conductor-new-track

Create a new track with specification and phased implementation plan

Quality

63%

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 ./skills/conductor-new-track/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear, validated workflow and concrete templates, but it carries some generic boilerplate and bundles large templates inline rather than offloading them to reference files.

Suggestions

Trim the generic "Instructions", "Use this skill when", and "Do not use this skill when" sections, which restate obvious guidance without adding skill-specific value.

Move the long spec.md and plan.md templates into reference files (e.g., references/spec-template.md) referenced one level deep to reduce inline bulk.

Consider replacing the optional "Press enter to skip" phrasing with a single concise note rather than repeating it across multiple questions.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete templates and prompts, but generic boilerplate sections ("Instructions", "Use this skill when", "Do not use this skill when") add filler Claude does not need and could be tightened.	2 / 3
Actionability	Exact file paths, per-question prompt text, full spec.md/plan.md/metadata.json templates, and a concrete track-ID format with collision handling make the guidance copy-paste ready and fully executable.	3 / 3
Workflow Clarity	The flow from pre-flight checks through spec generation, two user-review gates, plan generation, and track creation has an explicit sequence with validation checkpoints and an error-handling/feedback section.	3 / 3
Progressive Disclosure	The skill is self-contained with clean section organization, but the large spec.md and plan.md templates live inline in a ~425-line monolithic SKILL.md that could be split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concisely conveys what the skill produces but lacks any explicit use-when trigger guidance and relies on domain jargon rather than natural user keywords. It is competent but would benefit from a trigger clause and more concrete action enumeration.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers (e.g., starting a new feature, fixing a bug, planning a refactor, or bootstrapping a Conductor track).

Enumerate concrete actions beyond "create", such as "gathers requirements, generates a spec.md, and produces a phased plan.md".

Replace jargon-only terms with phrasings a user would naturally say, like "new feature", "bug fix", or "implementation plan".

Dimension	Reasoning	Score
Specificity	Quotes "Create a new track with specification and phased implementation plan" name the domain and two concrete artifacts, but the action list is not comprehensive enough to reach the multi-action score-3 anchor.	2 / 3
Completeness	It states what the skill does (create a track with spec and plan) but omits any explicit "when to use" trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Terms like "track", "specification", and "implementation plan" are Conductor-specific jargon rather than natural user phrasing, and there is no "Use when..." trigger, but the keywords are still recognizable domain terms.	2 / 3
Distinctiveness Conflict Risk	The "new track" niche is Conductor-specific and fairly distinct, but the absence of distinct trigger terms leaves some overlap risk with other track or project-management skills.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 3 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/conductor-new-track/SKILL.md
Commit: e63f7dd

Reviewed: about 4 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.