maintenance

File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: /maintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.

Quality

86%

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

Quality

Content

85%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 compact, well-organized maintenance skill: clear subcommand map, real one-level-deep reference, and proper validation gates for destructive batch operations. The body is navigational rather than code-heavy, which slightly limits its standalone actionability.

Dimension	Reasoning	Score
Conciseness	Lean, well-structured body that assumes Claude's competence and avoids concept over-explanation; a few prose passages (the 前提 block and 注意事項) could be trimmed marginally to reach full efficiency.	4 / 5
Actionability	Provides a concrete subcommand table, --dry-run flag, and a literal backup command, with the bulk of executable bash offloaded to cleanup.md; mostly executable guidance with minor gaps in the body itself.	4 / 5
Workflow Clarity	A destructive/batch skill that does include validation gates (SSOT-sync check, backups before edits, dry-run, WIP-tag protection, before/after reporting, error-stop in `all`), so it is not capped at 3 and matches the explicit-checkpoint anchor.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with subcommand detail pushed one level deep into a real references/cleanup.md, clearly signaled by a markdown link — easy navigation with no nested references.	5 / 5
	Total	18 / 20 Passed

Description

87%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 targets, natural trigger terms, explicit when-guidance, and a negative boundary that sharply limits conflict. Slightly below perfect only on action specificity and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete targets ("Plans.md, session-log.md, old logs, and state files") with specific actions (cleanup, archiving, tidying), but the action vocabulary is somewhat limited rather than comprehensive.	4 / 5
Completeness	Explicitly answers both what (file cleanup and archiving of named files) and when (concrete trigger phrases), and adds an explicit negative boundary ("Do NOT load for..."), matching the top anchor.	5 / 5
Trigger Term Quality	"Trigger: /maintenance, cleanup, archive, organize, split session-log" supplies natural terms users would say plus a slash command, but a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (workspace-file cleanup/archiving) with distinct triggers and an explicit exclusion list, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: Chachamaru127/claude-code-harness
Path: opencode/skills/maintenance/SKILL.md
Commit: 2b2b748

Reviewed: 4 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.