Skill
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…
@23ag1View SkillTesting
Skill
/check
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 not. Token-frugal; configured via completely.toml [check] or auto-detected per stack (front+back). Use before committing or
Install
$ npx -y skills add 23ag1/completely --skill check --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/check
Context preview
The summary Claude sees to decide when to auto-load this skill.
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 not. Token-frugal; configured via completely.toml [check] or auto-detected per stack (front+back). Use before committing or
SKILL.md
check.SKILL.mdname: completely:check description: 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 not. Token-frugal; configured via completely.toml [check] or auto-detected per stack (front+back). Use before committing or to verify a change. Backed by `cmpl check`. version: 0.3.0 user-invocable: true argument-hint: "[dir]"
Run `cmpl check` from the repo root instead of running lint/types/tests separately (fewer tokens, fixed sequence). It runs every check in `completely.toml [check]`, or auto-detects eslint/tsc/vitest for a frontend and ruff/mypy/pytest for a backend.
- Clean → one line ("clean (N checks)"). A failure → only that check's output tail, not all logs.
- Add a check by editing `completely.toml`, not the script.
Ships withcompletely
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.
Get the whole plugin
Stats
5
Stars
0
Forks
Maintained
Maintenance
Shell
Language
MIT
License
3mo ago
Last commit
3mo ago
Created
Repo: 23ag1/completely
Other skills on completely.
@23ag1View SkillSkill
completely
Overview and entry point for the completely harness — a quality-first agent workflow unifying GSD (planning depth), Ralph (autonomous loop), and Beads (the…
@23ag1View SkillSkill
control
Run completely UNDER CONTROL — execute the SINGLE next Beads task through the FULL task engine (understand → map → plan-check → parallel subagents → TDD →…
@23ag1View SkillSkill
init
Scaffold the completely thin layer into the current repository — Definition of Done, the harness rules snippet in CLAUDE.md, and an optional project-specific…
@23ag1View SkillSkill
plan
Plan a phase or feature DIRECTLY into Beads — no PLAN.md, no markdown bridge. Runs GSD-style socratic discovery + decomposition + a goal-backward self-check,…
@23ag1View Skill