CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

88%

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 multi-step workflow skill: every step has copy-paste commands, explicit validation gates, and honest fallback behavior for degraded environments. Its weaknesses are verbosity in the persuasive/rationale passages and a slightly imperfect reference structure with two files buried a second level deep.

Suggestions

Tighten the repeated skeleton-first warnings in the opening section into a single statement, and compress the Step 5 and Step 10 case-study narratives (the 66-line and +85/−40 anecdotes) to one line each — the rules stand without the full stories.

Move the comment-line-delta rationale and traps (Step 5) into a reference file (e.g., alongside the auditing recipe) so the main body keeps only the command and the "look, don't gate" rule.

Reference `references/wikilink-check.md` and `references/registering-a-stack.md` directly from the relevant steps in SKILL.md so every reference file is reachable one level deep instead of only via `workflow-steps.md`.

DimensionReasoningScore

Conciseness

The bulk is load-bearing (commands, templates, label rules), but there is real tightening room: the skeleton-first rule is restated three ways in the opening section, and Step 5 and Step 10 carry multi-anecdote narratives (the 66-line comment anecdote, the +85/−40 story, the retro justification). Fits the score-3 anchor "mostly efficient but includes some unnecessary explanation or could be tightened" — not 4 because the padding is more than minor, not 2 because every aside encodes repo-specific measured failures rather than concepts Claude already knows.

3 / 5

Actionability

Fully executable throughout: a verbatim heredoc skeleton to copy, exact git/gh/bash commands, the complete five-section PR body template with tables, and the closing `grep -c` shape check. Specific commands cover the common cases including the no-network/no-gh fallbacks — the score-5 anchor.

5 / 5

Workflow Clarity

Eleven clearly sequenced steps with explicit validation checkpoints and feedback loops: the up-front environment probe, "Both must print `5`", re-running the changeset check after committing, and re-running steps 3 and 4 after user changes. This matches the score-5 anchor (clear sequence, explicit validation, feedback loops, checklists) — not 4, because no meaningful checkpoint is missing.

5 / 5

Progressive Disclosure

Content is genuinely split across five real, one-level-deep reference files, clearly signaled ("the recipe is in `references/workflow-steps.md`"). However, `wikilink-check.md` and `registering-a-stack.md` are reachable only through `workflow-steps.md` (two hops from SKILL.md), and long case-study narratives are inlined in the overview — "minor organization gaps" per the score-4 anchor rather than the fully one-level-deep score-5 structure.

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: explicit when-trigger combined with a comprehensive, concrete list of what the skill does, written in third-person gerunds. Trigger vocabulary is natural and specific to the PR-preparation workflow, with only minor synonym gaps.

DimensionReasoningScore

Specificity

The description lists five concrete, distinct 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 prep-PR domain with no generic filler. It matches the score-5 anchor (multiple specific concrete actions, comprehensive coverage) and not score 4, which would require a coverage gap.

5 / 5

Completeness

Both questions are explicitly answered: an explicit "Use when" clause plus a concrete what-list with trigger phrases — the exact score-5 anchor pattern. Not score 4, because the when-clause is specific rather than merely present.

5 / 5

Trigger Term Quality

Natural terms are present — "preparing the current branch for a pull request", "pull request"/"PR", "changesets", "issues" — exactly what a user would say. A few natural variants are missing (e.g., "push the branch", "stacked PR", "get this branch ready"), matching the score-4 anchor rather than the comprehensive synonym coverage of score 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (branch preparation for a PR) with distinct triggers; sibling review skills are dispatched by it, not trigger competitors. Matches "clear niche with distinct triggers; minimal conflict risk"; not score 4, since no closely related skill would fire on the same phrasing.

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

Path

.claude/skills/prep-pr/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.