CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

43

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

17%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 a template shell: the 'Use this skill when' list is genuinely useful, but the Instructions and exclusion sections are universal boilerplate with zero domain content, the track lifecycle is never sequenced into steps, and the skill's only depth (the implementation playbook) points to a file that does not exist in the bundle. A reader learns nothing about how to actually create, update, or complete a Conductor track.

Suggestions

Replace the boilerplate Instructions with the concrete track lifecycle: how to create a track, what spec.md and plan.md must contain (with short examples), and the status marker conventions used in the tracks.md registry.

Fix or remove the dangling 'resources/implementation-playbook.md' reference — either ship the playbook as a bundle file or drop the pointer, since it currently breaks navigation twice.

Add explicit validation checkpoints for registry/lifecycle operations (e.g., re-verify the track's entry in tracks.md after any status change) and cut the tautological 'Do not use' bullets.

DimensionReasoningScore

Conciseness

Noticeably padded: the intro paragraph repeats the frontmatter description nearly verbatim, the 'Do not use this skill when' section is tautological ('The task is unrelated to track management', 'You need a different domain or tool outside this scope'), and the Instructions are universal boilerplate ('Apply relevant best practices and validate outcomes') that assumes no intelligence. This matches anchor 2 ('several unnecessary explanations or padded sections') rather than 3, where padding would be incidental to real guidance.

2 / 5

Actionability

Entirely abstract: no file formats, status marker conventions, lifecycle steps, commands, or examples anywhere — 'Clarify goals, constraints, and required inputs' and 'Provide actionable steps and verification' describe rather than instruct, matching anchor 1. The only concrete element, the pointer to 'resources/implementation-playbook.md', is a dangling reference (no such file or directory exists in the bundle).

1 / 5

Workflow Clarity

A rough phase order is implied by 'specification, planning, and implementation phases' and the bullet order in Instructions, but no steps are actually sequenced, no file operations or commands are given, and validation is purely generic ('validate outcomes'), matching anchor 2 ('rough sequence present but many gaps; validation absent') rather than 1, which requires no sequence at all.

2 / 5

Progressive Disclosure

The body's section structure is clean but minimal, and the sole reference is broken: 'resources/implementation-playbook.md' is signaled twice (in Instructions and Resources) yet no resources/ directory or playbook file exists in the bundle, so navigation fails. This sits at anchor 2 ('minimal structure... references buried/useless') — it is not 3 because a clearly signaled reference that points nowhere provides no working disclosure at all.

2 / 5

Total

7

/

20

Passed

Description

70%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.

A solid, focused description: it clearly delimits the Conductor-track niche, names the key artifacts (spec.md, plan.md), and opens with an explicit trigger clause. Its main weakness is that the capability verbs are generic ('creating, managing, or working with') so the 'what' is never stated as distinct concrete actions.

Suggestions

State capabilities in third person as concrete actions (e.g., 'Creates and completes Conductor tracks: writes spec.md and plan.md, updates status markers, and maintains the tracks.md registry') so the 'what' is explicit rather than folded into the trigger clause.

Swap the generic 'working with' for the operation names a user would actually say (e.g., 'track status', 'tracks.md registry', 'close/complete a track') to strengthen trigger coverage.

DimensionReasoningScore

Specificity

It names the domain precisely ('Conductor tracks', 'spec.md', 'plan.md', 'track lifecycle operations') but the actions — 'creating, managing, or working with' — are near-synonymous generic verbs rather than distinct concrete capabilities, matching anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive'). It is not 4 because, unlike 'extracts text / fills forms / converts pages', the verbs don't enumerate what the skill actually does.

3 / 5

Completeness

The 'when' is explicit ('Use this skill when creating, managing, or working with Conductor tracks') and the 'what' is present but folded into the same clause rather than stated separately, matching anchor 4 ('both present; when could be more explicit'). It is not 5 because there is no distinct third-person statement of capability, and not 3 because the Use-when clause is explicit and the what is clearly conveyed.

4 / 5

Trigger Term Quality

Good natural-term coverage: 'Conductor tracks', 'spec.md', 'plan.md', 'features, bugs, and refactors', 'track lifecycle' are phrases a user in this workflow would say. It falls short of anchor 5's comprehensive synonym coverage — missing variations like 'tracks.md', 'track registry', or 'work units' that appear only in the body.

4 / 5

Distinctiveness Conflict Risk

'Conductor tracks' is a clear niche term with minimal conflict risk, but the semi-generic 'spec.md' and 'plan.md' triggers could overlap with general spec/plan-authoring skills outside Conductor, matching anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/skills/track-management/SKILL.md

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.