phuetz/code-buddy/pubcommander-control

Claude Code and agent skill by phuetz/code-buddy

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Pilot PubCommander editorial and social campaigns through its MCP tools. Use for listing, drafting, revising, submitting, scheduling, or publishing posts while preserving human approval and dry-run safety.

Install

npx vskill@latest install phuetz/code-buddy/pubcommander-control

SKILL.md

PubCommander Control

Use the PubCommander MCP server as the system of record for social posts. Keep creation reversible and require an explicit human decision before any external publication.

Safe workflow

  1. Inspect existing work with list_posts, then use get_post before changing a specific post.
  2. Create with create_draft_post or revise an eligible post with update_draft_post.
  3. Show the final content, platform variants, hashtags, and targets to the user.
  4. Call submit_post_for_approval; do not interpret submission as approval.
  5. After PubCommander reports the post as approved, validate scheduling or publication with dryRun: true.
  6. Call schedule_post or publish_post with dryRun: false only after the user explicitly confirms that exact action and targets.
  7. Report the returned status and proof. Never claim publication succeeded without a successful tool result.

Guardrails

  • Never invent a postId; obtain it from PubCommander.
  • Never pass or request a user identity through tool arguments. The MCP server binds operations to its configured service user.
  • Treat schedule_post and publish_post as external side effects even if content was already approved.
  • Approval is state held by PubCommander, not a phrase inferred from conversation.
  • If a live action fails, preserve the draft and report the platform-level error; do not retry repeatedly without diagnosis.
  • Prefer platform-specific variants when the audience or format differs. Keep the shared draft as the canonical intent.

Common requests

  • “Prépare trois variantes LinkedIn et Instagram” → create or update a draft, then present it for review.
  • “Envoie-le en validation” → call submit_post_for_approval; stop before scheduling or publishing.
  • “Publie maintenant” → inspect status, run a dry run, request explicit confirmation if not already given for this exact live action, then publish and return the proof.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/phuetz/code-buddy/pubcommander-control/badge)](https://verified-skill.com/skills/phuetz/code-buddy/pubcommander-control)

Something wrong with this skill or its page? Tell us.