conductor-implement

Execute tasks from a track's implementation plan following TDD workflow

Quality

46%

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 ./.agent/skills/conductor-implement/SKILL.md

Quality

Content

40%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 opens with a genuinely useful pre-flight check section, but roughly a third of it is boilerplate filler, the 'Track Selection' section is empty, and the core workflow is a malformed list of 16 links to sub-skill files that do not exist in the bundle. The skill currently delegates all real guidance to files the reader cannot open.

Suggestions

Fix the knowledge-module list: repair the duplicate numbering at items 12-16, convert '[If argument provided:]'-style headings into proper descriptive titles, and group links by workflow phase (selection, execution, completion, error handling).

Ensure the referenced sub-skill files (./sub-skills/*.md and resources/implementation-playbook.md) actually exist in the bundle, or inline the essential steps for the most common path.

Delete the templated 'Use this skill when', 'Do not use this skill when', and generic 'Instructions' filler, and either fill the empty 'Track Selection' section or remove the header.

Add validation checkpoints to the main workflow (e.g. verify tests pass before marking a task complete) since the body only validates the pre-flight step.

Dimension	Reasoning	Score
Conciseness	The pre-flight and knowledge-module sections are lean, but three sections are pure template padding ('Clarify goals, constraints, and required inputs', 'The task is unrelated to implement track', 'You need a different domain or tool outside this scope') that tell Claude nothing it doesn't know. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' — not the several padded sections of anchor 2, since the padding is a small fraction of an already short body.	3 / 5
Actionability	The pre-flight checks are genuinely concrete (check specific files exist, suggest running /conductor:setup, parse TDD strictness and commit strategy), but every instruction past pre-flight is delegated to sub-skill files that are not present in the bundle, so the actual execution guidance is incomplete. This matches 'some concrete guidance but incomplete' rather than anchor 4's mostly-executable body.	3 / 5
Workflow Clarity	The body has a rough sequence (pre-flight, then task identification through completion) but large gaps and incoherent structure: the 'Track Selection' section is completely empty, the 16-item module list restarts its numbering at items 12-16 (duplicate '1.'-'5.' headings), and conditional headings like '[If argument provided:]' leave the branching ambiguous. This fits 'rough sequence present but many gaps; steps poorly defined' better than anchor 3, where the sequence itself is coherent and only validation is missing.	2 / 5
Progressive Disclosure	Scoring against the actual bundle: there are no reference, script, or asset files present, so all 17 referenced paths (./sub-skills/*.md, resources/implementation-playbook.md) are dangling and a reader following them hits dead ends. Combined with malformed one-line headings and no grouping of the 16 links, navigation is broken in practice despite the links being one level deep, fitting 'minimal structure' at 2 rather than the organized-but-imperfect anchor at 3.	2 / 5
	Total	10 / 20 Passed

Description

53%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 lean, third-person, domain-specific description that says what the skill does but never says when to use it. Adding an explicit 'Use when...' clause with natural trigger phrases would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when asked to implement tasks from a conductor track, work on track tasks, or run the TDD cycle for a track.'

List one or two more concrete actions (e.g. 'select tasks, run red-green-refactor cycles, update track status') to broaden coverage.

Include natural synonyms users would say ('implement a task', 'work on track X') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('a track's implementation plan') and one concrete behavior ('following TDD workflow'), matching the anchor for domain plus 1-2 concrete actions. It does not list the several specific actions (task selection, test-first cycles, commit strategy, status updates) that a comprehensive description would, so it sits at 3 rather than 4.	3 / 5
Completeness	It has a clear 'what' ('Execute tasks from a track's implementation plan following TDD workflow') but no 'Use when...' clause or equivalent trigger guidance at all — the judging guideline explicitly caps completeness at 3 for this. It cannot score 4, which requires both what and when.	3 / 5
Trigger Term Quality	Phrases like 'implementation plan', 'TDD workflow', and 'track' are relevant domain keywords, but common natural variations a user would actually say ('implement a task', 'work on track X', 'write the failing test') are missing. This matches 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	The conductor-specific vocabulary ('track's implementation plan', 'TDD workflow') carves out a clear niche with minimal conflict risk against unrelated skills. Minor overlap remains with sibling conductor skills (setup, planning) that would use similar terms, so it is 'mostly distinct' at 4 rather than the fully distinct anchor at 5.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 16 missing	Warning

	Total	13 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/conductor-implement/SKILL.md
Commit: c4a059b

Reviewed: 1 hour 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.