conductor-new-track

Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/conductor-new-track/SKILL.md

Quality

Content

62%

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

The skill delivers a well-sequenced, validation-rich workflow with strong checkpoints, which is its main strength. It loses points for a malformed curl command, abstract questioning guidance, mentor-style verbosity, and a monolithic body that keeps template material inline rather than in reference files. Fixing the install command and splitting reusable templates into references would lift the weaker dimensions.

Suggestions

Correct the skill-install curl sequence into a single executable command with proper line separators or `&&` between `mkdir` and `curl`.

Move the spec.md/plan.md section templates and registry-entry format strings into a reference file referenced one level deep from the body.

Trim the "Strategic Action"/"Strategic Transparency" rationale passages to the minimum needed, trusting Claude to understand the workflow's value.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable operational protocol rather than concept explanation, but mentor-style "Strategic Transparency"/"Strategic Action" exposition and repeated rationale padding add length that could be tightened.	2 / 3
Actionability	Concrete guidance exists (paths, metadata.json fields, commit-message format, curl install), but the curl command is malformed/line-broken and several instructions stay abstract ("Ask 3-4 relevant questions"), fitting the incomplete-guidance anchor.	2 / 3
Workflow Clarity	The process is clearly sequenced (Handshake → 2.1–2.5) with explicit validation checkpoints (file-existence health check, tool-call validation with one self-correct, collision check, skill-folder verification) and revise-until-confirmed feedback loops.	3 / 3
Progressive Disclosure	The single referenced file (assets/catalog.md) is one level deep and clearly signaled, but the body itself is a long monolithic protocol with inline spec/plan/registry templates and format specs that could be split into reference files.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 concrete capabilities but omits any explicit "Use when..." trigger guidance, leaving the "when" dimension implied and capping completeness. Trigger terms are framework-jargon-heavy and lack natural user variations. Adding an explicit usage-trigger clause would raise the completeness, trigger-term, and distinctiveness scores together.

Suggestions

Append an explicit trigger clause, e.g. "Use when starting a new feature, bug fix, or chore track in a Conductor/SDD project."

Include natural user phrasings alongside the jargon (e.g., "new feature", "start a task", "plan a bug fix") to improve trigger-term coverage.

Tie the niche more tightly to the Conductor framework in the description so it is less likely to overlap with generic planning skills.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — "Plans a new track", "generates spec/plan documents", and "updates the registry" — matching the multiple-specific-actions anchor rather than the partial coverage of level 2.	3 / 3
Completeness	The "what" is clearly stated, but there is no explicit "when to use" clause; per the judging guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "new track", "spec/plan documents", and "registry" are relevant but rely on Conductor/SDD framework jargon rather than natural user phrasing, and no "Use when..." trigger or common variations are offered.	2 / 3
Distinctiveness Conflict Risk	The track/spec/plan/registry niche is somewhat specific, but generic "feature or bug fix" planning language and the absence of distinct triggers mean it could overlap with other planning skills.	2 / 3
	Total	9 / 12 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: gemini-cli-extensions/conductor
Path: skills/conductor-new-track/SKILL.md
Commit: fb6212e

Reviewed: 4 days 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.