gh-find-prs

Survey open CodeWhale PRs and triage each for mergeability and disposition against the real landing branch.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./docs/skills/gh-find-prs/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and a well-sequenced, validated workflow — its strongest dimensions. It is slightly held back by redundancy between the workflow and the red-flags section, and by being entirely inline with no progressive-disclosure structure.

Suggestions

Trim the 'Red flags / don't' entries that restate steps 4–5 (mergeStateStatus, trivial-vs-real failures), keeping only the net-new cautions to reduce redundancy.

If the skill grows, split the CI job-decoding table or the disposition definitions into a reference file referenced one level deep from the workflow, to introduce progressive-disclosure structure.

Optionally move the CodeWhale CI job-name list into a short reference table so the main workflow stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and adds genuine domain knowledge (CI job names, the mergeStateStatus caveat), but the 'Red flags / don't' section restates guidance already given in steps 4–5, introducing mild redundancy that could be tightened.	2 / 3
Actionability	It provides exact, copy-paste-ready commands with flags and JSON fields ('gh pr list ... --json ...', 'git merge-tree --write-tree --messages <release-branch> <pr-head-sha>') plus a concrete credit-trailer format, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Seven clearly numbered steps run in sequence with an explicit validation checkpoint (the merge-tree exit-code/CONFLICT probe in step 5) and a one-of-four disposition checklist, satisfying the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is purely inline with no reference files and runs ~75 lines, exceeding the under-50-line simple-skill threshold that would let well-organized sections alone score 3.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 to a clear, low-conflict niche and states concrete actions, but it lacks an explicit 'Use when...' trigger clause and leans on a couple of technical terms over natural user phrasings. Completeness and trigger quality are the limiting dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when a maintainer asks what's in the PR queue, what can we land, or to triage open PRs before a release cut.'

Add natural user phrasings ('PR queue', 'what can we land', 'triage open PRs') to broaden trigger-term coverage beyond 'disposition' and 'landing branch'.

Consider naming a third concrete operation (e.g. 'test real mergeability with git merge-tree') to lift specificity from two high-level verbs to a fuller action list.

Dimension	Reasoning	Score
Specificity	The description names the domain and actions ('Survey open CodeWhale PRs and triage each for mergeability and disposition against the real landing branch'), but the verbs 'survey' and 'triage' are relatively high-level rather than a list of granular concrete operations as in the score-3 anchor.	2 / 3
Completeness	It clearly states what the skill does but contains no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 rather than reaching the what-and-both anchor.	2 / 3
Trigger Term Quality	'PRs', 'triage', and 'mergeability' are reasonably natural terms, but 'disposition' and 'landing branch' are technical and common user phrasings like 'what can we land?' or 'PR queue' are absent from the description itself.	2 / 3
Distinctiveness Conflict Risk	The scope is tightly bound to CodeWhale PR triage against a real landing branch — a clear niche with distinct triggers that is unlikely to fire for an unrelated skill.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: Hmbown/CodeWhale
Path: docs/skills/gh-find-prs/SKILL.md
Commit: f018d3e

Reviewed: about 14 hours ago

Table of Contents

Discovery Implementation Validation

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.