agentleFS
Sign inStart free
blu3moblu3mo/gtd-cosense/skills/gtd-engage/SKILL.md

gtd-engage

Skill0 starsChanged 5 months agoMITView on GitHub

Help the user pick what to actually do right now from their GTD system. Use when they ask "何やろう", "次何すればいい", "今の時間で何ができる", "手が空いた", or want to choose a task. Reads the Cosense inbox and recommends the best next action by Allen's four criteria — context, then time, then energy, then priority. Part of the gtd skill bundle.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If nothing fits the current context/time/energy, say so honestly and offer the real options — a quick 2-minute sweep, a [someday] glance, …

    line 39
  2. Very specific:

    If the panel is mostly items without a next:, the bottleneck is clarifying, not choosing → suggest a short gtd-clarify pass first.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

gtd-engage — pick the right next action now

The hard thinking already happened in clarify. Engaging is just choosing well from what's already decided — "minute-to-minute you don't have time to think; you need to have already thought." Keep this fast: the win is a confident 「これやる」 in a few seconds, not an optimization essay.

Do this

  1. Load the ready actions: python3 ~/.claude/skills/gtd/scripts/gtd_cosense.py show (the 🗂 整理済み zone). Read it with understanding — the candidates are the next: lines, but a human note beside one ("これ急ぎ") is real signal too. Ignore waiting: items and things with no next action (those need clarify — mention it if there are many). If the moment is time-bound, glance at today's Google Calendar (MCP list_events) so you don't step on a fixed commitment.
  2. Get the three filters — ask briefly, or infer from what the user already said:
    • Context 「今どこ？何が使える？」(PC前 / 外 / 電話だけ / 移動中) — this filters hardest.
    • Time 「どれくらい時間ある？」(5分 / 30分 / 2時間)
    • Energy 「頭は冴えてる？軽めがいい？」
  3. Apply the four criteria in order — context → time → energy → priority. Priority is an intuitive read against the whole visible list, not a rigid pre-assigned code.
  4. Recommend 1–3 candidates, each as its concrete next:, which project it moves, and why it fits now (「PC前・30分・元気あり → これが一番効く」). Let the user choose; don't force one.
  5. Set them up to start: offer to open the project page for context (python3 ~/.claude/skills/gtd/scripts/gtd_cosense.py raw browsePage <projectUrl>/<title>).

Notes

  • If nothing fits the current context/time/energy, say so honestly and offer the real options — a quick 2-minute sweep, a [someday] glance, or just resting. Don't manufacture busywork.
  • If the panel is mostly items without a next:, the bottleneck is clarifying, not choosing → suggest a short gtd-clarify pass first.
  • Whatever is genuinely most on the user's mind is legitimately Job One — if one thing is pulling at them, help them do that; don't moralize about theoretical priority.

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.

Check your setup, free