coding-cli

将编码工作委托给 Manager 持有的 AI CLI 工具（Claude Code / Gemini CLI / qodercli）执行

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./manager/agent/skills-alpha/worker-skills/coding-cli/SKILL.md

Quality

Content

67%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.

The body is a highly actionable, well-sequenced workflow with concrete commands, message templates, and validation checkpoints; its main weakness is mild redundancy between the intro list, the prompt-generation section, and the tips section.

Suggestions

Remove or shrink the intro 5-step list (lines 11–15) since it duplicates the 'Step-by-Step Workflow' section headers that follow.

Consolidate 'Tips for Better Prompts' with 'Generate a High-Quality Prompt' to eliminate the repeated guidance on being surgical, limiting scope, and providing imports.

Define the .processing marker wait-and-retry loop concretely (e.g., sleep interval and max retries) instead of leaving it as 'wait and retry'.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's competence (no basic-concept padding) and is mostly efficient, but the intro 5-step list duplicates the workflow section headers and 'Tips for Better Prompts' repeats §3 (be surgical, limit scope, provide imports), so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready bash commands and coding-request/result/failed/completed message templates plus a concrete good-prompt example with file path, line number, and function names; minor gaps remain (placeholders like {task-id}/DOMAIN and a vague 'implement … using your normal approach' fallback).	4 / 5
Workflow Clarity	Clear numbered sequence with explicit validation checkpoints (.processing marker check in 2b, review checklist in 6a) and feedback loops (6b manual fallback, Multiple Rounds); the .processing 'wait and retry' loop is left implicit, a minor validation gap keeping it below 5.	4 / 5
Progressive Disclosure	No bundle files exist; the single-file body is well-organized into clear sections (When to Use, Step-by-Step, Multiple Rounds, Tips) with content appropriately placed inline, fitting anchor 4 rather than 5 since there are no one-level-deep references to signal.	4 / 5
	Total	15 / 20 Passed

Description

53%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.

The description clearly conveys what the skill does and names specific tools, giving it a distinct niche, but it omits any explicit 'when to use' trigger guidance and relies on operational jargon rather than natural user phrases.

Suggestions

Add an explicit 'Use when…' clause to the description stating the trigger (e.g., 'Use when the Manager has enabled Coding CLI Mode in spec.md and you need to write, modify, refactor, or fix code').

Include natural user-facing trigger terms ('write code', 'fix bugs', 'refactor', 'delegate coding') in the description rather than only operational phrasing.

Optionally enumerate 1-2 more concrete actions (e.g., 'prepare a workspace and review CLI-generated diffs') to lift specificity above a single delegated action.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('将编码工作委托给…执行') and three specific tools (Claude Code / Gemini CLI / qodercli), but covers essentially one action rather than a comprehensive list, matching anchor 3.	3 / 5
Completeness	Clearly states what the skill does (delegate coding to the Manager's CLI tools) but provides no 'when' guidance in the description itself — the trigger lives in the separate assign_when field, so per the missing-'Use when' cap it stays at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords (编码工作, AI CLI 工具, named tool brands) but is framed as what-it-does rather than natural user phrasing, and lacks common variations or a 'use when' trigger phrase.	3 / 5
Distinctiveness Conflict Risk	Has a clear niche (Manager-mediated delegation to specific named CLI tools) with distinct triggers and only minor overlap risk with generic coding skills, fitting anchor 4 rather than the fully-distinct anchor 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: agentscope-ai/AgentTeams
Path: manager/agent/skills-alpha/worker-skills/coding-cli/SKILL.md
Commit: 69c5849

Reviewed: 2 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.