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.

64

Quality

75%

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.

The content is a strong, actionable workflow with explicit verification checkpoints and a concrete partial-fix path, making it well-suited to a destructive triage operation. It is lean and executable, with only minor prose padding and no need for external bundle references.

DimensionReasoningScore

Conciseness

The body is mostly lean with executable commands and tight rationale, but the opening paragraph and a few prose asides ('how reporters get burned', 'treat the reporter as a partner') add mild over-explanation that could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready `gh` and `git` commands with clearly marked placeholders cover the common cases (view, grep log, show, merge-tree, close with comment), plus a concrete partial-fix comment example.

5 / 5

Workflow Clarity

A six-step numbered workflow has explicit validation checkpoints (verify the landed commit, confirm the real landing branch, 'No citation → not verified → do not close'), an error/feedback path (partial fix → note, don't close), and a red-flags checklist — fully meeting the destructive-operation validation requirement.

5 / 5

Progressive Disclosure

Well-organized single-file skill with clear sections (When to use, Workflow, Partial fix, Red flags) and only an inline one-level reference to a repo CI file; no bundle files exist, so structure is good but a touch over the simple-skill line length with minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

62%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 is specific and clearly distinct, naming the verify-then-close-with-credit behavior concisely. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when an issue appears resolved by a landed commit and you want to close it with credit.'

Include a couple of natural user-facing phrases ('close resolved issues', 'verify the fix landed') to improve trigger-term coverage.

Optionally enumerate the key actions (verify, credit, close) to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names concrete actions — 'verifying the landed commit/behavior', 'positive crediting comment', 'never from title alone' — covering the core close/verify/credit behavior, but it is a single compound sentence rather than a comprehensive list of distinct actions.

4 / 5

Completeness

The 'what' is clear (close verified resolved issues with a crediting comment), but there is no explicit 'Use when...' clause, so 'when' is only weakly implied — the missing trigger guidance caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant terms like 'resolved issues', 'landed commit', and 'crediting comment' appear, but natural user phrases are thin and lack common synonyms or a trigger phrasing a user would naturally say.

3 / 5

Distinctiveness Conflict Risk

Targets a narrow, well-defined niche (closing resolved Codewhale issues after commit verification) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

15

/

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.