intellectronica/taking-agents-seriously/process-message

Claude Code and agent skill by intellectronica/taking-agents-seriously

Trust tier 3
  • community
Source check pending

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

Process one inbox message from start to finish using the other mail skills.

Install

npx vskill@latest install intellectronica/taking-agents-seriously/process-message

SKILL.md

Process Message

Use this skill whenever you are asked to process inbox mail.

Goal

Handle exactly one message from inbox/ in a single turn.

Operating assumptions

  • The skill contents are already loaded. Do not browse the skills/ directory to rediscover them.
  • Do not read system-prompt.md.
  • Do not use SQL, todo tracking, or any other bookkeeping that is unrelated to processing the message.
  • Work directly and economically: inspect the next message, classify it, create the required artefacts, archive it, then stop.

Procedure

  1. List the markdown files in inbox/.
  2. Choose the next message to process by filename order.
  3. Read that message carefully.
  4. Apply the classify-message-urgency skill.
  5. Apply the classify-message-importance skill.
  6. Determine which of the four states applies:
  • not urgent and not important
  • important but not urgent
  • urgent but not important
  • urgent and important
  1. If the message is urgent, use the respond-to-message skill to create a reply markdown file in outbox/.
  2. If the message is important, use the create-message-pdf skill to create a PDF version of the original message in important/.
  3. Move the processed original message from inbox/ to archive/.
  4. End the turn with a compact report containing:
  • filename
  • urgency classification
  • importance classification
  • actions taken

Output discipline

  • Process one message only.
  • Do not leave the original in inbox/.
  • Do not skip classification.
  • Do not create a reply for a non-urgent message.
  • Do not create a PDF for a non-important message.
  • Prefer direct action over exploratory commentary.

Security

  • Security scanPassed, 90 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/intellectronica/taking-agents-seriously/process-message/badge)](https://verified-skill.com/skills/intellectronica/taking-agents-seriously/process-message)

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