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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

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 highly actionable, well-sequenced workflow document with strong validation loops and sensible fallback behavior for degraded environments. Its weaknesses are repetition of key rationales across sections and two reference files that require a second hop to discover.

Suggestions

Consolidate the repeated edit-don't-rewrite rule (stated in the intro, the 'From here on' paragraph, and Step 8) and the TASK-BRANCH dispatch rationale (Steps 4 and 6) into one authoritative statement each, cross-referenced by step.

Link registering-a-stack.md directly from Step 9 and wikilink-check.md directly from Step 7 instead of routing both through workflow-steps.md, so every bundle file is one hop from SKILL.md.

Trim or move the historical failure anecdotes (the 66-comment-line and '+85 vs -40' stories) into a reference file, keeping the rule and one-line rationale in SKILL.md.

DimensionReasoningScore

Conciseness

The 525-line body is dense with genuinely non-obvious procedural detail (no padding explaining concepts Claude already knows), but several rules are restated repeatedly: the edit-don't-rewrite PR-body rule appears three times (intro, 'From here on this file is only ever edited', Step 8), the TASK-BRANCH dispatch rationale is explained nearly verbatim in Steps 4 and 6, and the static-equivalent rule is stated three ways in one section. This is more than the 'minor instances of over-explanation' of anchor 4 — several passages could be tightened or consolidated.

3 / 5

Actionability

Fully executable throughout: a copy-paste heredoc skeleton, exact git/gh/bun/jq commands, the grep-based five-section verification, a complete PR-body template, and a precise label/type taxonomy. A handful of placeholders (e.g. '<parent-branch>') are inherent to the task, not pseudocode.

5 / 5

Workflow Clarity

Steps 0–10 are clearly sequenced with explicit validation checkpoints (validate-changesets.sh, the Step 8 grep count check) and genuine feedback loops ('re-run steps 3 and 4' after user changes, 'Re-run the check after that commit', re-validate after fixes), plus pre-declared fallbacks for no-network/no-gh/no-user conditions. This matches the anchor-5 example's validate-fix-retry structure.

5 / 5

Progressive Disclosure

Structure is good: SKILL.md stays an overview with one-level-deep references clearly signaled by path ('references/workflow-steps.md', 'references/issue-filing-example.md', 'references/auditing-defect-classes.md' — all real files). The gap is that two bundle files, registering-a-stack.md and wikilink-check.md, are only reachable via a second hop through workflow-steps.md — Step 9 says the stack-registration content 'is in references/workflow-steps.md' even though a dedicated file exists, a minor buried-reference issue.

4 / 5

Total

17

/

20

Passed

Description

92%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: concrete action list, explicit 'Use when' trigger, and a distinctive niche. The only gap is synonym coverage of natural trigger phrasings users might use instead of 'preparing... for a pull request'.

DimensionReasoningScore

Specificity

The description enumerates five concrete actions — 'resolving the base branch, checking changesets, running builds and reviews, filing findings as issues, and opening the PR with the mandatory five-section body' — comprehensively covering the skill's steps with no vague filler.

5 / 5

Completeness

It explicitly answers both: what ('resolving the base branch, checking changesets, running builds and reviews, filing findings as issues, and opening the PR') and when ('Use when preparing the current branch for a pull request'), with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Natural phrases users would say are present ('preparing the current branch for a pull request', 'PR'), but common variations like 'open a PR', 'raise a PR', or 'get this branch ready to merge' are missing. Anchor 5 requires synonym-level coverage; this sits noticeably above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The trigger 'preparing the current branch for a pull request' carves a clear niche (branch-prep workflow with changesets and a five-section PR body) that is distinct from adjacent skills like commit-message generation or generic code review, minimizing wrong-skill triggering.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (526 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

14

/

16

Passed

Repository
englishstreetventures/englishstreetventures.com
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.