本文へ移動
cccskills
無料GitHub で公開

plan

Plan work using Mighty (mt) by creating/updating specs and recording decisions, then spawning/structuring implementation tasks. Use when asked to plan/outline/break down a change, draft a spec (feature/rule/invariant/bug), record an ADR-style decision, or turn a fuzzy request into a structured Mighty spec tree with linked tasks.

インストール方法を見る

含まれるファイル(15)

  • SKILL.md3.8 KB
  • references/decision-template.md382 B
  • references/examples.md737 B
  • references/examples/decision.md1.3 KB
  • references/examples/spec-agent.md1.0 KB
  • references/examples/spec-api.md2.1 KB
  • references/examples/spec-data.md981 B
  • references/examples/spec-infra.md1.1 KB
  • references/examples/spec-product.md1.1 KB
  • references/examples/spec-rule.md967 B
  • references/examples/spec-ui.md1.6 KB
  • references/examples/task.md1016 B
  • references/mt-command-patterns.md1.8 KB
  • references/spec-template.md2.0 KB
  • references/task-template.md397 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Plan

Overview

Create or update Mighty specs and decisions that explain what should change and why, then create linked Mighty tasks for execution.

Progressive disclosure rules

  • Assume mt prime has already been run for this session; only run it if you’re missing mt conventions/context.
  • Prefer the smallest artifact that preserves intent:
    • Update an existing spec/task/decision if it already captures the intent.
    • Create a new spec only when there isn’t a suitable one.
    • Create a decision only when you’re choosing between alternatives or setting a lasting constraint.
  • Keep descriptions short, structured, and link out via citations; avoid walls of text.

1) Pull current context (docs + graph + code)

  • If there’s a docs/ tree, run tree docs | head -n 200 and skim the relevant indices before proposing changes.
  • Search the Mighty graph before grepping code:
    • mt search <keyword>
    • mt tree / mt tree <spec-id>
    • mt show <id>
  • Then inspect code paths with rg and open only the files needed to avoid guessing.

2) Create or update the spec(s)

  • Use the unified spec template (references/spec-template.md) for all specs — parent and leaf alike. Detail level is a property of tree depth, not template structure.
  • Structure specs with Guarantees (everything the system promises) and Constraints (everything the system prevents).
  • Include ALL deliberate choices as guarantees — capabilities, visual treatments, spatial layout, data properties. Specs are the authoring surface; code is the compiled artifact.
  • Use citation links when referencing other entities: [Title](cite:<id_prefix>-spec-...) (always include link text).
  • For a large effort, create a parent spec and add child specs using --parent. Each level refines the parent's commitments into more specific detail.

Use the template in:

  • references/spec-template.md (unified, used at every tree level)
  • For examples, open references/examples.md to find the right domain file, then open only that file (e.g., references/examples/spec-ui.md for UI work).

3) Record decisions (ADR-style)

Use mt decision new when you choose between alternatives or set constraints the code must follow.

Template: references/decision-template.md

  • For example decision text, open references/examples/decision.md.

4) Spawn execution tasks from the spec(s)

  • Create implementation tasks with mt task new --source <spec-or-decision-id> so the graph tracks provenance.
  • Each task should have acceptance criteria and clear scope boundaries.

Template: references/task-template.md

  • For example task text, open references/examples/task.md.

5) Link structure and evidence

  • Link children to parents via mt new --parent <spec-id> (preferred at creation time).
  • Add explicit edges when helpful:
    • Parent/child: mt link --from <child-spec> --rel child_of --to-spec <parent-spec>
    • Evidence: mt link --from <spec-or-task> --rel implemented_by --to-type file --to-ref <path>

6) Sync planning artifacts

Run mt commit to commit .mighty changes.

Reference templates

  • Spec structure: references/spec-template.md (unified — same template at every tree level)
  • Decision structure: references/decision-template.md
  • Task structure: references/task-template.md
  • mt shell patterns: references/mt-command-patterns.md
  • Examples index: references/examples.md (points to domain-specific files in references/examples/)

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Optimize a pydantic-ai agent's instructions, tool descriptions, output type, and signature inputs using the gepa CLI. Trigger when the user asks to "optimize this agent", "improve tool descriptions", iterate on prompts driven by eval failures, or otherwise improve a pydantic-ai agent against a dataset. Operates in the user's repo with full filesystem access — YOU are the reflection model; the gepa CLI handles minibatches, evaluation, and Pareto bookkeeping.

日本語の概要は準備中です。原文の説明を表示しています。

indexedlabs/pydantic-ai-gepa362026年10月7日 更新

mighty

無料

Use the `mt` tool to work with this repo’s Mighty graph: run `mt prime` at session start; prefer `mt search`/`mt tree`/`mt show` before reading code; create specs/decisions/tasks and link evidence; triage `mt inbox`; and close out with `mt closeout` then `mt commit`. For full workflow + templates, run `mt prime`.

日本語の概要は準備中です。原文の説明を表示しています。

indexedlabs/pydantic-ai-gepa362026年10月7日 更新

Resolve `.mighty/loro/*.loro` merge conflicts safely using `mt merge`, then verify store health and sync.

日本語の概要は準備中です。原文の説明を表示しています。

indexedlabs/pydantic-ai-gepa362026年10月7日 更新

Convert roman numerals to integers.

日本語の概要は準備中です。原文の説明を表示しています。

indexedlabs/pydantic-ai-gepa362026年10月7日 更新

Audit and migrate specs to the Guarantees + Constraints format. Use when asked to review spec quality, find non-conforming specs, or batch-migrate specs from the old Behaviors/Interfaces format.

日本語の概要は準備中です。原文の説明を表示しています。

indexedlabs/pydantic-ai-gepa362026年10月7日 更新

tasks

無料

Track and execute implementation work using Mighty (mt) tasks, with progress comments, linked evidence, recorded decisions, and clean closeout. Use when asked to fix a bug, implement a feature/refactor, or “work through” changes in code while keeping Mighty tasks/specs/decisions updated.

日本語の概要は準備中です。原文の説明を表示しています。

indexedlabs/pydantic-ai-gepa362026年10月7日 更新

indexedlabs のスキルをすべて見る

このスキルの問題を報告する