conductor-new-track

Create a new track with specification and phased implementation plan

1.92x

Quality

31%

Does it follow best practices?

Impact

98%

1.92x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

62%Scale 1-3

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

This skill excels at actionability and workflow clarity with a well-structured, multi-step process including explicit validation gates and error handling. However, it is significantly over-verbose — full file templates and per-track-type question scripts are spelled out inline when Claude could generate these from brief structural guidance. The content would benefit greatly from splitting templates into referenced files and trimming redundant detail.

Suggestions

Move the full markdown templates (spec.md, plan.md, metadata.json, index.md) into separate referenced files to reduce the main skill from ~250 lines to ~80-100 lines.

Condense the interactive question flows — instead of spelling out every prompt verbatim, provide a concise table of questions per track type and let Claude generate natural conversational prompts.

Remove the 'Use this skill when / Do not use this skill when' section — this is generic boilerplate that adds no value and wastes tokens.

Trim the completion message template and error handling to bullet points rather than full formatted blocks — Claude can generate appropriate user-facing messages from brief guidance.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~250+ lines, with extensive template boilerplate that Claude could generate on its own. The full markdown templates for spec.md, plan.md, metadata.json, and index.md are spelled out in detail when brief structural guidance would suffice. The interactive question scripts are also overly detailed for Claude's capabilities.	1 / 3
Actionability	The skill provides highly concrete, executable guidance: exact file paths, directory structures, JSON schemas, markdown templates, specific question flows per track type, and precise ID generation rules. Every step is copy-paste ready with clear formats and examples.	3 / 3
Workflow Clarity	The multi-step workflow is clearly sequenced: pre-flight checks → classification → interactive gathering → spec generation → user review → plan generation → user review → track creation → completion message. Validation checkpoints are explicit (user review gates, uniqueness checks, error handling with rollback). The feedback loops for user review (edit/start over options) are well-defined.	3 / 3
Progressive Disclosure	There is one reference to `resources/implementation-playbook.md` for detailed examples, but the bulk of the content is monolithic — full templates, all track type question flows, and all file creation details are inline. The spec template, plan template, metadata schema, and index template could be split into referenced files to reduce the main skill's size significantly.	2 / 3
	Total	9 / 12 Passed

Description

0%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically underspecified. It fails to explain what kind of 'track' is being created, what domain it applies to, or when Claude should select this skill. The vague terminology makes it nearly impossible to distinguish from other planning or creation-oriented skills.

Suggestions

Clarify what 'track' means in this context (e.g., project track, learning track, feature track) and list specific concrete actions the skill performs.

Add an explicit 'Use when...' clause with natural trigger terms a user would actually say, such as specific keywords related to the domain.

Include domain-specific terminology and file types or artifacts involved to make the skill clearly distinguishable from generic planning or creation skills.

Dimension	Reasoning	Score
Specificity	The description uses vague language — 'track', 'specification', and 'phased implementation plan' are abstract terms without concrete actions. It doesn't specify what kind of track, what the specification entails, or what the implementation plan involves.	1 / 3
Completeness	The description only vaguely addresses 'what' (create a track with spec and plan) and completely lacks any 'when' guidance or explicit trigger clause. There is no 'Use when...' or equivalent.	1 / 3
Trigger Term Quality	The terms 'track', 'specification', and 'phased implementation plan' are not natural keywords a user would typically say. 'Track' is especially ambiguous (music track? project track? racing track?) and the other terms are generic project management jargon.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic and could overlap with project planning, task management, music production, or any number of other skills. 'Track' and 'specification' are too ambiguous to carve out a clear niche.	1 / 3
	Total	4 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/conductor-new-track/SKILL.md
Commit: fbdfd63

Reviewed: 3 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.