agentleFS
Loffee5422Loffee5422/plan-interview-skill/llms.txt

plan-interview-skill

llms.txt2 starsChanged 2 months agoMITView on GitHub

Canonical repository: https://github.com/Loffee5422/plan-interview-skill Installable latest tree: https://github.com/Loffee5422/plan-interview-skill/tree/main/skills/plan-interview Installable pinned tree: https://github.com/Loffee5422/plan-interview-skill/tree/v1.0.0/skills/plan-interview Entrypoint: skills/plan-interview/SKILL.md Direct install instruction: Install the plan-interview skill from https://github.com/Loffee5422/plan-interview-skill/tree/main/skills/plan-interview License: MIT

  • In this repositoryOne other file it gives its agents.

The file

Files
llms.txt
# Plan Interview Skill

Canonical repository: https://github.com/Loffee5422/plan-interview-skill
Installable latest tree: https://github.com/Loffee5422/plan-interview-skill/tree/main/skills/plan-interview
Installable pinned tree: https://github.com/Loffee5422/plan-interview-skill/tree/v1.0.0/skills/plan-interview
Entrypoint: skills/plan-interview/SKILL.md
Direct install instruction: Install the `plan-interview` skill from https://github.com/Loffee5422/plan-interview-skill/tree/main/skills/plan-interview
License: MIT

## Core facts

- Plan Interview turns a vague goal into a small, actionable project plan.
- It interviews for outcome, hard deadline, current state, available time, and likely obstacle.
- It creates 5–12 verb-first next actions for the next milestone, generally estimated at 15–45 minutes each.
- It includes if–then intentions, an intentionally easy ignition task, and one `next` task per project.
- It displays a draft and requires explicit user approval before any Todoist write.
- It inspects the live Todoist tool schema rather than assuming tool or field names.
- It can return a copy-pasteable plan in chat when Todoist is unavailable.

## Supported uses

- Interviewing a user to clarify a stalled or vague goal.
- Drafting the next milestone of a work, study, or personal project.
- Creating an approved Todoist project through an available Todoist MCP integration.
- Reviewing and re-breaking Todoist tasks that remain untouched.

## Unsupported uses

- Writing to Todoist without explicit approval of the displayed draft and write scope.
- Automatically scheduling tasks that do not have real external deadlines.
- Building a comprehensive long-term backlog in the first pass.
- Treating the workflow as medical or mental-health care.

## Dependencies

- An agent compatible with the Agent Skills `SKILL.md` format.
- For Todoist writes only: an authenticated Todoist MCP integration.

## Important files

- README.md: human-facing overview, installation, examples, FAQ, and limits.
- skills/plan-interview/SKILL.md: complete operational instructions for the agent.
- CHANGELOG.md: release history.
- CONTRIBUTING.md: contribution guidance.
- LICENSE: MIT license text.

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.