Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
60
40%
Does it follow best practices?
Impact
100%
1.75xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/conductor/skills/workflow-patterns/SKILL.mdQuality
Discovery
40%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 relies heavily on domain-specific terminology ('Conductor', 'phase checkpoints', 'verification protocol') without explaining what these concepts mean or what concrete actions the skill performs. It has a 'Use when' structure which is good, but the triggers and capabilities are too abstract to effectively differentiate this skill or help Claude understand when to select it.
Suggestions
Add concrete actions the skill performs, e.g., 'Guides implementation through red-green-refactor TDD phases, runs test suites, creates phase-specific git commits, and verifies test passage before advancing.'
Expand trigger terms with natural language variations users might say, such as 'test-driven development', 'red-green-refactor', 'task phases', 'test verification', or 'TDD cycle'.
Briefly explain what 'Conductor' and 'verification protocol' refer to so the description is self-contained and Claude can match it without prior context.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'implementing tasks', 'handling phase checkpoints', 'managing git commits', and 'understanding the verification protocol' without listing concrete actions. It names domain concepts but doesn't describe what the skill actually does (e.g., what phases, what verification steps). | 1 / 3 |
Completeness | The description has a 'Use when...' clause that addresses when to use the skill, but the 'what does this do' part is weak — it doesn't clearly explain what concrete actions the skill performs. The 'when' triggers are present but the 'what' is essentially restated as the 'when'. | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'TDD', 'git commits', 'phase checkpoints', and 'verification protocol', but these are fairly specific to the tool ('Conductor') and may not match natural user language. Missing common variations like 'test-driven development', 'red-green-refactor', or 'task workflow'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Conductor's TDD workflow' provides some distinctiveness, but terms like 'managing git commits' and 'implementing tasks' are generic enough to overlap with general git or task management skills. The proprietary tool name helps but the rest is vague. | 2 / 3 |
Total | 7 / 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.
This skill provides a thorough and well-sequenced TDD workflow with strong validation checkpoints and error recovery paths, but is severely undermined by its verbosity. At 400+ lines it explains many concepts Claude already knows (git commit types, TDD basics, why tests matter), repeats information across sections (commit format appears twice), and dumps everything into a single monolithic file with no progressive disclosure. The content would be significantly more effective at roughly one-third its current length with supporting details split into referenced files.
Suggestions
Reduce content by ~60%: Remove explanations of concepts Claude already knows (what TDD is, what git commit types mean, why checkpoints matter, what regression testing is) and eliminate the duplicate commit message format section.
Split into multiple files: Move 'Quality Assurance Gates', 'Handling Deviations', 'Error Recovery', 'TDD Variations by Task Type', and 'Checkpoint Verification Details' into separate referenced files, keeping SKILL.md as a concise overview with the 11-step lifecycle.
Remove the 'Best Practices' section entirely — its 12 points are either already stated in the workflow steps (redundant) or are general software engineering wisdom Claude already knows.
Consolidate the Git Integration section into Step 8 and Step 9 rather than having a separate section that re-explains the same commit format and git notes usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensively explains concepts Claude already knows (TDD, git commit message formats, what types like 'feat' and 'fix' mean, why checkpoints matter, what regression testing is). Sections like 'Why Checkpoints Matter', 'Performance Considerations', 'Best Practices' list of 12 items, and 'TDD Variations by Task Type' are largely redundant for Claude. The Git Integration section re-explains commit message format already covered in Step 8. | 1 / 3 |
Actionability | Provides concrete bash commands and code examples (pytest commands, git commit examples, Python test examples), but much of it is pseudocode-level or templated rather than truly executable in context. The skill describes a workflow framework with placeholder values (track names, SHAs) rather than providing copy-paste-ready automation. Some sections like 'TDD Variations by Task Type' are abstract summaries rather than actionable instructions. | 2 / 3 |
Workflow Clarity | The 11-step TDD lifecycle is clearly sequenced with explicit validation checkpoints (run tests at RED, GREEN, REFACTOR stages; verify coverage at Step 6; WAIT for user approval at phase completion). Error recovery paths are documented (failed tests after GREEN, checkpoint rejection, blocked dependencies). The phase completion protocol includes explicit feedback loops and a gate requiring user approval before proceeding. | 3 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files or references to external documents. All content is inline in a single massive file. Sections like 'Quality Assurance Gates', 'Verification Checkpoints', 'Manual Verification Guidance', and 'Handling Deviations' could easily be split into separate reference files. No navigation aids or cross-references to help Claude find relevant sections quickly. | 1 / 3 |
Total | 7 / 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 (624 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 | |
112197c
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.