maxqian888/cognia-next/plugin-conversion

Claude Code and agent skill by maxqian888/cognia-next

Trust tier 2
  • community
LLM review pending
Source check pending

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

Inspect and deterministically convert complete plugin bundles between supported ecosystems.

Install

npx vskill@latest install maxqian888/cognia-next/plugin-conversion

SKILL.md

Use Cognia's typed conversion tools; do not recreate converted manifests or runtime files yourself.

This skill is explicit-only. Loading its instructions does not authorize an apply: the host owns workspace confinement, plan freshness, output-directory checks, and the desktop confirmation before writes.

Inspect before writing

  1. Resolve the source plugin directory relative to the active workspace and the requested target: cognia, claude-code, codex, gemini-cli, agent-plugins, cursor, copilot, kimi, devin, opencode, pi, factory-droid, qoder, codebuddy, auggie, or open-plugins.
  2. Call plugin_conversion_inspect with the intended surface (cli, desktop, or cloud).
  3. Report the detected source format, fidelity, per-capability delivery outcomes, warnings, and blocking issues. Distinguish a native package from Cognia-hosted tools and identify capabilities retained in Cognia.
  4. If applicable is false or blocking is non-empty, stop. Explain the unsupported behavior; do not approximate or drop it.

Foreign → foreign conversion passes through Cognia's canonical representation. Support depends on each contribution and target, not just the manifest format. Unsupported invocation controls, hooks, agents, runtime code, and configuration semantics block conversion. A generated package is not evidence of an installed or authenticated host; cloud delivery remains unverified. A Cognia-hosted tool alternative requires an enabled plugin in a supported Cognia external-agent session and is not a standalone export.

Apply the inspected plan

Only call plugin_conversion_apply with the exact planId returned by the latest inspection. Use a new or empty output directory relative to the active workspace. If the report contains warnings, explain them and pass acknowledgeWarnings: true only after the user accepts them. The user will receive a desktop confirmation before files are written.

Treat these errors as safety signals:

  • Source changed or plan expired: inspect again and review the new report.
  • Output is non-empty: choose another empty directory; do not delete or overwrite existing work.
  • Source and output overlap: choose a separate sibling directory.

After a successful apply, report the plugin id, target format, output directory, written files, and remaining warnings. Never hand-edit the deterministic conversion output as part of the conversion step.

Security

  • Security scanPassed, 96 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

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

Source

Popularity

Repository stars
7
Repository forks
1
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. 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/maxqian888/cognia-next/plugin-conversion/badge)](https://verified-skill.com/skills/maxqian888/cognia-next/plugin-conversion)

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