Front-loads gap discovery before /grill-me by adding two skills:
research MOSTLY fans out Explore + WebSearch agents in parallel,
synthesizes findings into a brief, names open
unknowns explicitly (which become /prototype targets)
prototype MOSTLY builds a throwaway spike to test ONE falsifiable
assumption; code lives in .prototypes/ (gitignored),
never promoted; output is evidence — verdict, numbers,
observed behavior — that feeds /prd
Full chain now:
/research → /prototype → /grill-me → /prd → /prd-to-issues → /ship-it
Chain rationale: /research and /prototype surface knowledge gaps and falsify
risky assumptions while the cost of changing direction is still cheap; the
TOGETHER phases (grill-me, prd) lock down the contract; the AFK phase
(ship-it) only executes against contracts already on paper.
The chain is a default, not a mandate — README covers when to skip
upstream skills for small or stack-familiar work.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Four workflow skills that take a feature from fuzzy idea to merged code.
Two human-in-the-loop phases (grill-me, prd), one mostly-together (prd-to-issues
files only on explicit 'create'), and one AFK (ship-it).
grill-me TOGETHER pressure-test the idea with hard interview questions
prd TOGETHER synthesize PRD; gaps stay explicit, not papered over
prd-to-issues MOSTLY thin vertical-slice issues with coverage matrix +
per-issue Slice check; self-audits before showing
ship-it AFK shell loop ships each slice end-to-end with one
commit per issue, status streams to terminal,
Ctrl-C-able, survives session close
Vertical-slice principle throughout: every issue cuts end-to-end through every
integration layer (no horizontal "do all the DB work first" issues). The
AFK loop only ships against acceptance criteria already locked in by the PRD
phase — autonomous code never runs against undefined contracts.
ship-it tracker support: gh (GitHub) and tea (Gitea). For this repo, set
SHIP_IT_TRUNK=development to override the main default.
See .claude/skills/README.md for the full how-to and a worked example.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Delete .mcp.json + .claude/rules/repo-mem.md; drop .repo-mem from .gitignore
- Remove repo-mem / substrate_score / repo_search references from all .md
- Move 15 EVOLV skills from .agents/skills/ to .claude/skills/ so they are
auto-discovered by the Claude Code harness and invokable via the Skill tool
- Retire .agents/skills/evolv-orchestrator (duplicate of the subagent at
.claude/agents/evolv-orchestrator.md); orchestrator lives as a subagent only
- Drop OpenAI-format agent yaml metadata from each skill (not needed for CC)
- Update CLAUDE.md, CONTRACTS.md, AGENTS.md to point at the new locations and
disambiguate skills (.claude/skills/) vs subagents (.claude/agents/)
- Fix CLAUDE.md tick-loop wording (opt-in per-node, not a fixed 1000ms)
- Widen .claude/rules/ paths frontmatter so node-architecture and telemetry
rules trigger on more relevant files; add frontmatter to flow-layout rule
- Bump CONTRACTS.md review date to 2026-05-19; add step 7 to the contract-
change workflow (review example flows when topic usage changes)
- Bump nodes/generalFunctions pin (Home.md substrate_score reference removed)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
