conductor-validator

Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.

Quality

58%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/conductor-validator/SKILL.md

Quality

Content

53%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.

The body contains one genuinely useful, concrete section (Pattern Matching with status/task markers and track ID format) surrounded by generic boilerplate and a broken code fence. It is executable at a basic level but lacks the actual validation logic its description promises.

Suggestions

Fix the broken opening code fence before the 'ls -la conductor/' commands so the block renders as intended.

Replace the generic 'Instructions' bullets with the actual validation rules, e.g. criteria for what makes index.md/tech-stack.md complete and how to flag failures.

Remove or rewrite the templated 'Use this skill when / Do not use this skill when' sections, which substitute the literal phrase 'check if conductor directory exists' into nonsensical sentences.

Add a validation checkpoint after the file-existence checks describing what to report when required files are missing or status markers are malformed.

Dimension	Reasoning	Score
Conciseness	The body is short overall, but it carries generic filler ('Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification.') and templated 'Use this skill when / Do not use this skill when' boilerplate that adds no skill-specific value. It is not a 2 because it is not severely verbose, and not a 4 because the filler sections are genuinely unnecessary.	3 / 5
Actionability	Provides concrete executable commands ('ls -la conductor/', 'ls conductor/index.md conductor/product.md ...') and concrete pattern examples, but the opening code fence is never opened (broken markdown) and there is no actual validation logic beyond listing files. It is not a 4 because the commands tell Claude what to inspect without telling it how to judge correctness.	3 / 5
Workflow Clarity	A rough sequence is present (check directory exists, find track dirs, check required files), but there are no validation checkpoints or feedback loops for what to do when files are missing or malformed. Per the batch/verification cap, a verification skill without validation steps cannot exceed 3; it is above a 2 because the steps are ordered and named.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and is organized into labeled sections (Use this skill when, Do not use, Instructions, Pattern Matching). It is not a 5 because the top code block has a broken opening fence and the templated sections are awkwardly organized.	4 / 5
	Total	13 / 20 Passed

Description

62%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.

The description clearly states what the skill does and when to use it with explicit trigger guidance, anchored to a specific Conductor niche. It is solid but not exemplary, as the 'what' lists one abstract action rather than multiple concrete capabilities.

Suggestions

Replace the abstract 'validates for completeness, consistency, and correctness' with concrete validation actions, e.g. 'checks for required files, verifies track ID patterns, and flags missing status markers'.

Add natural synonym triggers users might say, such as 'audit Conductor setup', 'review track status', or 'check project context'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Conductor project artifacts') and one concrete action ('Validates ... for completeness, consistency, and correctness'), but does not list multiple distinct actions. It is above a 2 because the action carries three concrete quality dimensions, but below a 4 because there is only one action rather than several.	3 / 5
Completeness	Explicitly answers both 'what' (validates Conductor artifacts for completeness/consistency/correctness) and 'when' ('Use after setup, when diagnosing issues, or before implementation'), with explicit trigger guidance present so it is not capped at 3. It is not a 5 because the 'what' remains somewhat abstract rather than enumerating concrete capabilities.	4 / 5
Trigger Term Quality	Includes fairly natural triggers ('when diagnosing issues', 'before implementation', 'verify project context'), but misses common synonyms and variations a user might say. It is not a 4 because coverage is limited to these few phrases without broader keyword variation.	3 / 5
Distinctiveness Conflict Risk	Tied to the specific 'Conductor' niche with distinct triggers, giving it a clear domain with only minor overlap risk against other validation skills. It is not a 5 because 'validates artifacts for completeness/consistency/correctness' could still overlap with generic validation skills.	4 / 5
	Total	14 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/conductor-validator/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.