currytang/amadeus/project-todo-manager

Claude Code and agent skill by currytang/amadeus

Trust tier 2
  • community
LLM review pending
Source check pending

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

Manage project-management TODO workflows in ResearchOps. Use this skill when a user asks to generate, prioritize, clear, classify, or execute TODO items, or asks what to do next for project management tasks.

Install

npx vskill@latest install currytang/amadeus/project-todo-manager

SKILL.md

Project Todo Manager

Use this skill to answer and execute TODO-related requests against ResearchOps projects.

Workflow

  1. Resolve the target project and fetch current TODO items (OPEN, DONE, COMPLETED, blocked states).
  2. Classify the user request into one action:
  • summarize: show status, blockers, and top priorities.
  • prioritize: reorder open TODOs by urgency, dependency, and execution cost.
  • execute-next: select one actionable TODO and prepare/run the appropriate agent step.
  • clear: bulk-close current open TODOs only when explicitly requested.
  • generate: create TODOs from proposal/instruction text.
  • generate-dsl: request todo-dsl-generator and convert free-form idea/proposal into structured step DSL first.
  1. Keep updates auditable:
  • preserve original TODO text;
  • write concise status transition notes;
  • avoid destructive edits to already completed tasks unless explicitly requested.

Prioritization Rules

  1. Prefer TODOs that unblock downstream steps.
  2. Prefer TODOs with clear acceptance checks and runnable commands.
  3. Defer TODOs requiring missing infra/credentials and mark as blocked with reason.
  4. If two tasks are equivalent, choose lower runtime/cost first.

Output Contract

Always return:

  • selected_action
  • todo_snapshot (open/done counts)
  • next_steps (1-3 concrete commands or API actions)
  • risk_notes (blocking assumptions)
  • when generate-dsl is used: todo_dsl_summary (step count + reference coverage)

References

Read query-playbook for request-to-action mapping examples.

Security

  • Security scanPassed, 100 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

7-day trend score
0

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/currytang/amadeus/project-todo-manager/badge)](https://verified-skill.com/skills/currytang/amadeus/project-todo-manager)

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