conductor-implement
Execute tasks from a track's implementation plan following TDD workflow
35
31%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/conductor-implement/SKILL.mdQuality
Discovery
22%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 is too vague and lacks concrete actions, explicit trigger terms, and a 'Use when...' clause. While it references TDD and implementation plans, it fails to explain what specific actions the skill performs or when Claude should select it. It would be difficult for Claude to reliably choose this skill from a large pool of available skills.
Suggestions
Add a 'Use when...' clause specifying explicit triggers, e.g., 'Use when the user asks to implement the next task from a track plan, write tests, or follow a TDD workflow.'
Replace 'Execute tasks' with specific concrete actions such as 'Writes failing tests, implements code to pass tests, and refactors following red-green-refactor TDD methodology.'
Include natural trigger terms users would say, such as 'test-driven development', 'write tests first', 'red-green-refactor', 'next task', or 'implement feature from plan'.
| 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') and there is no 'when' clause or explicit trigger guidance at all. The absence of a 'Use when...' clause caps this at 2, but the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Includes 'TDD' and 'implementation plan' which are somewhat relevant keywords, but 'track' is ambiguous and it misses natural user terms like 'test-driven development', 'red-green-refactor', 'write tests first', or 'run tests'. | 2 / 3 |
Distinctiveness Conflict Risk | 'TDD workflow' and 'track's implementation plan' provide some specificity that narrows the domain, but 'execute tasks' is generic enough to overlap with any task execution or planning skill. The term 'track' is unclear and could conflict with other planning-related skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a comprehensive and well-sequenced workflow with strong validation checkpoints and error handling, but suffers severely from verbosity. Much of the content consists of templated output messages and JSON examples that Claude can generate on its own. The monolithic structure with no supporting bundle files means everything is inlined, wasting context window tokens on content that should be progressively disclosed.
Suggestions
Reduce the skill to a concise overview (~50-80 lines) covering the core workflow steps, and move detailed sections (error handling, track completion, resumption, progress tracking JSON schema) into separate referenced files.
Remove all templated output message blocks (the ```-fenced menu displays and status messages) — Claude can generate appropriate user-facing messages without being shown exact templates.
Eliminate the 'Use this skill when / Do not use this skill when' and 'Limitations' boilerplate sections, which add no actionable information for Claude.
Provide the referenced bundle files (conductor/workflow.md, resources/implementation-playbook.md) or remove references to them, as currently key implementation details are deferred to non-existent files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Much of the content describes UI menus, status messages, and JSON structures that Claude can generate dynamically. The boilerplate 'Use this skill when / Do not use this skill when' and 'Limitations' sections add little value. Significant portions explain obvious workflows (git add/commit, updating JSON fields) that Claude already knows. | 1 / 3 |
Actionability | Provides concrete steps and some executable commands (git commands, file paths), but much of the content is templated output messages rather than executable guidance. The actual implementation logic (how to write tests, what to validate) remains abstract. References to external files like `conductor/workflow.md` and `resources/implementation-playbook.md` without bundle files means key details are missing. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases (pre-flight, track selection, context loading, task execution loop, completion). Validation checkpoints are explicit — phase verification requires user approval before proceeding, error handling has clear HALT behavior, and the TDD red/green/refactor cycle includes verification at each step. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inlined. The skill references external files (workflow.md, implementation-playbook.md, code styleguides) but no bundle files are provided. The entire task execution loop, error handling, track completion, resumption logic, and progress tracking are all crammed into one file when they could be split into referenced sub-documents. | 1 / 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 | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
f5dc9e3
- Reviewed
Table of Contents
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.