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.

2.40x

Quality

73%

Does it follow best practices?

Impact

96%

2.40x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/track-management/SKILL.md

The canonical home for this skill is track-management in wshobson/agents

Quality

Content

63%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 is highly actionable with concrete templates and explicit workflow checkpoints, but it is verbose and monolithic—re-explaining familiar concepts and inlining large template sections that should live in separate reference files.

Suggestions

Move the spec.md, plan.md, metadata.json, and registry templates into separate reference files under references/ and link to them one level deep, keeping SKILL.md as a lean overview.

Trim generic definitions of feature/bug/chore/refactor and of scope/risk/dependencies that Claude already knows, keeping only Conductor-specific conventions.

Add explicit validate-fix-retry feedback loops for destructive/batch track operations (e.g. revert, phase checkpoints) to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	The ~594-line body re-explains concepts Claude already knows (generic feature/bug/refactor definitions, generic risk/scope/dependency semantics) and pads with template placeholders, so it is mostly useful but noticeably verbose.	3 / 5
Actionability	Provides concrete, copy-ready templates for spec.md, plan.md, metadata.json, status markers, and registry tables plus explicit commands (e.g. '/conductor:new-track', '/conductor:revert'); minor gaps are placeholder fields rather than fully worked examples.	4 / 5
Workflow Clarity	Multi-step track lifecycle is clearly sequenced (Creation, Implementation, Completion) with explicit checkpoints ('Wait for checkpoint approval', 'Record checkpoint SHA') and validation lists; a few validation feedback loops (validate-fix-retry) are only implicit.	4 / 5
Progressive Disclosure	The skill is a monolithic SKILL.md with no references/scripts/assets bundle files and no one-level-deep references; large template sections that belong in separate files are inlined, so structure is present but content is not split across files.	3 / 5
	Total	14 / 20 Passed

Description

83%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 concrete trigger phrases and a distinct Conductor-tracks niche. It is specific and complete, with only minor gaps in trigger-term synonyms and overlap risk.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('creating, managing, or working with Conductor tracks') and the targeted artifacts (spec.md, plan.md, track lifecycle), with only minor coverage gaps relative to a fully enumerated action list.	4 / 5
Completeness	Explicitly answers both what ('creating, managing, or working with Conductor tracks') and when ('Use this skill when... Applies to spec.md, plan.md, and track lifecycle operations') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Uses natural user-facing terms ('tracks', 'features, bugs, and refactors', 'spec.md', 'plan.md') with good coverage; a few common synonyms or casual phrasings a user might say are missing.	4 / 5
Distinctiveness Conflict Risk	The Conductor-tracks niche is fairly distinct with clear triggers; minor overlap risk remains with adjacent general project-management or planning skills.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 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
relative_links	Relative link issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/conductor/skills/track-management/SKILL.md
Commit: 6453c0b

Reviewed: about 10 hours 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.