Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill conductor-validator68
Quality
52%
Does it follow best practices?
Impact
96%
1.39xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/conductor-validator/SKILL.mdQuality
Discovery
67%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 adequately covers when to use the skill with explicit trigger scenarios, which is a strength. However, it lacks specific concrete actions (what exactly gets validated) and could benefit from more natural user-facing trigger terms. The Conductor-specific focus helps with distinctiveness but the validation actions remain abstract.
Suggestions
Add specific concrete actions like 'checks configuration files, verifies dependency versions, validates project structure'
Include more natural trigger terms users might say such as 'check my project', 'something's broken', 'troubleshoot', or 'debug setup'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Conductor project artifacts) and general action (validates for completeness, consistency, correctness), but doesn't list specific concrete actions like 'checks config files', 'verifies dependencies', or 'validates schema'. | 2 / 3 |
Completeness | Clearly answers both what (validates Conductor project artifacts for completeness, consistency, correctness) and when (after setup, when diagnosing issues, before implementation) with explicit trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'validates', 'diagnosing issues', 'setup', and 'verify', but missing natural user phrases like 'check my project', 'something's wrong', 'debug', or 'troubleshoot'. | 2 / 3 |
Distinctiveness Conflict Risk | Specific to 'Conductor project artifacts' which provides some distinction, but 'validates' and 'diagnosing issues' could overlap with general debugging or linting skills without more specific triggers. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides some useful reference patterns (status markers, track IDs) and basic directory checking commands, but fails to deliver on its stated purpose of validating project artifacts. The Instructions section is generic boilerplate that doesn't explain how to actually perform validation, what errors to look for, or how to diagnose issues. The shell commands lack context and the skill has no workflow for interpreting results.
Suggestions
Add a clear validation workflow: define what constitutes a valid project, list specific checks to perform in sequence, and explain how to interpret pass/fail conditions
Replace the generic Instructions section with concrete validation steps (e.g., 'Check index.md contains required sections: Overview, Tracks, Status')
Add expected output examples showing what valid vs invalid states look like, and what actions to take for common failures
Remove or condense the boilerplate 'Use this skill when' sections that don't add actionable information
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is relatively brief but includes some redundant sections (the 'Use this skill when' and 'Do not use this skill when' sections are generic boilerplate that don't add value). The shell commands are efficient but the instructions section is vague filler. | 2 / 3 |
Actionability | Provides concrete shell commands for checking directory structure and shows specific pattern examples for status markers and track IDs. However, the Instructions section is entirely vague ('Clarify goals, constraints...') with no executable guidance on what to actually validate or how to interpret results. | 2 / 3 |
Workflow Clarity | No clear sequence or workflow is defined. The shell commands at the top are listed without context of when to run them or what to do with results. There's no validation logic, no error handling, and no guidance on what constitutes a valid vs invalid project state. | 1 / 3 |
Progressive Disclosure | References an external file (resources/implementation-playbook.md) appropriately, but the main content organization is poor. Pattern matching examples are useful but disconnected from any validation workflow. The skill lacks a clear overview structure. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 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.