track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
66
51%
Does it follow best practices?
Impact
96%
2.40xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/track-management/SKILL.mdQuality
Discovery
75%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 has good completeness with an explicit 'Use when' clause and is distinctive enough to avoid conflicts with other skills. However, it lacks specific concrete actions (what exactly does managing tracks entail?) and could benefit from more natural trigger terms that users would actually say. The use of second person ('Use this skill') is noted but the rubric penalizes first/second person voice for specificity.
Suggestions
List specific concrete actions such as 'Creates spec.md files, generates implementation plans, updates track status, and manages track lifecycle from creation to completion'.
Add more natural trigger terms users might say, such as 'start a new feature', 'plan implementation', 'write a spec', 'track a bug fix', or 'organize work'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Conductor tracks') and mentions some artifacts (spec.md, plan.md, track lifecycle operations), but doesn't list specific concrete actions like 'create spec files', 'generate plans', 'update track status', etc. | 2 / 3 |
Completeness | Explicitly answers both 'what' (creating, managing, working with Conductor tracks including spec.md, plan.md, and lifecycle operations) and 'when' ('Use this skill when creating, managing, or working with Conductor tracks'). Has an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'tracks', 'spec.md', 'plan.md', 'features', 'bugs', 'refactors', but these are somewhat tool-specific jargon. Missing natural user phrases like 'start a new feature', 'plan work', 'track progress', or 'create a spec'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to 'Conductor tracks' with specific file references (spec.md, plan.md) and lifecycle operations, making it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but excessively verbose reference document that reads more like project management documentation than a concise skill for Claude. Its main strengths are the concrete markdown/JSON templates and clear status marker conventions. However, it suffers from significant bloat—explaining obvious concepts, inlining content that should be in separate files, and providing generic best practices that don't add value for an LLM.
Suggestions
Cut content by 60-70%: Remove explanations of what features/bugs/refactors are, sizing guidelines, dependency type definitions, and generic best practices—Claude already knows these concepts.
Extract templates into separate referenced files (e.g., spec-template.md, plan-template.md, metadata-schema.json) and keep SKILL.md as a concise overview with links.
Make the track operations section more concrete: specify exactly what `/conductor:new-track` does, what files it creates, and what the expected directory structure looks like after each operation.
Add explicit validation steps with concrete checks (e.g., 'Verify plan.md has a Verification section for each phase' or 'Validate metadata.json against schema') rather than abstract 'wait for checkpoint approval' instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensively explains concepts Claude already understands (what a track is, what features/bugs/refactors are, sizing guidelines, dependency types). Much of this is generic project management knowledge that doesn't need to be spelled out. The track type descriptions, sizing guidelines, best practices list, and quality checklists are largely common sense for an LLM. | 1 / 3 |
Actionability | Provides concrete templates for spec.md, plan.md, metadata.json, and tracks.md which are useful and copy-paste ready. However, the actual operations (creating, completing, reverting tracks) reference commands like `/conductor:new-track` and `/conductor:revert` without explaining what these do mechanically, and there's no executable code—just markdown templates and procedural checklists. | 2 / 3 |
Workflow Clarity | The lifecycle is clearly sequenced (Creation → Implementation → Completion) with numbered steps, and verification tasks are mentioned within phases. However, validation checkpoints are described conceptually ('Wait for checkpoint approval') without specifying what validation actually looks like or how to recover from failures. The revert workflow is particularly thin—just 5 vague steps. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content clearly warranting it. The spec.md template, plan.md template, metadata.json schema, tracks.md format, quality checklists, and common patterns could all be separate referenced files. Everything is inlined into one massive document, making it hard to navigate and consuming excessive context window. | 1 / 3 |
Total | 6 / 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 (594 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 | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
99da384
- 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.