auto
Run completely AUTONOMOUSLY — loop the FULL task engine over the Beads queue, a fresh `claude -p` per task, until the queue is empty. Same complete recipe as…
MIGRATION (one-time). Import existing markdown task state (Ralph IMPLEMENTATION_PLAN.md, checkbox task lists) into Beads, idempotently. Use when adopting completely in a repo that has markdown plans, or after an upstream update, to keep Beads the single source of truth. Backed
$ npx -y skills add 23ag1/completely --skill sync --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/syncContext preview
The summary Claude sees to decide when to auto-load this skill.
MIGRATION (one-time). Import existing markdown task state (Ralph IMPLEMENTATION_PLAN.md, checkbox task lists) into Beads, idempotently. Use when adopting completely in a repo that has markdown plans, or after an upstream update, to keep Beads the single source of truth. Backed
name: completely:sync description: MIGRATION (one-time). Import existing markdown task state (Ralph IMPLEMENTATION_PLAN.md, checkbox task lists) into Beads, idempotently. Use when adopting completely in a repo that has markdown plans, or after an upstream update, to keep Beads the single source of truth. Backed by `cmpl sync`. version: 0.2.0 user-invocable: true argument-hint: "[dir] [extra-markdown-files...]"
Run the idempotent markdown → Beads migration so the task queue lives in one place.
1. Ensure the repo has Beads — if `.beads/` is absent, run `bd init` first. 2. From the repo root run `cmpl sync` (backend: `<plugin>/scripts/sync.sh`). 3. It upserts each markdown checkbox task into Beads keyed by a stable `source_ref` (label `src-<hash>` + `metadata.source_ref`), so re-running NEVER duplicates and reconciles status (`- [x]` → closed, `- [ ]` → open). Safe to run after upstream updates. 4. Report created/reconciled counts. Then prefer `bd ready` over the markdown checklist.
Scope: Ralph-style `IMPLEMENTATION_PLAN.md` + any files you pass. GSD `*-PLAN.md` (requirements/must_haves/waves) is handled by the GSD→Beads emitter, not this skill.
A quality-first harness for autonomous AI coding agents. It turns "the agent said it's done" into *"here's the proof — graded by an independent, default-FAIL checker."* Done is earned, not asserted.
Repo: 23ag1/completely
Run completely AUTONOMOUSLY — loop the FULL task engine over the Beads queue, a fresh `claude -p` per task, until the queue is empty. Same complete recipe as…
Run all configured quality checks (lint, types, tests) in one pass with terse output — reports "clean" when green, and only the failing check's output when…
Overview and entry point for the completely harness — a quality-first agent workflow unifying GSD (planning depth), Ralph (autonomous loop), and Beads (the…
Run completely UNDER CONTROL — execute the SINGLE next Beads task through the FULL task engine (understand → map → plan-check → parallel subagents → TDD →…
Scaffold the completely thin layer into the current repository — Definition of Done, the harness rules snippet in CLAUDE.md, and an optional project-specific…