Coding & Dev Tools

nwave-ai Skill

KNOWLEDGE — use when evaluating a claim, check, measurement, or shared-log count.

nwave-ai Skill

PROCEDURE — verify one separately selected formal DESIGN obligation and state its runtime refinement boundary.

raja21068 Skill

Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.

raja21068 Skill

AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).

raja21068 Skill

Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.

raja21068 Bundle

Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

raja21068 Skill

SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.

raja21068 Skill

Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.

raja21068 Skill

Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.

raja21068 Skill

Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.

raja21068 Skill

Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.

raja21068 Skill

Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.

raja21068 Skill

Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

calven-ai Skill

Bring in the latest approved copy and say what is waiting on you. Use at the start of a session, when asked to "sync", "where am I", "what's waiting on me", or while a proposal is checking.

calven-ai Skill

Setup: the onboarding interview

calven-ai Skill

Pre-publish review of a draft against strategy, messaging and brand voice; findings only, no rewrite unless asked. Use when asked to review, check or QA a draft, or before it moves to in-review.

calven-ai Skill

Turn what changed into a proposal (a pull request) and hand back the link. Use when asked to "propose", "send this for review", "ship it", "save this to GitHub", or when work is done and should land.

calven-ai Bundle

Publish

calven-ai Bundle

Synthesise why deals were won and lost this period from closed deals and call transcripts, by competitor, segment and reason. Use when "why did we lose Acme", "quarterly win/loss".

calven-ai Bundle

Check an asset against the visual identity and tokens, or write the design brief for a missing one. Use when "does this match the brand", "design QA", "need a hero image for X".

calven-ai Bundle

Edit copy

cleanexpo Skill

Senior Brand Strategist (15+ yr calibration). Voice register strategic owner. Maintains per-brand voice tag system (Q2.5.5) + Phase 4 voice amendments + verification-gated category claims + portfolio taboo discipline + L9 cross-client carve-out. Approves voice register decisions before brand-voice-enforce mechanically gates drafts. Closes every decision with the specific voice-tag locked, amendments cited, and the brand-voice-enforce directive that downstream skills consume. Reads ceo-foundation.md + verification-gates.md at every invocation.

cleanexpo Skill

24/7 ~1.5-day autonomous shipping orchestrator for Synthex. Drives 7 child loops (build, test, sanity, watch, smoke, pr, merge) on differentiated cadences. Reads state from .claude/scratchpad/ship-loop-state.json on every tick, dispatches the next eligible child loop, and exits cleanly after 36 hours OR when state.completion === 'merged'. Use when the CEO says "/loop ship-loop-master" to start an autonomous shipping run.

cleanexpo Skill

Mechanical gate that checks senior-skill output against the brand rules locked in `.claude/memory/ceo-foundation.md` and the gate state in `.claude/memory/verification-gates.md`. Reads both at every invocation. Pass/fail decision per draft. Forwards passing drafts to senior-strategist for final review before CEO batched-review queue.

cleanexpo Skill

The "no invaders" gate for Synthex. The ship already carries everything it needs. NEVER add a new npm dependency, external SaaS, framework, datastore, or auth system to solve a problem an existing system already solves — adding one is a CEO-gated decision. ALWAYS prove the capability isn't already present (grep package.json, lib/, the skills list, Vercel env) before integrating anything new. Activate on ANY request to "add a package / install / npm i / integrate X / we need a tool / use library Y / add a provider / new database".

cleanexpo Skill

Senior Customer Insights Lead (16+ yr calibration · JTBD · ethnography · audience-evidence base custodian). Owns the locked audience profiles for the portfolio (foundation Phase 3.1.2 RA · Phase 3.2.2 DR + NRPG · Phase 3.3.2 CARSI · Phase 3.4.2 CCW + Bridge) and the verified-vs-hypothesised state of every JTBD claim senior-copywriter consumes. Surfaces audience-match · drift · trigger-alignment opportunity to invoking skill with explicit verification-state tagging. Reads ceo-foundation.md + verification-gates.md at every invocation.

cleanexpo Skill

DX Review Specialist

cleanexpo Bundle

Listing optimisation, review response strategy, Google Posts, local pack ranking factors, NAP consistency, and category selection for Google Business Profile. Use when optimising GBP listings, managing reviews, or improving local search visibility.

cleanexpo Bundle

Algorithm update types, diagnosis workflows, recovery strategies, and proactive hardening for Google algorithm changes. Use when diagnosing traffic drops, responding to algorithm updates, or hardening sites against future updates.

cleanexpo Bundle

Algorithm Intelligence Layer for Synthex. Loads curated platform algorithm knowledge to inform content strategy recommendations. Auto-invokes when generating content recommendations, explaining reach drops, reviewing posts for platform fit, or building advisor briefs. Contains signal data for Google Search, Instagram, and LinkedIn with confidence ratings.

cleanexpo Skill

Senior Platform Content Adaptor (15+ yr calibration · multi-platform native voice · algorithm-aligned formatting · brand-DNA preservation across resize). Takes one source piece (post · article · video script · announcement) and produces correctly-formatted versions for every active platform — never the same copy across platforms · LinkedIn hooks never start with "I" · Instagram hooks land in 125 chars · TikTok opens with a challenge or question. Every adaptation passes the brand-voice-enforce gate, the platform-distinct-voice rule, and the hashtag-tier discipline (broad/medium/niche mix). Reads ceo-foundation.md + verification-gates.md at every invocation.

cleanexpo Skill

Test Quality Review Specialist

cleanexpo Skill

Senior Platform Content Optimiser (15+ yr calibration · algorithm-signal scoring · plain-English client translation · falsifiable lift framing). Scores content 0-100 against platform algorithm signals and outputs prioritised, plain-English recommendations. Uses algorithm-knowledge-base as the signal intelligence layer. Every signal name in client-facing output uses the plain-English translation from `algorithm-knowledge-base/references/signal-translations.json` — never exposes raw signal names (NavBoost · sends_per_reach etc.) to clients. Reads ceo-foundation.md + verification-gates.md at every invocation.

cleanexpo Skill

Commit Hygiene Review Specialist

cleanexpo Skill

Review Board Metrics Analyzer

cleanexpo Skill

Supabase Patterns Specialist