ワンクリックで
create-invoke-task
Create a new Python invoke task for the dda CLI
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Create a new Python invoke task for the dda CLI
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generate the Agent Supply Chain newsletter by researching team activity on GitHub and Confluence, then creating a Confluence draft and Gmail draft
Give your AI agents something more useful than a prompt. Velocity through clarity.
Extract an Allium specification from an existing codebase. Use when the user has existing code and wants to distil behaviour into a spec, reverse engineer a specification from implementation, generate a spec from code, turn implementation into a behavioural specification, or document what a codebase does in Allium terms.
Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help shaping it into a specification.
Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.
Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge
| name | create-invoke-task |
| description | Create a new Python invoke task for the dda CLI |
| allowed-tools | Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion |
| argument-hint | [namespace] [task-name] |
| model | sonnet |
Create a new invoke task accessible via dda inv <namespace>.<task-name>.
Use AskUserQuestion to collect the following. If $ARGUMENTS provides values, skip those questions.
Task name: The function name (e.g. build, refresh_assets). Underscores become hyphens in the CLI.
Namespace: Which task module does it belong to?
tasks/ (e.g. agent, linter, dogstatsd). Check tasks/__init__.py for the full list.tasks/<name>.py file and register it.What does the task do?: Brief description (becomes the docstring / help text).
Parameters: What CLI flags does the task need? (name, type, default value, description)
Read an existing task file matching the desired complexity:
tasks/auth.pytasks/agent.py or tasks/linter.pytasks/__init__.py — to see how modules and tasks are registeredAdd the @task decorated function to the appropriate file. Follow the patterns from Step 2.
Key rules:
ctx (the invoke Context)ctx.run("command") to execute shell commandsdda inv --listinvoke: task, Exit (for errors), ContextIf you created a new module file, edit tasks/__init__.py:
from tasks import (...) block (alphabetical order)ns.add_collection(<module>) — creates dda inv <module>.<task>ns.add_task(<task>) — creates dda inv <task>If adding to an existing module, no registration is needed — invoke auto-discovers @task functions.
Test the task:
dda inv <namespace>.<task-name> --help
/create-invoke-task — Interactive: prompts for all details/create-invoke-task agent my-task — Pre-fills namespace and name