conductor-review

Reviews the completed track work against guidelines and the plan. Acts as a Principal Software Engineer to ensure quality and compliance.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/conductor-review/SKILL.md

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 well-structured, highly actionable review protocol with strong workflow sequencing and validation checkpoints, scoring 3 on actionability and workflow clarity. It loses points on conciseness (padded persona/preamble) and progressive disclosure (monolithic with no reference-file split).

Suggestions

Trim the 'Persona' bullets and consolidate the repetitive Interaction Protocol / Sequential Questioning preamble into a single concise statement to improve token efficiency.

Extract the detailed report format and commit/plan-update templates into a reference file (e.g., references/report-format.md) referenced one level deep, leaving SKILL.md as an overview.

De-duplicate the repeated instructions to always include an '(Recommended)' prefix and an 'Other' option, stating the rule once in the Interaction Protocol.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural protocol, but the 'Persona' bullets and the repetitive Operational/Interaction/Sequential-Questioning preamble plus repeated '(Recommended)'/'Other'-option instructions add padding that could be tightened.	2 / 3
Actionability	Provides fully executable commands (git diff --shortstat, git status --porcelain), concrete commit-message templates, explicit file paths, and a copy-paste-ready report/diff output format.	3 / 3
Workflow Clarity	Clearly sequenced phases with explicit validation checkpoints (file-existence health checks, tool-validation/self-correct-once, test execution and failure analysis, Yes/No gating of irreversible deletion) and error-recovery loops.	3 / 3
Progressive Disclosure	A single monolithic SKILL.md with no bundle reference files; sections are well-organized but detailed report templates and commit protocols are inline rather than split into one-level-deep reference files.	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 states what the skill does clearly but omits any explicit 'when to use it' trigger guidance and leans on domain-internal jargon over natural user keywords. It is competent but not exemplary, scoring 2 across all dimensions.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms, e.g. 'Use when reviewing completed track work, running a code review, or checking implementation against the plan and guidelines.'

Enumerate concrete review actions (e.g., 'verifies plan compliance, checks style-guide adherence, runs the test suite, and commits fixes') to lift specificity to 3.

Replace Conductor-internal jargon with user-facing terms ('code review', 'review my changes', 'check the track') to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain (track-work review) and a concrete action ('Reviews the completed track work against guidelines and the plan') but does not enumerate multiple specific concrete actions like the score-3 anchor.	2 / 3
Completeness	Clearly answers 'what' but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Has plausible keywords ('review', 'track') but relies on Conductor-internal jargon ('track work', 'guidelines and the plan', 'compliance') rather than broad natural terms users would say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific Conductor niche but the 'Principal Software Engineer / quality and compliance' framing could still overlap with other generic code-review skills.	2 / 3
	Total	8 / 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-review/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.