simplify-code

Parallel 4-agent cleanup of recent code changes.

Quality

63%

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 ./skills/software-development/simplify-code/SKILL.md

Quality

Content

77%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 highly actionable and workflow clarity is excellent, with concrete commands, structured output templates, and explicit validation feedback loops at every apply step. The main weakness is conciseness — the four reviewer prompt blocks are verbose — and minor progressive-disclosure room to externalize those prompts.

Suggestions

Tighten the four reviewer 'look for' lists into shorter bullet summaries; the exhaustive enumerations read as padding and dilute token efficiency.

Consider moving the four full reviewer-prompt blocks into a references file (e.g. REVIEWER_PROMPTS.md) and keeping one-line summaries inline, improving both conciseness and progressive disclosure.

The 'Pitfalls' section repeats some risk-tier guidance already covered in Phase 3; consolidate to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but several reviewer-prompt blocks (e.g. the long enumerated look-for lists) are detailed to the point of padding and could be tightened without losing clarity.	3 / 5
Actionability	It provides concrete, executable guidance throughout: real git diff commands, a batch-mode delegation pattern, structured output templates with confidence/risk fields, and explicit risk-tier application rules with test verification.	5 / 5
Workflow Clarity	The three-phase process is clearly sequenced with explicit validation checkpoints (run tests after SAFE, after each CAREFUL file, revert-on-break), feedback loops (fix and re-validate), and a dry-run gate; it also honors the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Structure is good with clearly labeled sections (When to Use, The Process, Pitfalls, Related) and no nested references, but the reviewer-goal blocks are large inlined content that could arguably live in a separate reference file; with no bundle files present it stays one level deep.	4 / 5
	Total	17 / 20 Passed

Description

50%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 concise and avoids fluff, with a clear 'what' and reasonable distinctiveness. Its main weakness is the absence of any explicit 'Use when...' trigger guidance and only partial keyword coverage, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user asks to simplify, clean up, or review recent code changes.'

Include natural user phrasings and synonyms in the description ('review my code', 'clean up my changes', '/simplify') to improve trigger-term coverage.

Briefly enumerate the concrete actions (remove duplication, flatten complexity, cut waste) to lift specificity above a single generic action.

Dimension	Reasoning	Score
Specificity	Names the domain (code cleanup) and one concrete action ('cleanup of recent code changes') but does not enumerate the specific actions (dedup, flatten, cut waste) inside the description field, so coverage is partial.	3 / 5
Completeness	It states a clear 'what' (parallel 4-agent cleanup of recent changes) but the description has no 'Use when...' clause or explicit 'when' guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'simplify', 'cleanup', and 'code changes' are relevant natural terms, but the description omits common variations like 'review my code', 'clean up', or file/extension triggers that users actually say.	3 / 5
Distinctiveness Conflict Risk	The phrase 'Parallel 4-agent cleanup' carves a fairly specific niche distinct from general review skills, with only minor overlap risk against generic code-review skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/simplify-code/SKILL.md
Commit: 6327930

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.