conductor-implement

Execute tasks from a track's implementation plan following TDD workflow

Quality

31%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/conductor-implement/SKILL.md

Quality

Content

47%

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

This skill provides a comprehensive and well-structured workflow for track implementation with strong sequencing and validation checkpoints. However, it is significantly over-verbose, spelling out UI templates, option menus, and JSON structures in full rather than trusting Claude to generate these contextually. The content would benefit greatly from being split across multiple files with the SKILL.md serving as a concise overview.

Suggestions

Reduce the SKILL.md to ~100 lines by moving UI templates, error handling menus, JSON examples, and completion summaries into a referenced playbook file (e.g., resources/implementation-playbook.md which is already mentioned but apparently not used)

Remove boilerplate sections like 'Use this skill when', 'Do not use this skill when', and 'Limitations' which add ~20 lines of generic content Claude doesn't need

Replace descriptive instructions like 'Parse plan.md to find next incomplete task' with concrete regex or parsing examples that are directly executable

Provide the referenced bundle files (conductor/workflow.md, resources/implementation-playbook.md) or remove references to them to avoid broken navigation

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Contains extensive boilerplate sections ('Use this skill when', 'Do not use this skill when', 'Limitations') that add little value. Many UI mockups and menu displays are spelled out in full when Claude could generate these contextually. The metadata.json example, completion summary template, and multiple option menus are overly prescriptive for things Claude can infer.	1 / 3
Actionability	Provides concrete file paths, JSON structures, and git commands, which is good. However, much of the guidance is procedural description rather than executable code—e.g., 'Parse plan.md to find next incomplete task' and 'Look for lines matching...' are instructions about what to do without providing actual parsing logic. The git commands are copy-paste ready but many steps remain at the description level.	2 / 3
Workflow Clarity	The multi-step workflow is clearly sequenced with explicit phases (Red/Green/Refactor for TDD), validation checkpoints between phases requiring user approval, error handling with explicit HALT behavior, and feedback loops for test failures. The 'CRITICAL: Wait for explicit user approval' and 'STOP on any failure' rules demonstrate strong validation checkpoint discipline.	3 / 3
Progressive Disclosure	References `conductor/workflow.md` and `resources/implementation-playbook.md` for detailed content, which is good. However, the SKILL.md itself is monolithic—it contains extensive inline content (error handling templates, completion summaries, progress tracking JSON, resumption logic) that could be split into separate reference files. No bundle files are provided to support the references made.	2 / 3
	Total	8 / 12 Passed

Description

14%

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 description is too vague and abstract to effectively guide skill selection. It lacks concrete actions, natural trigger terms users would say, and any explicit 'when to use' guidance. The terms 'track' and 'execute tasks' are ambiguous and would likely cause conflicts with other skills.

Suggestions

Add a 'Use when...' clause with explicit trigger conditions, e.g., 'Use when the user asks to implement the next task from a track's plan, or mentions TDD, test-driven development, or red-green-refactor workflow.'

List specific concrete actions such as 'Writes failing tests, implements code to pass tests, refactors, and marks tasks complete in the implementation plan.'

Clarify what 'track' means in this context (e.g., 'project track', 'feature track') and add natural keyword variations like 'test-driven development', 'write tests first', 'implement next step'.

Dimension	Reasoning	Score
Specificity	The description mentions 'TDD workflow' and 'implementation plan' but does not list any concrete actions (e.g., write tests, run tests, implement code, refactor). 'Execute tasks' is vague and abstract.	1 / 3
Completeness	The 'what' is vaguely stated ('execute tasks...following TDD workflow') and there is no 'when' clause or explicit trigger guidance at all. The missing 'Use when...' clause caps this at 2 per the rubric, but the 'what' is also weak, so it scores 1.	1 / 3
Trigger Term Quality	'TDD' and 'implementation plan' are relevant keywords, but the description lacks common natural variations users might say such as 'test-driven development', 'red-green-refactor', 'write tests first', or 'track tasks'. The term 'track' is ambiguous and could refer to many things.	2 / 3
Distinctiveness Conflict Risk	'Execute tasks' and 'implementation plan' are extremely generic phrases that could overlap with many coding, project management, or task execution skills. The term 'track' is ambiguous and adds to confusion rather than distinctiveness.	1 / 3
	Total	5 / 12 Passed

Validation

90%

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 — 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

Repository: sickn33/antigravity-awesome-skills
Commit: 88d1e11

Reviewed: 5 days 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.