conductor-new-track

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

Quality

66%

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

73%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 well-sequenced, validation-rich planning protocol with concrete paths, formats, and commands — strongest in workflow clarity and actionability. Its main weakness is conciseness, due to a duplicated critical-questioning block and mentoring exposition that inflate token load.

Suggestions

Remove the duplicated 'Sequential Questioning (CRITICAL)' paragraph (stated both in Operational Standards and in section 2.2) — define it once and reference it.

Trim the 'Strategic Transparency' / 'Strategic Action' mentoring rationale to brief notes so the protocol stays lean while preserving the why.

Specify the metadata.json schema concretely (field names and types) so artifact creation is copy-paste ready rather than loosely enumerated.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational protocol, but carries redundancy (the 'Sequential Questioning (CRITICAL)' block is restated near-verbatim at lines 22 and 72) and mentoring/strategic-philosophy exposition that could be tightened.	3 / 5
Actionability	Highly actionable instruction-only skill: exact paths, formats (Track ID 'shortname_YYYYMMDD', commit message, status markers '[ ]'), and a concrete curl/mkdir block, with only minor gaps like the loosely-specified metadata.json fields.	4 / 5
Workflow Clarity	Clearly sequenced Handshake → 2.1–2.5 → Artifacts → Registry flow with explicit validation (health checks for missing files, collision checks, Approve/Revise loops, verify-after-install) and feedback loops (self-correct once or halt).	5 / 5
Progressive Disclosure	Good sectioned structure with a clearly signaled, verified one-level-deep reference to assets/catalog.md; the inline operational protocol is appropriately kept together, with only minor organization gaps given the body length.	4 / 5
	Total	16 / 20 Passed

Description

58%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 concrete actions in proper third-person voice but omits any explicit 'when to use' trigger guidance, capping its completeness. It is specific and distinct within the Conductor niche yet relies on framework jargon over natural user phrases.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when starting a new feature, bug fix, or chore track in a Conductor/SDD project.'

Include natural phrasings users would actually say ('plan a feature', 'start a new track', 'create a spec and plan') alongside the SDD terminology.

Differentiate from conductor-implement in the description (e.g. 'planning phase only — hands off to implementation') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions in third person ('Plans a new track', 'generates spec/plan documents', 'updates the registry'), comparable to the anchor listing multiple specific actions with only minor coverage gaps.	4 / 5
Completeness	The 'what' is clear (plans, generates, updates) but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes some natural terms ('feature', 'bug fix') but leans on Conductor/SDD jargon ('track', 'spec/plan documents', 'registry') and misses common phrasings a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Conductor track planning) and is mostly distinct, with only minor overlap risk against sibling skills like conductor-setup or conductor-implement.	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
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: f06add3

Reviewed: 12 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.