Best for
- Check spec.md for the task. If it contains Coding CLI Mode, use this skill for all code changes.
agentscope-ai/AgentTeams/manager/agent/skills-alpha/worker-skills/coding-cli/SKILL.md
Use it for engineering and operations tasks; the detail page covers purpose, installation, and practical steps.
Decision brief
When the Manager assigns you a task with a " Coding CLI Mode" section in spec.md, you do not write the code yourself. Instead, you:
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Declared | Source record | Install path and trigger |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/agentscope-ai/AgentTeams --skill "manager/agent/skills-alpha/worker-skills/coding-cli"Inspect the Agent Skill "coding-cli" from https://github.com/agentscope-ai/AgentTeams/blob/062f1c8d7edd54ceaa2141862dd98a75c36c6980/manager/agent/skills-alpha/worker-skills/coding-cli/SKILL.md at commit 062f1c8d7edd54ceaa2141862dd98a75c36c6980. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Set up the workspace directory under the shared filesystem:
cd /root/agentteams-fs/shared/tasks/{task-id}/workspace git diff if it's a git repo
Check spec.md for the task. If it contains Coding CLI Mode, use this skill for all code changes.
Set up the workspace directory under the shared filesystem:
Review the “Clone a repo (example)” section in the pinned source before continuing.
Permission review
The documentation asks the agent to run terminal commands or scripts.
git clone <repo-url> "$workspace"The documentation asks the agent to run terminal commands or scripts.
The Manager will run the CLI tool and respond with either:The documentation asks the agent to create, modify, or delete local files.
**Limit scope**: tell the CLI "only modify file X, do not change tests or other files"Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 88/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 5,317 | Source | Repository attention, not individual Skill quality |
| Compatibility | 2 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
When the Manager assigns you a task with a "## Coding CLI Mode" section in spec.md, you do not write the code yourself. Instead, you:
Check spec.md for the task. If it contains ## Coding CLI Mode, use this skill for all code changes.
Set up the workspace directory under the shared filesystem:
workspace="/root/agentteams-fs/shared/tasks/{task-id}/workspace"
mkdir -p "$workspace"
# Clone a repo (example)
git clone <repo-url> "$workspace"
# Or copy existing code
cp -r /path/to/source "$workspace/"
Constraint: The workspace path must be under /root/agentteams-fs/. The Manager accesses the same path via MinIO mirror.
Before sending the coding-request, push all workspace files so the Manager can access them:
mc mirror "/root/agentteams-fs/shared/tasks/{task-id}/workspace/" \
${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/workspace/
Before modifying the workspace or sending a coding-request, check if the task directory is being processed:
# Sync latest state from MinIO
mc mirror "${AGENTTEAMS_STORAGE_PREFIX}/shared/tasks/{task-id}/" \
"/root/agentteams-fs/shared/tasks/{task-id}/"
# Check for processing marker
if [ -f "/root/agentteams-fs/shared/tasks/{task-id}/.processing" ]; then
echo "Task directory is being processed. Wait for manager to complete."
# Do NOT send coding-request yet; wait and retry
fi
If a .processing marker exists, wait for the Manager to complete their operation before sending your request.
A good prompt includes:
Example of a good prompt:
In the file `src/server/handlers/auth.go`, implement the `RefreshToken` function (currently a stub at line 142).
Requirements:
- Validate the incoming refresh_token from the request body (field name: "refresh_token")
- Look up the token in the database using `db.FindRefreshToken(ctx, token)` (already imported)
- If valid, generate a new access token with `auth.GenerateAccessToken(userID)` and return it as JSON: {"access_token": "<token>", "expires_in": 3600}
- If invalid or expired, return HTTP 401 with body: {"error": "invalid_refresh_token"}
- Follow the existing error handling pattern used in `LoginHandler` (line 89)
Do not change any other files.
Signs of a weak prompt (avoid):
coding-request: to ManagerSend in your Worker Room (or Project Room, wherever the task was assigned):
@manager:DOMAIN task-{task-id} coding-request:
workspace: /root/agentteams-fs/shared/tasks/{task-id}/workspace
---PROMPT---
{your detailed coding prompt here}
---END---
Note: workspace can be any subdirectory under /root/agentteams-fs/, e.g. a cloned git repo:
workspace: /root/agentteams-fs/shared/tasks/{task-id}/workspace/my-repo
The Manager will run the CLI tool and respond with either:
Success — coding-result:
@{your-name}:DOMAIN task-{task-id} coding-result:
CLI 工具已完成编码。请同步工作目录并 review 变更...
Failure — coding-failed:
@{your-name}:DOMAIN task-{task-id} coding-failed:
CLI 工具执行失败...你生成的提示词已保存于:/root/agentteams-fs/shared/tasks/{task-id}/coding-prompts/
coding-result:# Sync changes from MinIO
agentteams-sync
# Review what changed
cd /root/agentteams-fs/shared/tasks/{task-id}/workspace
git diff # if it's a git repo
# or: check coding-cli-logs/ for CLI output
Review the changes:
Report to Manager:
@manager:DOMAIN task-{task-id} completed:
Changes reviewed and verified. {Brief summary of what was implemented.}
coding-failed:Implement the coding task yourself using your normal approach. When done, report:
@manager:DOMAIN task-{task-id} completed:
Implemented manually (CLI delegation failed). {Brief summary.}
If one CLI delegation doesn't fully complete the task (e.g., the first run fixed the bug but tests still fail), you can send another coding-request: with a follow-up prompt. Sync the workspace first to get the latest state before generating the next prompt.
go test ./... to verify"Alternatives
PramodDutta/qaskills
Gate RAG pipelines in CI with versioned golden eval sets, per-metric thresholds, baseline drift detection, and a build that fails when retrieval or answer quality regresses.
PramodDutta/qaskills
Generate comprehensive test cases from state machine models covering all states, transitions, guard conditions, and invalid transition attempts for workflow-heavy features
PramodDutta/qaskills
Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases
Yeachan-Heo/oh-my-claudecode
N coordinated agents on shared task list using Claude Code implicit agent teams