patforna/auto-task

An opinionated agentic workflow to turn well-defined units of work into shippable code with minimal human input.

3Stars on the repository
16Mods indexed here, across every type
13d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

auto-task

01

patforna/auto-task

Skill Claude CodeCodex

use to drive a well-defined task end-to-end with minimal human input: plan, implement, review, ship.

3 13d ago A 26 tokens original MIT

clarify-task

02

patforna/auto-task

Skill Claude CodeCodex

Use this skill to resolve ambiguities, clarify vague criteria and make implicit assumptions explicit. Invoked at the end of /at:create-task and the start of /at:plan-task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

3 13d ago A 65 tokens original MIT

config

03

patforna/auto-task

Skill Claude CodeCodex

Use this skill to resolve auto-task settings. It owns the procedure that merges the shipped defaults file with project and local config, per-leaf, plus the resolved-block contract consumers read. Run it standalone to inspect the resolved settings and where each value came from.

3 13d ago A 54 tokens original MIT

create-task

04

patforna/auto-task

Skill Claude CodeCodex

Use this skill to crystallise and scope an ongoing conversation into a well-defined task, capturing user intent at a high level. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

3 13d ago A 52 tokens original MIT

impl-task

05

patforna/auto-task

Skill Claude CodeCodex

Implement a task by executing its implementation plan. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

3 13d ago A 36 tokens original MIT

panel

06

patforna/auto-task

Skill Claude CodeCodex

Use to get independent perspectives on a topic from multiple models (a strong Claude model + Codex by default). Use with /at:synthesize to merge.

3 13d ago A 33 tokens original MIT

plan-task

07

patforna/auto-task

Skill Claude CodeCodex

Write an implementation plan for a well-defined task. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

3 13d ago A 37 tokens original MIT

review-code

08

patforna/auto-task

Skill Claude CodeCodex

Use to review a diff for correctness, design, security, and convention conformance. High-signal, read-only, severity-gated, with an autofix lane for mechanically-certain trivia. Default review step in /at:auto-task.

3 13d ago C 51 tokens original MIT

review-design

09

patforna/auto-task

Skill Claude CodeCodex

Use to review a design / UI change against its specification. Read-only; produces findings, applies no fixes.

3 13d ago A 25 tokens original MIT

review-task

10

patforna/auto-task

Skill Claude CodeCodex

Verify that a task has been completed according to its intent and criteria. Typical workflow: create-task → clarify-task → plan-task → impl-task → review-code → review-task → ship-task.

3 13d ago A 41 tokens original MIT

ship-task

11

patforna/auto-task

Skill Claude CodeCodex

Use to wrap up a finished task - set status to done, merge, clean up.

3 13d ago A 21 tokens original MIT

synthesize

12

patforna/auto-task

Skill Claude CodeCodex

use to combine N independent perspectives on a prompt into a single synthesis without forcing consensus.

3 13d ago A 20 tokens original MIT

tdd

13

patforna/auto-task

Skill Claude CodeCodex

Strict test-driven development (Beck-style). Use when writing new code, adding features, or fixing bugs with TDD discipline. TRIGGER when: user asks to use TDD, write tests first, or red/green/refactor. DO NOT TRIGGER when: writing tests after the fact, or user explicitly opts out of TDD.

3 13d ago A 72 tokens original MIT