CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 well-built operational skill: copy-paste-ready commands, exact paths, clear step sequencing, and explicit success/failure messaging for both Worker and admin. The weaknesses are modest — a couple of redundant prose spots, no verification of CLI output before the overwrite push to MinIO, and a flat single-file layout with no navigation beyond step headers.

Suggestions

Add a post-run verification step before the mc mirror --overwrite push (e.g. check the CLI log tail or git diff in the workspace) to close the workflow_clarity validation gap.

Trim the opening paragraph (it restates the frontmatter description) and fold the config table's false/any row into the surrounding prose to tighten conciseness.

Move the spec.md Coding CLI Mode template and the admin failure-diagnostics block into a references/ file referenced from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense operational content — commands, paths, and message templates — with no explanation of concepts Claude already knows. Minor trim spots: the opening paragraph restates the frontmatter description and the config table's false/any row partially duplicates the surrounding prose.

4 / 5

Actionability

Fully executable guidance throughout: concrete bash (mc mirror with the exact storage prefix, run-coding-cli.sh with --cli/--workspace/--prompt-file/--timeout flags), jq commands, and exact success/failure message templates. Placeholders like {task-id} are appropriate substitution, not gaps.

5 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced with real checkpoints (processing-marker coordination before execution, exit-code branch, defined failure recovery where the worker codes on its own). Minor gaps: no verification that the CLI actually produced changes before pushing to MinIO with --overwrite, and no retry loop.

4 / 5

Progressive Disclosure

Heavy lifting is externalized to real bundle scripts (scripts/detect-available-cli.sh, scripts/run-coding-cli.sh) referenced by exact path, and the procedural steps belong inline in a ~200-line operational skill. Minor gaps: the spec.md template and failure-diagnostics block could be split into a reference file, and external skill dependencies (task-coordination, worker-management) are path-referenced but not described.

4 / 5

Total

17

/

20

Passed

Description

82%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 description: it clearly states what the skill does, names the supported tools, and gives an explicit, concrete trigger condition tied to the coding-request: message format. The main weakness is that it lists only one action, leaving the fuller capability set (workspace sync, result return, failure handling) implicit.

Suggestions

Enumerate the concrete actions in the description (e.g. 'sync the worker workspace, run the configured CLI, return coding-result:/coding-failed: to the Worker') to raise specificity from 1-2 actions to several.

Add one or two natural trigger synonyms such as 'delegate coding' or 'run coding operations in the worker's workspace' so trigger_term_quality reaches comprehensive coverage.

Consider naming the fallback behavior (worker codes on their own when the CLI is unavailable or fails) to distinguish this skill further from generic CLI-runner skills.

DimensionReasoningScore

Specificity

Names the domain and tools ("Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli) on behalf of Workers") with one concrete action, but does not enumerate several specific actions such as syncing the workspace, running the CLI, returning results, or handling failure.

3 / 5

Completeness

Explicitly answers both: what ("Execute AI coding CLI tools ... on behalf of Workers") and when ("Use when a Worker sends a coding-request: message, asking Manager to run coding operations in their workspace") with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Good natural trigger coverage for this context — "coding-request: message", "coding operations", and the tool names claude/gemini/qodercli — but a few natural variations (e.g. "run code changes", "delegate coding") are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — Manager-side delegation of coding to specific CLI tools, triggered by a literal coding-request: message type — with minimal overlap risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Revision

76a79fc

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill