CtrlK
BlogDocsLog inGet started
Tessl Logo

prep-pr

Use when preparing the current branch for a pull request — resolving the base branch, checking changesets, running builds and reviews, filing findings as issues, and opening the PR with the mandatory five-section body.

68

Quality

84%

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

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.

A high-quality, executable multi-step workflow with strong validation and feedback loops and well-structured references. Its one real weakness is conciseness — the prose over-justifies and repeats itself, inflating the token budget beyond what the instructions alone require.

Suggestions

Trim the rhetorical admonitions that restate the same failure mode across sections (e.g. the repeated "a section goes missing" warnings) to a single statement; the rule only needs to land once.

Reduce the 'why' justification in the opening skeleton section ("Creating it first means the shape is already right…") to one line, keeping the heredoc and the hard rule but cutting the extended rationale.

Link the two un-referenced bundle files (registering-a-stack.md, wikilink-check.md) by path from the relevant steps, or fold their content into workflow-steps.md, so every reference file is discoverable from the body.

DimensionReasoningScore

Conciseness

It assumes Claude's intelligence (no explaining git or PRs) and most prose earns its place, but it is lengthy with repeated rhetorical admonitions and extensive justifications of why rather than just instructing — it could be tightened without losing clarity.

3 / 5

Actionability

Fully executable throughout — concrete bash commands (git config, git diff, validate-changesets.sh, bun run pr-metrics, gh pr create --base), exact filenames, exact heading shapes, and a copy-paste-ready PR-body skeleton covering the common cases.

5 / 5

Workflow Clarity

Steps 0–9 are clearly sequenced with explicit validation checkpoints (the upfront gate probe, validate-changesets.sh, the grep shape check that must print 5) and feedback loops (re-run steps 3–4 after changes; read back the skeleton before editing), matching the top anchor.

5 / 5

Progressive Disclosure

Body content is appropriately split into clearly signaled one-level-deep references (workflow-steps.md, issue-filing-example.md, auditing-defect-classes.md — all real files), but two bundled reference files (registering-a-stack.md, wikilink-check.md) are not linked by path from the body, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: explicit trigger, concrete enumerated actions, and a distinctive niche. The only soft spot is slightly limited synonym coverage in the trigger phrasing and a mildly abstract lead verb.

DimensionReasoningScore

Specificity

Names several concrete actions — "resolving the base branch, checking changesets, running builds and reviews, filing findings as issues, and opening the PR" — but the lead verb "preparing the current branch" is slightly abstract, leaving minor coverage gaps versus a fully enumerated list.

4 / 5

Completeness

Clearly answers both what (the em-dash list of concrete actions) and when (an explicit "Use when" clause with a concrete trigger phrase), matching the top anchor.

5 / 5

Trigger Term Quality

"Use when preparing the current branch for a pull request" is a natural phrase and "pull request" / "PR" appear, but synonyms like "opening a PR" or "creating a PR" are thin, so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

"Preparing the current branch for a pull request" with "the mandatory five-section body" carves a clear niche unlikely to fire for unrelated skills, with minimal conflict risk.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
xchromo/osn
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.