conductor-implement

Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.

Quality

68%

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 ./skills/conductor-implement/SKILL.md

Quality

Content

70%

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

The content is a well-structured, clearly sequenced operational protocol with strong validation checkpoints and good file-based navigation. Its main weaknesses are verbosity (repetitive emphasis and restated rules) and dependence on external files for the actual executable implementation detail.

Suggestions

Trim repetitive emphasis and restated rules (e.g., consolidate the multiple 'MUST ask one at a time / MUST provide options / include Other' guidance) to improve token efficiency.

Inline a minimal concrete example of a task loop iteration (read task, follow Workflow, test, commit) so the protocol is actionable without fully deferring to external files.

Add an explicit retry/feedback loop for tool failures beyond 'self-correct once' (e.g., validate -> fix -> re-run) given the batch/file-editing operations involved.

Dimension	Reasoning	Score
Conciseness	The protocol is mostly instructional and free of concept explanation, but it is verbose and repetitive (CRITICAL/You MUST emphasis, restated rules on question types and path integrity) that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It gives concrete guidance (file paths like conductor/index.md, status tokens [~]/[x], commit message templates) but key steps rely on deferring to other files (Workflow, Specification, Implementation Plan) without inlining the executable detail, fitting 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	It provides a clearly sequenced five-phase protocol with explicit validation/checkpoint language ('HALT', 'verify that every linked file actually exists', 'Only after receiving explicit user confirmation', status transitions), matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	The SKILL.md is a self-contained operational overview with well-organized numbered sections and references to one-level-deep external files (conductor/index.md, product.md, workflow.md, the track's index.md); no bundle files exist and the per-scoring-notes exception applies, so it scores 3.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 well-formed: it pairs a clear 'what' with an explicit 'Use this to...' trigger clause in third person. It is somewhat generic and could be sharpened with more concrete capability verbs and more distinctive trigger terms.

Suggestions

Add more concrete action verbs (e.g., 'parses the plan, executes each task, runs tests, commits progress, and syncs project docs') to lift specificity.

Broaden natural trigger terms to include variations users say (e.g., 'implementation plan', 'work on the next task', 'resume a track', 'SDD workflow').

Tie the trigger more tightly to Conductor-specific artifacts (e.g., 'Use when resuming work on a Conductor track from conductor/tracks.md') to reduce overlap with generic coding skills.

Dimension	Reasoning	Score
Specificity	It names the domain (executing tasks in a track's plan) and a couple of actions (start or continue work on a feature, bug fix, or chore) but does not list multiple concrete distinct capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It answers 'what' ('Executes the tasks defined in the specified track's plan') and 'when' with an explicit trigger clause ('Use this to start or continue working on a feature, bug fix, or chore'), matching the 'both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	'feature', 'bug fix', 'chore', 'plan', and 'track' are reasonable natural terms a user might say, but it lacks common variations and explicit artifact/scope vocabulary, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The Conductor/track/plan framing is somewhat distinctive but 'start or continue working on a feature, bug fix, or chore' is generic and could overlap with general implementation skills, fitting 'somewhat specific but could still overlap'.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gemini-cli-extensions/conductor
Path: skills/conductor-implement/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.