conductor-implement

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 body is a highly actionable, clearly sequenced workflow with strong validation checkpoints and error-recovery loops, but it carries generic boilerplate up top and fails to split its long content across reference files for progressive disclosure.

Suggestions

Remove the generic boilerplate in 'Use this skill when', 'Do not use this skill when', and 'Instructions' (e.g. 'Apply relevant best practices and validate outcomes') that merely restates Claude's defaults.

Move large, self-contained blocks (menu templates, the metadata.json schema, error-handling option menus) into reference files under references/ and link to them one level deep to enable progressive disclosure.

Either create resources/implementation-playbook.md or remove the dangling reference to it, so the body's only external reference points at a real file.

Dimension	Reasoning	Score
Conciseness	The body is largely concrete (paths, git commands, JSON, menus), but opens with generic boilerplate such as 'Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes', and 'Provide actionable steps and verification' that Claude already knows, matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It provides copy-paste-ready executable commands ('git add -A', 'git commit -m "{commit_prefix}: ..."'), concrete file paths ('conductor/tracks/{trackId}/plan.md'), exact status transitions ('[ ]' to '[~]' to '[x]'), and a full metadata.json schema, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	The process is explicitly sequenced (pre-flight checks -> track selection -> context loading -> task execution loop -> phase completion -> track completion) with explicit validation (phase verification, running the full test suite) and feedback loops (tool/test/git failure option menus plus 'CRITICAL: Wait for explicit user approval before proceeding to next phase'), matching the level-3 anchor; the destructive-operation cap does not apply because verification checkpoints are present.	3 / 3
Progressive Disclosure	No bundle files exist and the entire workflow lives inline in a single ~387-line file; the one referenced file 'resources/implementation-playbook.md' is not present, so content that could be split stays inline, matching 'some structure but could be better organized; content that should be separate is inline' rather than the well-signaled external-reference level 3.	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 is concise and identifies a clear domain and action, but it omits any explicit 'when to use' trigger and leans on internal jargon, leaving all dimensions at the mid level.

Suggestions

Append an explicit trigger clause, e.g. 'Use when implementing tasks from a Conductor track plan, running the TDD red/green/refactor cycle, or resuming an in-progress track.'

Add natural-language keywords users would actually say (e.g. 'implement track tasks', 'run TDD workflow', 'resume track') alongside the domain terms.

List a couple more concrete actions (e.g. 'update plan.md status, commit per task, run phase verification') to lift specificity from a single action to multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Quotes 'Execute tasks from a track's implementation plan following TDD workflow' name a concrete domain and a single action but do not enumerate multiple specific actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	The description states what the skill does but contains no 'Use when...' or equivalent explicit trigger clause; per the rubric guideline a missing trigger clause caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Terms like 'track', 'implementation plan', and 'TDD workflow' are relevant but heavily tied to internal Conductor jargon and lack the common natural variations a user would say, fitting 'some relevant keywords but missing common variations' rather than broad level-3 coverage.	2 / 3
Distinctiveness Conflict Risk	The track-implementation-plus-TDD niche is somewhat specific, but the skill belongs to a Conductor family with referenced sibling skills (setup, new-track, status), creating overlap risk consistent with 'somewhat specific but could still overlap with similar skills' rather than the conflict-free level 3.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 615669b

Reviewed: 5 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.