state-directory-manager

Manage persistent state directories for bash scripts

2.96x

Quality

—

Does it follow best practices?

Impact

89%

2.96x

Average score across 6 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with thorough executable bash patterns, but it is bloated by a redundant complete-example module and lacks validation safeguards around destructive operations. Splitting the reusable module into a reference file and tightening duplication would improve it.

Suggestions

Remove or externalize the "Complete Example: State Manager Module" since it duplicates sections 1–6, keeping the body lean.

Add validation/confirmation steps before destructive operations (e.g. guard `state_reset`'s `rm -rf` and back up files before `sed -i` edits).

Move the reusable module into a `references/` or `scripts/` bundle file and reference it one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable code, but the "Complete Example: State Manager Module" largely duplicates the six preceding sections (~680 lines total), adding substantial redundant tokens.	2 / 3
Actionability	Every section provides concrete, executable, copy-paste-ready bash functions with real fallbacks and cross-platform stat handling, fully matching the executable-code anchor.	3 / 3
Workflow Clarity	Sections are well sequenced, but destructive operations such as `rm -rf "$STATE_BASE_DIR"` in state_reset and in-place `sed -i` config edits lack validation or backup checkpoints, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and everything is inline in one monolithic file; the reusable complete module is content that could be split into a separate reference rather than embedded inline.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 clear and distinct but generic: it names the domain with a single broad verb and omits any explicit "Use when" trigger guidance. Adding concrete actions and a trigger clause would raise specificity and completeness.

Suggestions

Add explicit trigger guidance, e.g. "Use when scripts need to persist config, cache, logs, or state between runs."

Replace the single verb "Manage" with multiple concrete actions (e.g. "Create, read, and rotate state, config, cache, and log directories").

Include natural user-facing terms such as "config files", "cache", "XDG", and "log rotation" to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Manage persistent state directories for bash scripts" names the domain and a general action, but offers only the single verb "Manage" rather than multiple concrete actions like create, read, rotate, or clean.	2 / 3
Completeness	It states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 2.	2 / 3
Trigger Term Quality	"persistent state directories" and "bash scripts" are relevant terms, but common variations a user would actually say (config files, cache, XDG, log rotation) are missing.	2 / 3
Distinctiveness Conflict Risk	"persistent state directories for bash scripts" carves a clear niche that is unlikely to trigger for unrelated skills, matching the distinct-anchor example.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (690 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: cb3ef45

Reviewed: about 18 hours 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.