71건 · 관련도순
Turn the selected specification into a maintained implementation plan with clear outcomes, useful tasks, dependencies, and verification steps. Drafting uses the existing authorization and does not require artifact approval codes, reviewer receipts, or a frozen implementation script.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit. Never on the default path; it does not bypass a gate or finish per unit.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build an authorized feature from a maintained specification, testable criteria and useful plan, without duplicating user approval.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Develop greenfield context from a durable interview and initialize it through the native context writer.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build source-backed project context through bounded inspection, optional agents, and safe selected writes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or $ca-feature.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Restructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Inspect architectural variances with SMARTS; record only explicit user choices. Report-only requests make no changes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Scope arbitration — resolve disagreements between product and engineering on what is in or out of scope, with a decision log and escalation path. Use when asked to "resolve this scope disagreement", "arbitrate between product and eng", "scope is creeping", "we can't agree on what's in scope", or "help us decide what to cut".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Coordinates staged or parallel jobs across live-verified coding-agent runtimes (Claude Code, Codex, Cursor, and other installed CLIs) and in-session toolkit subagents. Routes each job by capability and risk tier, isolates parallel writers in git worktrees, captures redacted output, resumes interrupted runs, and blocks completion until an independent arbiter verifies the results. Use when work should be split across multiple runtimes or subagents, run as staged or parallel jobs, and reviewed before handoff. NOT for a single-agent task or the in-session 7-phase flow (use mk:cook / mk:workflow-orchestrator).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create a coding bounty that locks ERC20 token rewards for making a failing test suite pass. The skill checks CLI configuration, gathers the repository, commit, reward, and arbitration details, then reports the escrow identifier and solution submission command.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Compare competing plans from AI agents against the actual task and available evidence. Choose one, combine useful parts, or request revisions, then produce a single execution handoff with ordered steps, verification checks, and reasons for rejected alternatives.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Report the compatibility redirect to `ap-independent-checker`; this retired role cannot perform new work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of ~4 extra LLM turns.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.