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

77%Weight 40%Scale 1-3

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

The body is highly actionable with executable bash, real referenced scripts, and a well-sequenced workflow including validation and failure handling. It is held back by repeated config/sync snippets and dense inline templates that a longer skill could offload into reference files.

Suggestions

Consolidate the three near-identical config-write echo blocks in Step 1 (and the repeated mc mirror calls in Step 3) into a single helper script under scripts/, referencing it instead of duplicating the JSON construction.

Move the spec.md Coding CLI Mode template and the coding-result/coding-failed message templates into a references/ file (e.g. references/templates.md), keeping SKILL.md a leaner overview that links one level deep.

Extract the ~/coding-cli-config.json schema table into a short reference or fold the three config states into one example with a note on the enabled/cli combinations to reduce inline repetition.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays operational, but repeats near-identical config-write echo blocks (three variants in Step 1) and mc-mirror patterns that a helper script could consolidate, fitting 'mostly efficient but could be tightened' rather than the fully lean top anchor.	2 / 3
Actionability	It provides fully executable bash (agt get workers, mc mirror, jq, an 8-step execution block with real flags and paths) and concrete message templates, and the referenced scripts detect-available-cli.sh and run-coding-cli.sh exist as real files, matching copy-paste-ready guidance.	3 / 3
Workflow Clarity	Steps 1-4 are clearly sequenced, with an explicit 8-step execution flow that includes validation checkpoints (processing-marker guard, exit-code check before MinIO push) and a dedicated Step 4 failure branch with a diagnostic checklist, matching the anchor for clear sequence with validation and error recovery.	3 / 3
Progressive Disclosure	The two bundle scripts are cleanly externalized and referenced one-level-deep with full paths, but the ~196-line SKILL.md inlines reference-style content (config schema, multiple message templates, the spec.md template) with no references/ directory, fitting 'some structure but content that should be separate is inline' rather than the well-split top anchor.	2 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 concrete and specific, naming the three supported CLIs and the exact message-protocol trigger, with an explicit Use-when clause covering both what and when. Its only weakness is a narrow, protocol-literal trigger term that offers few natural-language variations.

Dimension	Reasoning	Score
Specificity	"Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli)" names concrete tools and the concrete action of running coding operations, matching the anchor for multiple specific concrete actions rather than the vague single-action anchor at 2.	3 / 3
Completeness	It states what the skill does (execute CLI tools on behalf of Workers) and gives an explicit "Use when..." trigger clause, satisfying both what and when per the top anchor; the present Use-when clause avoids the cap at 2.	3 / 3
Trigger Term Quality	The trigger "Use when a Worker sends a coding-request: message" is explicit and relevant, but it is a single internal protocol literal with limited natural-language variations, fitting 'some relevant keywords but missing common variations' rather than broad coverage at 3.	2 / 3
Distinctiveness Conflict Risk	The unique "coding-request:" message protocol scoped to Manager-on-behalf-of-Workers gives it a clear niche unlikely to conflict with other skills, matching the distinct-triggers anchor.	3 / 3
	Total	11 / 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: agentscope-ai/AgentTeams
Path: manager/agent/skills-alpha/coding-cli-management/SKILL.md
Commit: 785c2db

Reviewed: 6 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.