Huawei Cloud Vod Collector

VoD (Voice of Developer) Collector Skill

Script execution: All scripts are located in <SKILL_DIR>/scripts/. You must use skill action=exec to execute them. Do not run them directly in a shell. <SKILL_DIR> = directory containing this SKILL.md. .vod/ is relative to CWD (project working directory).

<!-- cli-install-version: 3.8.0 -->

Step 0: Install skill-quality-cli (idempotent, skip if already installed)

bash scripts/ensure_cli.sh

The script detects whether skill-quality-cli is available; if not, it downloads the tar.gz package (wrapper + ELF + Python fallback, low-GLIBC compatible) and installs it to ~/.local/bin/. Silently skipped when offline — never blocks the business flow.

Overview

The VoD (Voice of Developer) Collector captures poor developer experiences and issues encountered while using Huawei Cloud tools or services. It prepares high-quality requirements or issue reports (GitCode issues) for product and engineering teams. The skill is declarative: it collects feedback with scripts and a hooks-based capture pipeline, deduplicates, sanitizes, and delivers prioritized issues to a GitCode repository.

Core Commands

Common CLI examples grouped by function (all scripts under <SKILL_DIR>/scripts/):

• Capture

python <SKILL_DIR>/scripts/md_io.py write-feedback --output .vod/feedbacks/
python <SKILL_DIR>/scripts/vod_sanitize.py file --path <file>

• Extract / Edit (use write-feedback to update fields or edit feedback files directly)

• Deliver

python <SKILL_DIR>/scripts/vod_deliver.py deliver --feedback-id <id> --feedbacks-dir .vod/feedbacks
python <SKILL_DIR>/scripts/vod_deliver.py update-status --feedback-id <id> --status delivered --feedbacks-dir .vod/feedbacks

• Auto-login (only when deliver returns need_login)

bash <SKILL_DIR>/scripts/vod_install.sh
python <SKILL_DIR>/scripts/vod_deliver.py server-start
curl -s -X POST http://localhost:8080/login/start
python <SKILL_DIR>/scripts/vod_deliver.py login-wait --session-id <session_id>
python <SKILL_DIR>/scripts/vod_deliver.py server-stop --pid <pid>

Parameter Confirmation

The following parameters can be configured by users or integrators:

• --feedbacks-dir: Path for storing feedbacks, default is .vod/feedbacks/.
• --atomgit-home / ATOMCODE_HOME: AtomGit-GO configuration directory, default ~/.atomcode.
• delivery.channels.gitcode.repo_url: Target repository URL — read only from assets/config.yaml.
• capture.dedup_window_sec: In-session deduplication window in seconds.
• storage.max_feedbacks_per_session: Maximum stored feedbacks per session (default 5).
• Logging/Debug: Optional flags inside scripts to enable additional logging or debug modes.

Before delivery or auto-login, ensure the repo_url is provided via assets/config.yaml and is not inferred from git remote.

References

See additional implementation details and integration guides in the repository:

• references/hooks-setup.md
• references/openclaw-integration.md
• assets/VOD_FEEDBACKS.md
• assets/VOD_ISSUE.md
• references/acceptance-criteria.md

Prerequisites

Python dependencies

Install required Python packages before running any scripts:

pip install -r <SKILL_DIR>/requirements.txt

Workflow

Phase 1: Capture

Triggered by hooks (tool errors, user rejection, proactive reports). Generates raw feedback.

1.1 Generate Raw Feedback

• Write the feedback file — python <SKILL_DIR>/scripts/md_io.py write-feedback --output .vod/feedbacks/ (see --help for all params)
• Sanitize — secrets are redacted automatically by write-feedback. To manually sanitize an existing file: python <SKILL_DIR>/scripts/vod_sanitize.py file --path <file>

1.2 Deduplication

• In-session (during write): Same session_id + command + error_type within capture.dedup_window_sec → increment recurrence_count instead of writing a new file.
• Cross-session (before Phase 3 delivery): Scan 10 recent feedbacks via LLM for duplicates.

Phase 2: Extract

Note: This phase is executed by the Agent (LLM) directly — there is no independent extraction script. The Agent enriches the feedback file using write-feedback to update fields.

Enrich feedback with context using LLM, then write all fields directly into the feedback file.

Each field maps to a specific section in the markdown file:

• `error_stack` — Extract traceback/exit code from error context → ## Error Information → error_stack
• `user_intent` — What the user wanted to do (e.g. "create OBS bucket"), NOT how → ## Context → user_intent
• `scenario` — Reconstruct what the user was doing → ## User Report → scenario
• `expected_behavior` — What the user expected. From dialog if explicit, otherwise infer from error → ## User Report → expected_behavior
• `product_name` — Priority: annotation > agent_action > error_message → Title prefix 【Product】
• `environment` — Platform, OS, session ID, Python version → ## Context → environment
• `dialog_context` — 3-5 key turns around the problem point, preserve original language → ## Context → dialog_context

Use write-feedback again to update fields, or edit the markdown file directly.

Phase 3: Deliver

3.1 Sync to GitCode Issue

⚠️ repo_url comes only from assets/config.yaml → delivery.channels.gitcode.repo_url. Never use git remote, never ask the user.

Single delivery — submit one feedback as a GitCode Issue:

python <SKILL_DIR>/scripts/vod_deliver.py deliver \
  --feedback-id <id> \
  --feedbacks-dir .vod/feedbacks

Update status — mark a feedback as delivered (or other status):

python <SKILL_DIR>/scripts/vod_deliver.py update-status \
  --feedback-id <id> --status delivered --feedbacks-dir .vod/feedbacks

Auto-login — when deliver returns "need_login": true, perform the following:

CRITICAL: Before installation, MUST tell the user:

• This login uses the open-source project AtomGit-GO (MIT license).
• Source: https://gitcode.com/weixin_45218422/AtomGit-GO

1. Check & install: Execute bash <SKILL_DIR>/scripts/vod_install.sh (Linux/macOS) or powershell <SKILL_DIR>/scripts/vod_install.ps1 (Windows).

1. Start server: python <SKILL_DIR>/scripts/vod_deliver.py server-start → get pid from JSON output

1. Initiate QR login: curl -s -X POST http://localhost:8080/login/start → get login_url, qr_code, session_id from JSON

1. Show QR to user: Display the login_url and ASCII qr_code. Say: "🔐 First-time login requires AtomGit authorization. Scan the QR code or open the URL in your browser."

1. Wait for authorization: python <SKILL_DIR>/scripts/vod_deliver.py login-wait --session-id <session_id> — blocks until scanned (up to 60s). Do NOT ask the user whether they scanned; just wait.

1. On SCAN_SUCCESS, proceed to step 7.

CRITICAL: After successful authorization, MUST output the Security Notice:

• Security Notice: After authorization, the access token will be saved to ~/.atomcode/auth.toml (owner-readable only, mode 0600). Anyone with file access can impersonate you — do not share this file.
• Note: Stored only in the local AI Shell environment. It will not be uploaded to any external server.
• Deletion: Manually delete the file, or it will be cleaned up when the environment resources are reclaimed.

1. Stop server: python <SKILL_DIR>/scripts/vod_deliver.py server-stop --pid <pid>

1. Re-run the original deliver command.

Behavioral Constraints

• Cancel: Clean up current file only. Never delete .vod/ or other records.