mr-onion

Phase 17 — Skills Extraction (Claude Code) Backlog

Version: 1.0 Date: 2026-09-16 Status: Shipped — content built out under Phases 18-21 (skills/README.md, skills/ROADMAP.md are the live source of truth); this doc’s own header was never updated when the work landed. Corrected 2026-09-23 (Cowork verification pass) — see the Sept 22 handover note that first flagged this.

Context

docs/REIMAGINING.md proposed rebuilding TestForge as a set of testing skills for coding agents instead of a standalone app. That proposal was written against main-origin, the pre-Phase-16 codebase (a 4,739-line page.tsx, a 2,226-line run/route.ts, a 2,415-line generate/route.ts, and a FastAPI backend). Phase 16 already deleted the FastAPI backend entirely and decomposed all three of those files — page.tsx is 353 lines with no code editor, run/route.ts is 120 lines, and the actual prompt content already lives on its own in src/lib/generate/prompt.ts (29 lines). The literal “delete ~12,000 lines” reading of the proposal no longer applies to a codebase that’s already been decomposed and is about to ship as test-assist.

What still holds from the proposal, reconciled against Emil’s own answers to Martin’s four questions: TestForge is paused, not abandoned, so this is additive work alongside the app, not a replacement for it (Q1). The prompt + problem statement are worth packaging now, since the prompt is already isolated and more skills are expected to surface as work continues (Q2). Claude Code is the only target for now; portability to Copilot/Cursor is an explicitly deferred follow-up (Q3). Testing is multi-disciplinary — this backlog treats skills/ as a growing set, and no single skill is positioned as the product (Q4).

Scope (this phase)

In scope

  1. A new, additive skills/ directory at the repo root.
  2. One real, working Claude Code skill built from content that’s already isolated in the codebase (the prompt + best-practice guidance).
  3. A roadmap document recording the other candidate skills from REIMAGINING.md as candidates, not commitments.
  4. A spike to check whether Playwright MCP already covers the DOM exploration introspect/crawl currently do, before anyone commits to rebuilding that as a skill.

Out of scope

Backlog

TFP-034 - Package the prompt and problem statement as a Claude Code skill

TFP-035 - Record the multi-skill roadmap before building a second skill

TFP-036 - Spike: does Playwright MCP already cover introspect/crawl?

  1. TFP-034
  2. TFP-035
  3. TFP-036

Suggested Milestone Gates

Gate A - Phase 17 first-skill checkpoint