coding-cli-management

Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli) on behalf of Workers. Use when a Worker sends a coding-request: message, asking Manager to run coding operations in their workspace.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

76%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.

A highly actionable, well-structured operational skill with real, verified scripts and clear multi-step sequencing. Its main weakness is the absence of a validation/verification checkpoint before the destructive MinIO overwrite, which caps workflow clarity.

Suggestions

Add a validation/review checkpoint before 'mc mirror --overwrite' pushes the CLI's changes back to MinIO — e.g. diff the workspace, run tests/lint, or require an explicit verification step — so the destructive overwrite is gated on confirmed-correct changes.

Tighten the redundancy between the intro paragraph (which restates the frontmatter description) and the Config section (which shows the same fields as both a JSON block and a table).

Make the cross-skill references explicit links (e.g. 'see channel-management skill: Sending Messages to Primary Channel') rather than inline prose mentions so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean and free of concept padding Claude already knows; minor redundancy in the intro restating the description and the config being shown both as a JSON block and a table.	4 / 5
Actionability	Fully executable copy-paste bash with real script paths (verified to exist), concrete CLI invocations with flags, and coverage of both success and failure cases.	5 / 5
Workflow Clarity	Steps 1–4 are clearly sequenced with checkpoints (processing-marker check, exit-code branching, failure notification), but the 'mc mirror --overwrite' push back to MinIO is destructive with no validation of the CLI's changes before overwriting, capping this at 3 per the destructive-operations rule.	3 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep script references that resolve to real bundle files; cross-skill references (task-coordination, worker-management, channel-management) are named but not explicitly linked.	4 / 5
	Total	16 / 20 Passed

Description

87%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 strong, third-person description that concretely states what it does and gives an explicit, protocol-specific 'Use when' trigger with named tools. Minor room for more natural synonyms but otherwise clear and distinct.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Execute AI coding CLI tools', 'run coding operations in their workspace') plus three specific tools (Claude Code / Gemini CLI / qodercli), with only minor coverage gaps versus a fully comprehensive list.	4 / 5
Completeness	Explicitly answers both 'what' (execute AI coding CLI tools on behalf of Workers) and 'when' via an explicit 'Use when a Worker sends a coding-request: message' trigger phrase.	5 / 5
Trigger Term Quality	Good keyword coverage including the concrete protocol trigger 'coding-request:' message and all three tool names; a few natural synonyms a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Manager/Worker delegation via the coding-request: protocol) with a distinct, unlikely-to-misfire trigger and minimal overlap with other skills.	5 / 5
	Total	18 / 20 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: agentscope-ai/AgentTeams
Path: manager/agent/skills-alpha/coding-cli-management/SKILL.md
Commit: 517caff

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.