mjasnikovs

Pi Task — Testing skill for Claude Code

Testing community

Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fetch worker tools.

How to install Pi Task

This entry records only its repository, not the path inside it, so there is no exact command to give. Open mjasnikovs/pi-task and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Pi Task does

Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fetch worker tools.

Alternatives in Testing

Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
Add Plugin — Integrate a spec-driven/skill framework as a bundled agtx plugin 1.5k ★
Grill — Sharpen a fuzzy idea into §G/§C before spec 1.1k ★

README

![pi-task — Deterministic Local AI Workflows. Every request runs a fixed pipeline: refine to clarify and structure it, research to gather information in parallel, grill to cross-examine the findings, compose to write the implementation spec, critique to check it for quality and completeness.](https://raw.githubusercontent.com/mjasnikovs/pi-task/main/assets/hero.svg)

pi-task

**Deterministic spec-orchestration for local models — with bundled web, docs, fetch, and worker sub-agent tools.**

[![npm](https://img.shields.io/npm/v/@mjasnikovs/pi-task?color=cb3837&logo=npm)](https://www.npmjs.com/package/@mjasnikovs/pi-task) [![license](https://img.shields.io/badge/license-AGPL--3.0-blue.svg)](./LICENSE) [![pi extension](https://img.shields.io/badge/pi-extension-7c3aed)](https://www.npmjs.com/package/@earendil-works/pi-coding-agent) [![tests](https://img.shields.io/badge/tests-4631%20passing-3fb950)](#development) [![types](https://img.shields.io/badge/TypeScript-strict-3178c6?logo=typescript&logoColor=white)](./tsconfig.json)

What it does

Local models drift. Ask one to plan a non-trivial change and it skips context, hallucinates APIs, and forgets what you actually asked. `pi-task` fixes this by **not trusting a single prompt** — it drives your request through a fixed, persisted pipeline of small, verifiable steps (shown above), then hands the main session a clean spec to execute.

Every phase boundary is written to `.pi-tasks/TASK_NNNN.md`, so a task survives a crash, a restart, or a `/task-cancel` — pick it back up with `/task-resume`.

Why it's different

Deterministic by construction. The phase order is fixed code, not a model's free choice. The orchestrator loops over a config table; each phase has one job and one output section.
Parallel research, focused output. The research phase fans out to isolated child agents — one indexing project files, others digging into APIs, context, and tooling — and **verifies to