CtrlK
BlogDocsLog inGet started
Tessl Logo

gh-find-prs

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

64

Quality

76%

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-find-prs/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 body is a strong, highly actionable read-and-recommend workflow: concrete executable commands, explicit validation checkpoints driving a clear disposition decision tree, and a useful don't-checklist. Its only real weakness is mild redundancy between the red-flags section and earlier workflow steps, and a monolithic single-file structure that leaves minor progressive-disclosure headroom.

Suggestions

Tighten the 'Red flags / don't' section by referencing the corresponding workflow steps instead of restating them, removing the conciseness redundancy.

Consider splitting the CI-job catalog and the full disposition/credit-trailer spec into a one-level-deep reference file (e.g. DISPOSITIONS.md) to improve progressive disclosure, leaving SKILL.md as a tighter overview.

Add an explicit 'if a real Test/clippy failure appears, read the log and re-classify the disposition' feedback loop to make the error-recovery path in step 4 concrete.

DimensionReasoningScore

Conciseness

The body is lean and command-driven with little concept over-explanation, but the 'Red flags / don't' section lightly reiterates rules already stated in steps 2, 4, and 6, which is minor over-explanation that could be trimmed — matching the 'efficient; minor instances of over-explanation that could be trimmed' anchor.

4 / 5

Actionability

It provides fully executable, copy-paste-ready commands (gh pr list/view/diff, git branch, git merge-tree --write-tree --messages, cargo fmt/clippy) plus concrete disposition definitions and credit trailers, covering the common cases — matching the 'fully executable; copy-paste ready' anchor.

5 / 5

Workflow Clarity

A clear 7-step numbered sequence with explicit validation (merge-tree result interpretation in step 5, trivial-vs-real check classification in step 4) feeding a disposition decision tree, plus a red-flags checklist — matching the 'clear sequence with explicit validation steps; checklists' anchor. The skill is explicitly read-only (no destructive operations), so the missing-retry cap does not apply.

5 / 5

Progressive Disclosure

Content is well-organized into clear sections (When to use, Workflow, Red flags) with no nested references and no wall of text, but it is a monolithic single ~73-line file with all content inlined and no external references, fitting the 'good structure; most content appropriately placed; minor organization gaps' anchor rather than a clean one-level-deep reference split.

4 / 5

Total

18

/

20

Passed

Description

65%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 distinctive, clearly carving out a CodeWhale PR-triage niche, but it omits an explicit 'Use when...' trigger clause and relies on maintainer jargon over the most natural user phrasings. Its strongest dimension is distinctiveness; completeness is capped by the missing trigger guidance.

Suggestions

Append an explicit 'Use when...' trigger clause naming natural maintainer phrasings (e.g., 'Use when a maintainer asks what's in the PR queue, what can we land, or to triage open PRs').

Add a couple of natural synonyms a user would actually say ('PR queue', 'what can we land/merge') to broaden trigger-term coverage beyond 'mergeability' and 'disposition' jargon.

Optionally name the disposition outcomes (DIRECT-MERGE / HARVEST / DEFER / CLOSE-WITH-NOTE) in the description to make the capability set more comprehensive.

DimensionReasoningScore

Specificity

Names the domain ('CodeWhale PRs') and a few concrete actions ('Survey', 'triage each for mergeability and disposition') but does not comprehensively enumerate the actions or dispositions, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.

3 / 5

Completeness

It clearly states what the skill does but provides no explicit 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 3 ('has a clear what but when is missing or only weakly implied').

3 / 5

Trigger Term Quality

Includes several natural maintainer keywords ('PRs', 'triage', 'mergeability', 'disposition') with good coverage; a few natural user phrasings like 'what can we land' or 'PR queue' are absent, fitting the 'good keyword coverage; a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

It targets a narrow, specific niche (triaging CodeWhale PR mergeability against the real landing branch) with distinct triggers, giving it a clear niche with minimal conflict risk.

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.