This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
78
70%
Does it follow best practices?
Impact
94%
1.84xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/plugin-dev/skills/plugin-settings/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger term coverage and clear completeness, explicitly stating both what the skill does and when to use it. The main weakness is that the 'what' portion focuses on documenting a pattern rather than listing specific concrete actions the skill enables. The description effectively carves out a distinct niche that would be easy for Claude to match against user requests.
Suggestions
Add more specific concrete actions beyond 'documents the pattern', such as 'create plugin configuration files', 'read and parse YAML frontmatter from .local.md files', 'set default plugin values'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (plugin configuration) and mentions the specific pattern (.claude/plugin-name.local.md with YAML frontmatter and markdown content), but the concrete actions are limited to 'documents the pattern' and 'storing plugin-specific configuration' rather than listing multiple distinct actions like 'read settings', 'write defaults', 'validate configuration'. | 2 / 3 |
Completeness | The description clearly answers both 'what' (documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content) and 'when' (explicit 'Use when' clause at the beginning listing multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'plugin settings', 'store plugin configuration', 'user-configurable plugin', '.local.md files', 'plugin state files', 'read YAML frontmatter', 'per-project plugin settings', and 'make plugin behavior configurable'. These are terms users would naturally use when asking about this topic. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — plugin configuration via .local.md files with YAML frontmatter in the .claude directory. The trigger terms are highly specific to this pattern and unlikely to conflict with general configuration or YAML skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%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 executable bash examples and concrete file templates, but is severely bloated with repetitive content — the same frontmatter parsing pattern appears 5+ times across different sections. The content would benefit enormously from being split into a concise overview SKILL.md with references to supporting files for parsing techniques, patterns, and examples. Referenced bundle files (examples/, references/, scripts/) don't exist.
Suggestions
Reduce the main SKILL.md to ~80 lines: one parsing example, one settings template, the implementation workflow, and links to reference files for patterns/examples/security.
Eliminate repeated sed/grep parsing snippets — show the pattern once in a 'Parsing' section and reference it elsewhere.
Add explicit validation checkpoints to the implementation workflow (e.g., 'Test parsing with validate-settings.sh before wiring into hooks').
Create the referenced bundle files (references/parsing-techniques.md, examples/read-settings-hook.sh, etc.) so progressive disclosure actually works.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Massive repetition of the same sed/grep parsing patterns shown 5+ times. Explains obvious concepts (what markdown body can contain, what YAML frontmatter is). Many sections restate the same quick-exit pattern. The 'Common Patterns' section largely duplicates the 'Reading Settings Files' section. Claude doesn't need this level of hand-holding. | 1 / 3 |
Actionability | Provides fully executable bash code for parsing frontmatter, extracting fields, reading body content, and validating settings. Code examples are copy-paste ready with real sed/awk commands and complete if/case logic. Multiple concrete file templates are provided. | 3 / 3 |
Workflow Clarity | The 'Implementation Workflow' section at the end provides a clear 7-step sequence, but lacks explicit validation checkpoints. There's no 'validate your settings file works' step between creating it and using it. The validate-settings.sh script is referenced but not shown, and there's no feedback loop for when parsing fails silently (e.g., malformed YAML). | 2 / 3 |
Progressive Disclosure | References to examples/, references/, and scripts/ directories are well-signaled, but no bundle files are provided, so these are dead references. The SKILL.md itself is monolithic — the parsing techniques, real-world examples, security considerations, and common patterns sections could all be in separate reference files, with the main file serving as a concise overview. | 2 / 3 |
Total | 8 / 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 (545 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 | |
fcdcd07
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.