pr-workflows

Turn issues into PRs, handle commits, and run prek checks consistently.

Quality

46%

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 ./.agents/skills/pr-workflows/SKILL.md

Quality

Content

47%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 admirably concise and well-structured as an overview, but it provides no executable commands or concrete steps and relies entirely on reference files that are not present in the bundle, leaving it unactionable as written. Workflows also lack the validation checkpoints expected for commit and prek-fixing operations.

Suggestions

Provide at least minimal executable guidance inline — e.g. the actual prek command to run and the commit message format to follow — rather than only pointing to reference files.

Add explicit validation/feedback steps for prek and commit workflows (run prek -> read failures -> fix -> re-run) since these are batch/destructive-adjacent operations that the rubric requires checkpoints for.

Either ship the referenced files under reference/ (issue-to-pr.md, committing.md, prek.md) or correct the paths so the references resolve; missing reference targets break progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding, no explaining what a PR or commit is, every line earning its place, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It gives high-level hints ('Turning an issue into a PR', 'Running prek checks and fixing hook output') but no concrete commands, code, or specific steps to execute, fitting 'minimal concrete guidance; high-level hints but missing the specific steps'.	2 / 5
Workflow Clarity	A rough 'When to use' list implies a sequence but steps are poorly defined and validation/feedback loops for prek hook fixing and commits are absent, matching 'rough sequence present but many gaps; validation absent'.	2 / 5
Progressive Disclosure	References are signaled but point to a 'reference/' path that does not exist in the bundle, and no bundle files are actually provided, so navigation is broken; this fits the 'references are buried / minimal structure' lower-to-mid band, settling at 2 because the referenced files are missing.	2 / 5
	Total	11 / 20 Passed

Description

45%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 names a concrete domain and several actions in concise third-person voice, but lacks any explicit 'Use when...' trigger guidance, which both limits completeness and leaves the activation context implicit. It is reasonably distinct from other skills due to the prek reference.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when turning an issue into a PR, preparing commits, or running/fixing prek checks.'

Include natural user phrasings and synonyms (e.g. 'pull request', 'commit message', 'pre-commit hooks') so the description matches what users actually say.

Expand the actions slightly (e.g. 'write commit messages', 'summarize PRs', 'resolve prek hook failures') to move from generic verbs toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Turn issues into PRs, handle commits, and run prek checks') but each is generic and not elaborated, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	A clear 'what' is present but there is no 'Use when...' clause or any explicit trigger guidance, and per judging guidelines a missing 'Use when' clause caps completeness at 3; here 'when' is entirely absent so it sits at the lower anchor.	2 / 5
Trigger Term Quality	Relevant terms (issues, PRs, commits, prek) are present but missing common variations or synonyms a user would naturally say, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The prek-specific term and the issue-to-PR framing carve a fairly distinct niche with only minor overlap risk against general git/PR skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: pymc-labs/CausalPy
Path: .agents/skills/pr-workflows/SKILL.md
Commit: f94d7af

Reviewed: 3 days 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.