cleanup

Review, refactor, document, and validate code changes in the current branch

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/cleanup/SKILL.md

Quality

Content

63%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 content is action-rich and well-structured, with concrete Pipecat code templates and a clear execution flow including a validation step, but it suffers from duplicated sections/examples and inlines reference material that has no separate bundle files to defer to.

Suggestions

Consolidate the overlapping "Skill Overview" and "What This Skill Does" sections to remove duplicated content, and merge the two near-identical service-class examples into one canonical template.

Move the longer reference material (API/class patterns, example structure scaffolding) into files under references/ and link to them from the overview to improve progressive disclosure.

Add explicit validation checkpoints and a recovery loop to the middle execution-flow steps (e.g. re-check after refactoring that examples still run) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and avoids teaching concepts Claude already knows, but it duplicates material (the Overview list vs. the "What This Skill Does" sections, and two near-identical service-class code examples), which is more than minor padding.	3 / 5
Actionability	Provides multiple concrete, largely copy-paste-ready code templates using real Pipecat APIs (TTSService, can_generate_metrics, create_transport, Pipeline, docstring formats), but a few snippets (e.g. diff retrieval commands, metric helpers) are sketched rather than fully executable.	4 / 5
Workflow Clarity	The Execution Flow gives a clear six-step sequence with an explicit validate-then-fix feedback loop (step 6, /prose-review branch), but the middle analysis steps lack explicit checkpoints and error-recovery loops, keeping it below 5.	4 / 5
Progressive Disclosure	No references/, scripts/, or assets/ bundle files exist, so all reference-like material (API patterns, docstring templates, example scaffolding) is inlined in one file; sections are well-organized but content that could be split into separate files is not.	3 / 5
	Total	14 / 20 Passed

Description

66%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 is specific and action-oriented, naming four concrete operations on branch code changes, but it lacks any explicit "Use when..." trigger guidance, capping completeness at 3. Trigger-term coverage is good but misses natural phrases like "clean up my branch" and the /cleanup command.

Suggestions

Add an explicit trigger clause, e.g. "Use when cleaning up, refactoring, or documenting code changes in the current branch, or when the user asks to review and improve branch code."

Include the natural trigger phrases users would say ("clean up my branch", "refactor my branch code") and the /cleanup slash command in the description.

Optionally surface the sub-actions (readability, performance, docstrings, pattern consistency) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names four concrete actions ("Review, refactor, document, and validate") applied to a clear object ("code changes in the current branch"), matching the several-specific-actions anchor; it falls short of 5 because it does not enumerate the sub-actions the body later details.	4 / 5
Completeness	Clearly answers "what" the skill does but provides no "Use when..." clause or equivalent trigger guidance, which the rubric explicitly caps at 3; it is above 2 because the "what" is specific rather than vague.	3 / 5
Trigger Term Quality	Reasonable natural keywords (review, refactor, document, validate, code changes) but omits common variations a user would say, such as "clean up my branch" and the /cleanup slash command, so it is good but not comprehensive.	4 / 5
Distinctiveness Conflict Risk	The branch-scoped, multi-action framing makes it mostly distinct from generic skills, though "review code changes" still risks minor overlap with general code-review and git skills, keeping it below 5.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pipecat-ai/pipecat
Path: .claude/skills/cleanup/SKILL.md
Commit: baf1f16

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.