Skill Claude CodeCodexCursor
Runs one evidence-driven Vibelution optimization iteration from the ROI backlog: pick one todo item, worktree isolate, implement, machine-verify, merge, update STATE. Use when the user starts /loop for project improvement, continuous optimization, or agent-dev ROI backlog work.
Instructions file CodexOpenCode
Instructions for CCDawn/Vibelution, covering vibelution agent rules, 1. identity and priority, 2. global red lines, 3. start and routing and 3.0 每任务先 router.
Agent
A maintained map of the main path from a user message through the Chat/Coding system to the displayed model response. It documents current code entry points and boundaries for learning and diagnosis.
Agent
This document defines the canonical domain language for Vibelution so architecture work can use stable names for the same concepts. It is intentionally small: add terms when they become load-bearing in design or tests.
Agent
This repository uses GitHub Issues as its source of truth for issues, PRDs, and issue-linked agent work.
Agent
The operational guide for deploying and calling the Vibelution MCP gateway, a service that lets compatible AI hosts discover and use tools. It covers readiness states, registration, resource discovery, and the command used to start the gateway.
Agent
A guide to the project’s callable agents, sessions, and background APIs, along with their access and safety rules. It is a derived index: the actual source of truth is the route and tool registration code.
Agent
This inventory is the Milestone 0 baseline for the unified authorization design. It records where tools become visible to a model and where calls reach executable implementations. It does not change runtime behavior.
Agent
This repository uses the default Matt Pocock triage label vocabulary.
Agent
This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.
Plugin Claude Code
briefbound-skills. Chinese-first Codex skill pack for intent alignment, dynamic routing, lightweight development, code review, UI design, and AI research workflows.
Instructions file CodexOpenCode
Instructions for CCDawn/codex-skills, covering agents, repo rules, slash-command lessons learned, duplicate or missing slash-command checklist and default verification flow.
Instructions file
Instructions for CCDawn/codex-skills: Skills are organized into bucket folders under skills/.
Skill Claude CodeCodex
Use when a Huawei Algorithm Challenge 37 NSLB workspace needs live status, adaptive solver search, comparable evaluation, packaging, or online-score feedback; it is a thin project adapter over briefbound-score-loop.
Skill Claude CodeCodex
Use when repeated work is governed by an explicit metric, active baseline, candidate search, promotion rule, leaderboard feedback, or submission iteration; do not use for a one-off research check that its current owner can execute directly.
Skill Claude CodeCodex
Use when the user wants non-obvious but useful ideas, concept invention, naming, reframing, variation, selection, creative unblocking, or synthesis grounded in the current context.
Skill Claude CodeCodex
Use when the user explicitly enables an automated same-project multi-thread development loop that keeps peer Codex tasks progressing, recovers conflicts or stale coordination, integrates verified work into local main, and closes cleanup without repeated gates; do not use before opt-in, for one-off coordination, remote…
Skill Claude CodeCodex
Use when an already-defined new behavior or high-risk implementation contract needs a failing test before implementation, or the user explicitly requests TDD; diagnosed bugs stay with briefbound-bug-review, while simple or mechanical work uses targeted verification.
Skill Claude CodeCodex
Use when an observed bug, correctness regression, failing test, build failure, abnormal behavior, or unresolved root cause needs Chinese-first diagnosis and bounded repair; obvious local inefficiency found during feature work stays with its owner, while measurable performance work uses…
Skill Claude CodeCodex
Use when active development or explicit refactoring has concrete code-structure risk: a source file is accumulating independently changing responsibilities, a class/component/function is hard to navigate or test, repeated changes touch distant sections, or the user asks to split a giant file; do not use for line count…
Skill Claude CodeCodex
Use when completed work needs formal cross-stage or cross-session synthesis, resumed-task closure, durable handoff evidence, deferred-risk accounting, or an independent PR/release evidence package that the current owner's concise final response cannot represent.
Skill Claude CodeCodex
Use when a frontend task primarily concerns cross-component design tokens, semantic theming, component APIs, variants and states, shared primitives, Storybook or library governance, Figma-to-code consistency, or a staged design-system migration; do not use for a single page, isolated styling fix, visual direction, or…
Skill Claude CodeCodex
Use when a verified or integrated software change has concrete temporary artifacts, generated noise, task-owned background processes or listeners, stale claims, merged local branches, disposable worktrees, or a known PR lifecycle state that requires deferred or post-merge local closeout, or when the user explicitly…
Skill Claude CodeCodex
Use when Briefbound workflow needs a Chinese-first evaluation adapter and no more specific existing skill already owns the review, debugging, PR, planning, feedback, verification, or goal task.