a dedicated partial-fix branch, and a red-flags section serving as an error-recovery checklist for a destructive/batch operation.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and one inline reference to a workflow file (auto-close-harvested.yml); no bundle files exist to offload detail, and that single reference is textual rather than a clearly signaled link, so it is good but not a fully navigable one-level-deep structure.

4 / 5

Total

18

/

20

Passed

Description

71%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, distinctive description that clearly conveys what the skill does and its hard constraints. Its main weakness is trigger-term coverage: it reads as a policy statement rather than enumerating the natural phrases a user would say to invoke it.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasings such as 'close this resolved issue', 'credit the reporter', or 'sweep the milestone for already-fixed issues'.

Include common synonyms and trigger variants users might say (e.g. 'mark issue as completed', 'close with thanks') alongside the repo-specific jargon.

Surface a couple of the concrete trigger scenarios from the body (merged PR harvest, milestone sweep) directly in the description to strengthen the 'when'.

DimensionReasoningScore

Specificity

Names the domain (closing CodeWhale issues) and multiple concrete actions — verifying the landed commit/behavior, posting a crediting comment, citing path:line or SHA — but the 'when' triggers are slightly under-specified relative to a fully enumerated list.

4 / 5

Completeness

Clearly states both what (close resolved issues after verifying the landed commit with a crediting comment) and a when-gate ('only after verifying... never from title alone'), but the 'when' is a constraint rather than an explicit 'Use when...' trigger clause, so it stops short of a 5.

4 / 5

Trigger Term Quality

Contains relevant keywords ('close', 'resolved', 'commit', 'crediting comment', 'release branch') but lacks the natural phrasings a user would actually say ('close this issue', 'sweep the milestone', 'credit the reporter') and omits synonyms; leans on repo-specific jargon rather than user-facing terms.

3 / 5

Distinctiveness Conflict Risk

Targets a narrow, specific niche (closing verified CodeWhale issues with crediting comments) with distinctive triggers and a strong 'never from title alone' boundary, making overlap with other skills minimal.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Hmbown/CodeWhale
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.