Ccdawn Project Review
Use when CCDawn workflow needs a Chinese-first review of an entire repository, codebase, architecture, technical debt, test coverage, risk modules, maintainability, onboarding state, or project health before planning, refactoring, takeover, or prioritization.
Ccdawn Ui Design
Use when a CCDawn task materially involves UI/UX direction, information hierarchy, interaction states, responsive behavior, accessibility, frontend visual review, or browser-based visual QA; do not use for backend work or mechanical frontend edits that introduce no design decision.
Ccdawn Competition Research Lifecycle
Use when coordinating an end-to-end research competition or benchmark program across multiple lifecycle stages such as task definition, data, baseline, experiments, evidence, paper claims, and submission packaging; use score-loop for a single metric lane and ai-research-loop for a standalone research direction.
Ccdawn Score Loop
Use when an experiment or competition lane has an explicit metric, baseline, candidate comparison, promotion gate, leaderboard/validation feedback, or submission iteration; do not use for ordinary software latency, performance debugging, or one-off measurements without a baseline-candidate loop.
Ccdawn Feature Reuse Research
Use when a complex feature has an unresolved reuse decision and external projects, libraries, standards, examples, or in-project modules could materially change architecture, dependencies, scope, or implementation; do not use for routine work already covered by local patterns or standard platform capabilities.
Ccdawn Ai Research Loop
Use when AI/ML research engineering needs baseline reproduction, hypothesis-driven experiments, ablations, evaluation design, findings synthesis, research direction selection, plateau recovery, or a reproducible loop from a paper/repository/research question to evidence-backed results.
Ccdawn Bug Review
Use when a bug, regression, failing test, build failure, abnormal behavior, performance symptom, or suspected root cause needs Chinese-first diagnosis, bounded repair, and evidence-based verification without loading a heavyweight debugging workflow.
Ccdawn Thread Coordination
Use when multiple Codex App threads or agents work in the same project and need shared progress awareness, ownership arbitration, conflict pause/resume, bounded discussion, merge coordination, status exchange, or handoff through native thread tools without heavyweight orchestration.
Ccdawn Brt
Use when a user message needs Chinese-first intent inference, low-confidence collaborative clarification, routing, workflow weight control, skill choice, review/testing/planning/debugging/evaluation routing, multi-thread conflict coordination, continuation handling, execution permission inference, or protection from process over-escalation.
Ccdawn Bdd Tdd Development
Use when a selected CCDawn subtask has meaningful behavior, regression, state, data, security, migration, public-contract, or cross-module risk that needs a failing test before implementation; simple or mechanical work should stay with its current owner and use targeted verification.
Ccdawn Research Rigor Review
Use when an AI/ML research result, baseline promotion, ablation conclusion, benchmark claim, paper claim, surprising finding, or high-cost next experiment needs an evidence-focused rigor review before it is accepted, generalized, published, or used to redirect the research program.
Ccdawn Evaluation
Use when CCDawn 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.
Ccdawn Creative Toolbox
Use when the user wants context-aware concept collision, unknown concept generation, divergent thinking, creative ideation, concept invention, paradigm exploration, unusual alternatives, product ideas, research concepts, strategy concepts, story concepts, or surprising but useful options.
Ccdawn Simplification Review
Use when the user explicitly asks whether a diff, PR, branch, commit range, or proposed patch is over-engineered or can be made smaller, or when concrete evidence makes removable complexity the primary review question; do not attach it to every code review.
Ccdawn Pr Review
Use when the user explicitly requests review of a PR, diff, branch, commit range, merge readiness, or review feedback, or when a high-risk change has reached an explicit pre-integration review gate; do not trigger merely because ordinary development finished.
Ccdawn Goal Loop
Use when the user explicitly wants a persistent iterative goal contract with bounded inputs/tools, strict constraints, success evidence, repeated next-step selection, and stop conditions, and no more specific CCDawn owner already controls the work; do not use for ordinary one-turn or finite implementation requests.
Ccdawn Task Splitting
Use when BRT or an accepted implementation plan has already found multiple independent deliverables, owners, dependency artifacts, risk gates, verification contracts, parallel lanes, or cross-session boundaries that genuinely require an executable task graph before development.
Ccdawn Dawn Agent Html Memory
Use when the user or project rules explicitly request project-local memory/dashboard initialization or updates, or when an existing `.docs/project-memory/` is needed for cross-session recovery, durable decisions, blockers, parallel-agent coordination, or formal handoff; do not auto-initialize or sync it for ordinary development.
Ccdawn Development Cleanup
Use when a verified or integrated software change has concrete temporary artifacts, generated noise, stale claims, merged local branches, or disposable worktrees to clean, or when the user explicitly asks to remove development residue or old branches.
Ccdawn Completion Summary
Use when completed work needs formal cross-stage or cross-session synthesis, resumed-task closure, durable handoff evidence, deferred-risk accounting, or PR/release readiness evidence that cannot be represented by the current owner's normal verification and concise final response.
Ccdawn Huawei Nslb Score Loop
Use when optimizing, benchmarking, packaging, comparing baselines, handling online score feedback, or coordinating parallel agents for a Huawei Algorithm Challenge 37 NSLB workspace identified by its solver and score-loop artifacts.
Ccdawn Simplification Audit
Use when the user explicitly requests a repository/subsystem simplification audit, dependency-bloat review, or ranked removal plan, or when concrete evidence makes structural complexity the primary investigation; do not substitute it for ordinary project health review.
Ccdawn Planning
Use when aligned requirements need a persistent or reviewable implementation plan because real design choices, cross-boundary contracts, multiple owners, risky sequencing, migration, release, or cross-session handoff make an internal execution outline insufficient.