agentleFS
Aias00Aias00/agent-skills/tencent-dev-community-publisher/SKILL.md

tencent-dev-community-publisher

Skill2 starsChanged 8 months agoApache-2.0View on GitHub

Publish articles to Tencent Developer Community (腾讯开发者社区) with persistent login. Supports pre-flight checks, one-time auth setup, EXTEND.md preferences, and browser automation for title/content/cover/publish workflow.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no file exists and user wants stable defaults, follow: references/config/first-time-setup.md

    line 42
  2. Very specific:

    Every article must select the existing platform tag 腾讯云架构师技术同盟 (displayed as #腾讯云架构师技术同盟).

    line 109
  3. Very specific:

    When --content is a Markdown file that contains local image references like !图, the publisher now uploads those body images in order and …

    line 110
  4. Very specific:

    If --cover points to the same image as the first Markdown image, the body insertion step skips that duplicate and keeps it only as cover.

    line 111
  5. Distinctive:

    if failed: failed phase + retry command

    line 142

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tencent Developer Community Publisher

Language

Match the user's language for prompts, commands, and completion reports.

Script Directory

Resolve this file's directory as SKILL_DIR, then run scripts via:

python ${SKILL_DIR}/scripts/run.py <script.py> [args...]
ScriptPurpose
scripts/check_permissions.pyPre-flight checks
scripts/auth_manager.pyLogin setup/status/validate/clear
scripts/publisher.pyArticle publish automation
scripts/extend_config.pyEXTEND.md preference loading

When to Use

Trigger this skill when user asks to:

  • publish article to Tencent Developer Community / 腾讯开发者社区
  • setup or fix Tencent community login session
  • automate title/content/cover filling on cloud.tencent.com/developer/article/write

Preferences (EXTEND.md)

Load optional preferences in this order:

  1. Project-level: .baoyu-skills/tencent-dev-community-publisher/EXTEND.md
  2. User-level: ~/.baoyu-skills/tencent-dev-community-publisher/EXTEND.md

If no file exists and user wants stable defaults, follow: references/config/first-time-setup.md

Supported keys:

  • default_headless
  • default_no_cover
  • default_raw
  • default_debug_screenshots
  • default_wait_seconds
  • default_login_timeout_minutes
  • default_auth_headless

Boolean accepts: 1/0, true/false, yes/no.

Priority for publish/auth options:

  1. CLI args
  2. EXTEND.md
  3. Script defaults

Workflow

Tencent Community Publishing Progress:
- [ ] Step 0: Load EXTEND.md preferences
- [ ] Step 1: Run pre-flight checks
- [ ] Step 2: Ensure authentication is valid
- [ ] Step 3: Resolve publish params (title/content/cover)
- [ ] Step 4: Select #腾讯云架构师技术同盟 and execute publish flow
- [ ] Step 5: Report result and next actions

Step 1: Pre-flight checks

python ${SKILL_DIR}/scripts/run.py check_permissions.py

Step 2: Authentication

First-time login:

python ${SKILL_DIR}/scripts/run.py auth_manager.py setup

Management commands:

python ${SKILL_DIR}/scripts/run.py auth_manager.py status
python ${SKILL_DIR}/scripts/run.py auth_manager.py validate
python ${SKILL_DIR}/scripts/run.py auth_manager.py clear
python ${SKILL_DIR}/scripts/run.py auth_manager.py reauth

Step 3: Resolve publish params

Reference: references/article-posting.md

Rules:

  • --title is strongly recommended.
  • --content accepts file path or inline text.
  • --cover is optional.
  • --no-cover can force no-cover mode.
  • Every article must select the existing platform tag 腾讯云架构师技术同盟 (displayed as #腾讯云架构师技术同盟). Do not submit if the selected tag cannot be verified.
  • When --content is a Markdown file that contains local image references like ![图](images/01.jpg), the publisher now uploads those body images in order and inserts them into the editor.
  • If --cover points to the same image as the first Markdown image, the body insertion step skips that duplicate and keeps it only as cover.

Step 4: Publish

Standard:

python ${SKILL_DIR}/scripts/run.py publisher.py --title "标题" --content article.md

Headless:

python ${SKILL_DIR}/scripts/run.py publisher.py --title "标题" --content article.md --headless

Debug mode:

python ${SKILL_DIR}/scripts/run.py publisher.py --title "标题" --content article.md --debug-screenshots --wait-seconds 30

Step 5: Completion report

Report should include:

  • input type/path
  • resolved options (headless, no_cover, raw)
  • auth state (existing/new login)
  • publish result (success/failure)
  • selected tag (#腾讯云架构师技术同盟)
  • if failed: failed phase + retry command

Review stage note

Publishing succeeds when the page shows 发布成功/提交成功/审核中 text. That is the sole success signal — the publisher does not open the article list afterwards. Newly published articles enter platform review and may not appear in the user's article list for a while; this is expected and is NOT a publish failure. Do not retry publishing and do not poll the article list to "verify".

Security Notes

  • run.py prevents path traversal and only executes scripts in scripts/.
  • Auth state is stored in skill-local data/.
  • Debug screenshots are off by default and created only when enabled.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.