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.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/track-management/SKILL.md

The canonical home for this skill is track-management in rmyndharis/antigravity-skills

Quality

Content

36%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 skill body is well-organized and appropriately scoped, but it offers almost no concrete, domain-specific guidance: the instructions are generic boilerplate, no track lifecycle workflow is sequenced, and the one detailed reference points to a file that does not exist.

Suggestions

Replace the generic Instructions bullets with a concrete track lifecycle workflow (e.g., 1. create track in tracks.md, 2. author spec.md, 3. draft plan.md, 4. advance status with a validation checkpoint) so the steps are sequenced and actionable.

Add concrete, track-specific guidance — the spec.md/plan.md structure, the status marker conventions, and how to update the tracks.md registry — instead of 'apply relevant best practices'.

Either create the referenced 'resources/implementation-playbook.md' with the promised patterns and examples, or remove the broken reference so navigation is not dead-ended.

Dimension	Reasoning	Score
Conciseness	The body is short and sectioned, but the 'Instructions' bullets ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') and the 'Do not use when' pair are generic boilerplate Claude already knows rather than domain-specific guidance, so the token budget is only partially earned.	3 / 5
Actionability	It names the relevant artifacts (spec.md, plan.md, tracks.md registry, status markers, metadata) but provides no concrete, executable steps for any track task — the Instructions are abstract platitudes, and the single concrete reference ('resources/implementation-playbook.md') does not exist on disk.	2 / 5
Workflow Clarity	Track lifecycle is inherently a multi-step process (create → spec → plan → implement → complete), but the body never sequences it; only a faint implied order comes from the 'Use when' list, and the lone 'validate outcomes' mention is generic with no real checkpoint or feedback loop.	2 / 5
Progressive Disclosure	Section structure is clean and the body correctly points outward to a single one-level-deep reference, but that referenced file ('resources/implementation-playbook.md') is missing — no resources/ directory exists — so the promised detailed patterns are unreachable, undermining the navigation.	3 / 5
	Total	10 / 20 Passed

Description

65%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 scopes a distinctive niche and supplies a solid set of natural trigger terms, but it leans on generic verbs and second-person phrasing rather than concrete third-person capabilities and user-mentionable triggers.

Suggestions

Lead with a third-person capability clause (e.g., 'Creates, manages, and completes Conductor tracks...') before the 'Use when' trigger, instead of opening with second-person 'Use this skill when'.

Swap generic verbs ('working with') for concrete track actions (e.g., 'author spec.md, draft plan.md, advance track status') to raise specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Conductor tracks') and artifacts ('spec.md', 'plan.md', 'track lifecycle operations') but the verbs are generic ('creating, managing, or working with') rather than concrete like extract/fill/merge; base specificity is 3, reduced to 2 because the description uses second-person imperative voice ('Use this skill when...') instead of a third-person capability clause.	2 / 5
Completeness	Both 'what' (manage Conductor tracks across spec/plan/lifecycle) and 'when' ('Use this skill when creating, managing, or working with Conductor tracks') are present and explicit, but the 'when' clause reuses the same action verbs as the 'what' rather than referencing user-mentionable trigger phrases, leaving it one notch below a 5.	4 / 5
Trigger Term Quality	It includes natural domain terms a Conductor user would say — 'Conductor tracks', 'spec.md', 'plan.md', 'features, bugs, and refactors', 'track lifecycle' — with good coverage including file extensions, though it lacks synonym variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	'Conductor tracks' is a distinctive niche with low conflict risk against unrelated skills, though scoping to spec.md/plan.md could cause minor overlap with sibling spec- or plan-writing skills in the same plugin.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/track-management/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.