Manage persistent state directories for bash scripts
Install with Tessl CLI
npx tessl i github:majiayu000/claude-skill-registry-data --skill state-directory-manager60
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 identifies a specific technical domain (bash script state management) but lacks the detail needed for effective skill selection. It fails to provide explicit trigger conditions and doesn't enumerate the specific capabilities offered, making it difficult for Claude to confidently choose this skill over alternatives.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when bash scripts need to persist data between runs, store session state, or maintain configuration across executions'
List specific concrete actions such as 'Create, read, update, and clean up state files for bash scripts; track execution history; manage temporary data persistence'
Include natural trigger terms users might say: 'script state', 'save between runs', 'persistent variables', 'script memory', 'session data'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (persistent state directories, bash scripts) and implies an action (manage), but doesn't list specific concrete actions like 'create', 'read', 'update', 'delete', or 'track state between runs'. | 2 / 3 |
Completeness | Only addresses 'what' at a high level (manage state directories) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms ('persistent state', 'bash scripts', 'directories') but misses common variations users might say like 'save state', 'script data', 'temp files', 'session storage', or 'script persistence'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'persistent state' and 'bash scripts' provides some specificity, but 'manage directories' could overlap with general file management skills. The niche is somewhat defined but not sharply distinct. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent executable code examples covering multiple state management patterns. However, it suffers from verbosity by including overlapping implementations (XDG vs workspace-hub, JSON vs key-value state) inline rather than using progressive disclosure. The lack of explicit validation steps for destructive operations and missing verification checkpoints slightly weaken the workflow clarity.
Suggestions
Extract the 'Complete Example: State Manager Module' into a separate reference file (e.g., STATE_MANAGER.md) and link to it, reducing SKILL.md to core patterns only
Add validation checkpoints after state_init() to verify directories exist and have correct permissions before proceeding
Consolidate overlapping patterns - choose either XDG or workspace-hub as primary, move the alternative to a 'See also' reference
Add a verification step after state_reset() to confirm the reset completed successfully before continuing
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but verbose - it includes multiple alternative patterns (XDG vs workspace-hub), extensive code examples that overlap in functionality, and some explanatory text that could be trimmed. The 'When to Use This Skill' section adds value but the overall length (~400 lines) could be reduced. | 2 / 3 |
Actionability | Excellent actionability with fully executable bash code throughout. Every pattern includes complete, copy-paste ready functions with proper error handling, variable declarations, and usage examples. The final 'Complete Example' provides a production-ready module. | 3 / 3 |
Workflow Clarity | While individual functions are clear, the skill lacks explicit validation checkpoints for potentially destructive operations like state_reset() or cache_clear(). The workflow for integrating the state manager is shown but doesn't include verification steps to confirm directories were created correctly or permissions are set properly. | 2 / 3 |
Progressive Disclosure | The skill is mostly monolithic - all patterns are inline rather than split into separate reference files. The structure with numbered sections helps, but the 'Complete Example' duplicates much of the earlier content. External links to XDG spec are provided but internal progressive disclosure is weak. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
Table of Contents
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.