CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pm-simplify

This skill should be used when the user asks to "simplify this", "simplify the diff", "clean up this code", "clean up the changed code", "reuse pass", "simplification pass", "efficiency pass", "altitude pass", or wants the changed code reviewed for reuse, simplification, efficiency, and altitude issues and fixed directly — without hunting for correctness bugs. Also triggered by the /pm-simplify command.

Quality

87%

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

75%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 dense, highly actionable skill body with concrete git commands and a well-sequenced phased workflow backed by explicit validation stops. Its main weakness is conciseness: the embedded rationale is thorough but could be trimmed, and no detail is split out to reference files.

Suggestions

Tighten Phase 0's prose: convert the multi-sentence 'why not baseRefOid / @{upstream} / local base branch' rationale into a short bulleted list of anti-patterns with one-line reasons, keeping the commands but cutting the explanatory narrative.

Extract the cross-repository PR base-resolution and untracked-file edge-case material into a reference file (e.g. references/diff-base.md) referenced from Phase 0, so SKILL.md stays a lean overview.

Add an explicit post-fix verification checkpoint in Phase 2 (e.g. re-run the diff or a syntax/type check after applying fixes) so the workflow has a feedback loop matching its validation-heavy Phase 0.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but ~200 lines of dense prose embed substantial 'why each alternative is wrong' rationale (baseRefOid frozen, @{upstream} resolving to self, octal-escaping of non-ASCII names) that could be tightened without losing the actionable guidance.

3 / 5

Actionability

Fully executable, copy-paste-ready commands throughout — 'gh pr view --json url,baseRefName', 'git symbolic-ref refs/remotes/<base-remote>/HEAD', 'git diff FETCH_HEAD...HEAD', 'git -c core.quotePath=false ls-files --others --exclude-standard', 'readlink -- "$p"' — with a complete fallback ladder covering the common cases.

5 / 5

Workflow Clarity

Clear phased sequence (Phase 0/1/2) with explicit validation stops ('Stop if they differ', 'Any non-zero exit stops', empty-scope reporting, dedup/skip logic), but no explicit re-verification step after Phase 2 applies fixes, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and no nested references, but the file is monolithic with all detail inlined — no bundle files exist, and the lengthy Phase 0 edge-case material could optionally be externalized into a reference.

4 / 5

Total

16

/

20

Passed

Description

95%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, third-person description that pairs an explicit 'Use when...' trigger list with a clear statement of what the skill does and a boundary against the separate bug-hunt review. Trigger-term coverage is comprehensive and the niche is well-differentiated.

DimensionReasoningScore

Specificity

Names the domain ('changed code reviewed') and several concrete actions — 'reuse, simplification, efficiency, and altitude issues and fixed directly — without hunting for correctness bugs' — but is framed around four review angles rather than an exhaustive list of distinct operations, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (review the changed code for reuse/simplification/efficiency/altitude and fix directly, excluding correctness bugs) and 'when' ('This skill should be used when the user asks to...') with concrete trigger phrases, in third-person voice.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger phrases and synonyms users would actually say — 'simplify this', 'simplify the diff', 'clean up this code', 'clean up the changed code', plus 'reuse/simplification/efficiency/altitude pass' variants and the '/pm-simplify' command.

5 / 5

Distinctiveness Conflict Risk

Clear niche (quality-only cleanup, not a bug hunt) with an explicit exclusion — 'without hunting for correctness bugs' — that separates it from a correctness code-review skill and distinct four-angle triggers.

5 / 5

Total

19

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

pmatos/skills

Path

pm-simplify/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.