repo-harness-product

Solid

Canonical rule owner for PRD drafting, Sprint planning/execution, and native Goal-session preparation from repo-harness planning artifacts.

AI & Automation 397 stars 27 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 90/100

Stars 20%
87
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
63
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# repo-harness-product Canonical rule owner for PRD, Sprint, and Goal. Router-only: shared preflight, mode selection, and cross-mode boundaries. Mode protocol lives under `references/`. ## Shared Preflight 1. Confirm the working repo with `git rev-parse --show-toplevel`. 2. Read `docs/spec.md` and `.ai/harness/policy.json` when present. ## Mode Selection - A product idea needs an upper-layer PRD -> `references/prd.md`. - A PRD or spec needs an ordered Sprint backlog, or a Sprint task needs to run or report status -> `references/sprint.md`. - A detailed PRD/Sprint needs a bounded native `/goal` session -> `references/goal.md`. ## Boundaries - Approval gating: no mode sets `> **Status**: Approved`, or bypasses `$think`, `repo-harness run capture-plan`, task contracts, `/check`, or external acceptance on the user's behalf; explicit human approval always precedes implementation. - `tasks/todos.md` is the deferred-goal ledger only; no mode treats it as an active backlog or goal queue. - Product planning does not install or imply ChatGPT; ChatGPT surfaces are discovered only through their own explicit setup. - None of these modes implements backlog tasks itself; work flows through the existing plan -> contract -> worktree -> verify gates.

Details

Author
Ancienttwo
Repository
Ancienttwo/repo-harness
Created
4 months ago
Last Updated
yesterday
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category