本文へ移動
cccskills
無料GitHub で公開

tasks

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.

インストール方法を見る

含まれるファイル(5)

  • SKILL.md2.8 KB
  • references/examples.md1.4 KB
  • references/mt-command-patterns.md977 B
  • references/progress-comment-examples.md575 B
  • 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。

Tasks

Overview

Claim (or create) a Mighty task for the work, keep short progress comments as you go, record decisions when you choose between alternatives, then link evidence and close cleanly.

Progressive disclosure rules

  • Assume mt prime has already been run for this session; only run it if you’re missing mt conventions/context.
  • Prefer comments for ephemeral progress and decisions for lasting choices/constraints.
  • Keep comments short and high-signal (1–5 bullets or a few sentences).
  • When referencing specs/decisions/tasks in descriptions/comments, use [label](cite:<id_prefix>-...) (always include link text).

Workflow

0) Start with context (graph first)

Start with:

  • mt work / mt mine to see what’s already assigned.
  • mt search <keyword> and mt tree to find the relevant spec/decision.
  • mt show <id> to read the current intent before changing code.

1) Ensure there is a task for the change

  • If the user provides a task ID, use it.
  • Otherwise create one, linking it to the source spec/decision with --source:
    • Template: references/task-template.md

2) Claim the task (start a session)

mt claim <task-id> --reason "Starting work"

3) While working, leave lightweight breadcrumbs

Use comments for progress checkpoints and “why”:

mt comment <task-id> --content "Observed X. Choosing Y because Z. Next: A then B."

Record design decisions when you pick between alternatives:

  • mt decision new ... --source <task-id> (creates a spawned edge)
  • If you revise an existing decision, use mt decision update ... --reason "..."

Examples: references/progress-comment-examples.md More examples: references/examples.md

4) Link evidence for completed work

When the work is implemented/tested, link evidence (files and/or commits):

mt link --from <task-or-spec-id> --rel implemented_by --to-type file --to-ref path/to/file.py -d "Core implementation"

5) Close the task

mt task close <task-id> --reason "Done" --resolution "What changed and how to verify"

6) Session close protocol (before saying “done”)

Run:

mt closeout
mt commit

If mt closeout indicates missing decisions or evidence, add them before syncing.

Reference templates

  • Task structure: references/task-template.md
  • Progress comment examples: references/progress-comment-examples.md
  • mt shell patterns: references/mt-command-patterns.md
  • Good end-to-end examples: references/examples.md

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

plan

無料

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.

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

indexedlabs のスキルをすべて見る

このスキルの問題を報告する