CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gh-find-prs

Survey the open Codewhale PR and issue queue read-only: fetch each item, check it against current code, and produce one coverage and disposition matrix with cited evidence and credit owed.

Quality

79%

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

81%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 tightly written, fully sequenced read-only workflow: concrete gh/git commands, explicit validation checkpoints, a concrete disposition taxonomy, and a red-flags checklist that together warrant top workflow-clarity marks. Remaining gaps are minor — a missing CI-log fetch command, mild repetition of the title and untrusted-data warnings, and cross-links to sibling skills that do not resolve in the bundle.

DimensionReasoningScore

Conciseness

Dense and free of concept explanations, with domain knowledge Claude would not have ('Version drift on a community PR is expected and not a blocker'), but the title rule is stated four times ('never the title', 'A title says nothing...', 'do not pattern-match the title', 'Don't judge by title') and the untrusted-data warning twice, so a few tokens could be trimmed.

4 / 5

Actionability

Nearly every step ships copy-paste-ready commands ('gh pr list --repo codewhale-hq/CodeWhale --state open --limit 200 --json ...', 'git merge-tree --write-tree --messages origin/main <pr-head-sha>') plus a concrete output table schema, but step 4's 'read the log' gives no command for actually fetching a CI log.

4 / 5

Workflow Clarity

Eight clearly sequenced steps with explicit validation checkpoints: check-failure triage ('a failing Test job or a clippy failure is real — read the log'), a mergeability probe with an explicit pass criterion ('Exit 0 with no CONFLICT lines is clean'), path:line evidence mandates, per-item confidence levels, and a red-flags checklist — the batch operation is fully validated, so the cap at 3 does not apply.

5 / 5

Progressive Disclosure

A well-sectioned single file (When to use / Workflow / Red flags / Output) with clearly signaled, one-level-deep cross-links ('[cw-land](../cw-land/SKILL.md) step 3'), but no bundle files exist and those sibling-skill paths do not resolve in the skill's directory, and the ~109-line body keeps everything inline.

4 / 5

Total

17

/

20

Passed

Description

70%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 states a clear, concrete 'what' and occupies a distinct read-only triage niche, but it entirely lacks a 'when to use' clause, which caps completeness at the midpoint. It also misses the natural trigger phrases ('triage', 'milestone sweep') that the body itself identifies. Adding an explicit trigger clause would resolve the main weakness.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g., 'Use when triaging the open PR/issue queue, sweeping a milestone before a release cut, or asking what can we land') so the 'when' half of completeness is stated rather than absent.

Fold in the natural trigger phrases the body already lists — 'triage these issues', 'what can we land', 'milestone sweep' — to broaden trigger-term coverage beyond 'PR and issue queue'.

Mention one or two of the omitted capabilities (mergeability probing against main, decoding CI check failures) to close the coverage gap that keeps specificity at 4.

DimensionReasoningScore

Specificity

Lists four concrete actions — 'fetch each item', 'check it against current code', 'produce one coverage and disposition matrix with cited evidence and credit owed' — but omits capabilities the body covers (mergeability probing, CI check decoding, fan-out for large queues), leaving minor gaps in coverage.

4 / 5

Completeness

The 'what' is explicit (survey, fetch, check against code, produce a matrix), but the description contains no 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

'PR and issue queue', 'survey', 'cited evidence' are natural terms a user might say, but common phrasings like 'triage', 'milestone sweep', or 'what can we land' appear only in the body's 'When to use' section and not in the description itself.

4 / 5

Distinctiveness Conflict Risk

'open Codewhale PR and issue queue read-only' plus 'coverage and disposition matrix' carves out a repo-specific, survey-only niche with distinct outputs, minimizing overlap with merge, land, or code-review skills.

5 / 5

Total

16

/

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: 4 suspicious

Warning

Total

15

/

16

Passed

Repository

Hmbown/Codewhale

Path

docs/skills/gh-find-prs/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.