AI & ML

aibtcdev Bundle

AIBTC Network editorial skill — "Protocol and Infrastructure Updates" signal composition, source validation, and editorial voice guide for aibtc.news correspondents covering API changes, contract deployments, MCP updates, protocol upgrades, bugs, and breaking changes.

aibtcdev Bundle

Agent-powered limit orders on Bitflow — set price targets, auto-execute swaps when conditions are met.

aibtcdev Bundle

Executes LP-based sBTC/STX arb on Bitflow HODLMM. Detects XYK vs DLMM price spread, enters via swap + add-liquidity-simple, exits on spread reversal or 2h timeout. Write-capable; requires --confirm. Emits MCP command objects.

aibtcdev Bundle

Deal Flow editorial skill — signal composition, source validation, and editorial voice guide for aibtc.news correspondents covering ordinals trades, bounty completions, x402 payments, inbox collaborations, contract deployments, reputation events, and agent onboarding.

aibtcdev Bundle

JingSwap STX↔sBTC cycle monitor and participation agent. Reads live cycle state and prices directly from the Stacks contract via Hiro API and Pyth oracle — no API key required. Outputs PARTICIPATE / MONITOR / WAIT_FOR_DEPOSIT_PHASE / NO_SBTC_AVAILABLE with oracle-vs-DEX discount analysis.

aibtcdev Bundle

Cross-protocol yield rotator for Stacks mainnet. Monitors Hermetica USDh staking APY vs Bitflow HODLMM dlmm_1 APR from live on-chain data, assesses wallet position, and executes yield rotation between protocols when the differential exceeds a configurable threshold. Write-capable: outputs MCP commands for stake, initiate-unstake, complete-unstake, and cross-protocol rotate actions.

sd0xdev Bundle

Lightweight model correction with context-aware rule loading. Use when: model forgot a rule, skipped a required step, edited code/docs without running review, needs to re-read CLAUDE.md or rules. Triggers on: 'you forgot', 'remind', 'check rules', 'what did you miss', '你忘了', 'did you skip review', 'why didn't you run precommit', or /remind. Also use PROACTIVELY after editing files if unsure whether auto-loop was followed — the detection prelude is cheap and catches drift early — the corrections it then runs cost what those reviews cost. Not for: full code review (use codex-review-fast), next step advice (use next-step), workflow progression (use feature-dev).

compozy Bundle

Assess a spec task or delivery claim against its contract and available verification evidence.

compozy Bundle

Audit backend tasks/spec coverage for Web, site, public agent interfaces, config, and extensibility impact. Use for contract, handler, CLI, extension/hook/tool/registry/bridge/MCP/workflow changes; excludes refactors without those impacts.

compozy Bundle

Run a requested external review of an approved Compozy spec; continue follow-ups in the same reviewer session and incorporate only user-selected findings. Excludes product drafts, automatic gates, code reviews, and review loops.

compozy Bundle

Orchestrate Claude and Codex worker TUIs from a controller agent — one worker per named herdr tab, driven over the herdr socket CLI.

compozy Bundle

Data-boundary audit for Compozy route loaders, TanStack Query caches, paginated catalogs, filters, ordering, totals, live streams, workspace-scoped reads, and their backend APIs. Use when adding, changing, or debugging those paths. Don't use for presentational-only UI or backend work with no public read-model impact.

compozy Bundle

Isolates Compozy runtime state for concurrent worktrees and QA runs. Use when another agent or runtime may share the machine, or when creating a parallel worktree. Do not use for single-worktree or build-only work.

compozy Skill

Executes agent-authored review remediation using existing round files under .compozy/tasks/<name>/reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for task execution, review generation, or generic coding tasks without review issue files.

compozy Bundle

Maintains workflow-scoped task memory for CompozyOS runs using .compozy/tasks/<name>/memory/ files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across spec task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.

compozy Skill

Conducts one spec's tasks by delegation — spawns a dedicated bounded worker session per task, dispatches the briefing, and uses the task file on disk for completion state and checks its verification evidence. Use when a prompt names a spec slug under .compozy/tasks/ and asks for its tasks to be orchestrated across worker sessions. Do not use for implementing a task directly, for review remediation, or for QA and pull-request work.

nwave-ai Skill

KNOWLEDGE — canonical worked examples for agent creation, migration, and command optimization. Reference for the relevant procedures; no sequence.

nwave-ai Skill

Lightweight eval method for testing nWave AGENTS and SKILLS (LLM behavior) as a lean alternative to heavy BDD/ATD. An eval = one prompt -> one captured run (trace + artifacts) -> a small set of checks -> a comparable score over time. Load when validating agent behavior, building a regression net for an agent/skill, or reducing agent-test bloat.

nwave-ai Skill

PROCEDURE — create a NEW agent via the 5-phase workflow (ANALYZE→DESIGN→CREATE→VALIDATE→REFINE). Trigger: build a new AI agent. Composes nw-ab-validate-spec.

nwave-ai Skill

PROCEDURE — merge agent B into agent A, relocating skills and cleaning up all references. Trigger: two agents must become one. Composes nw-ab-validate-spec.

nwave-ai Skill

KNOWLEDGE — agent/skill/command anti-pattern catalog with fixes. Reference scanned by validate-spec; no sequence.

nwave-ai Skill

PROCEDURE — validate an EXISTING agent spec against the 19-item checklist. Trigger: checking a spec for compliance (also the shared composition target create/migrate/merge invoke). One job: run the checklist, report pass/fail.

nwave-ai Skill

Erlang/Elixir language-specific patterns, OTP as the effect model, and runtime-enforced immutability

nwave-ai Skill

KNOWLEDGE — the canonical agent-spec template (frontmatter + body skeleton). Reference loaded by the create/migrate procedures; no sequence.

nwave-ai Skill

KNOWLEDGE — resolve code facts (who-calls-X / where-defined-or-read / call-graph / change-scope / file-atoms) through the vendor-neutral CLI `des code-fact`, degrading LOUD through bundled adapters (AST, TextSearch). Trigger: any time an agent designs, writes, analyzes, or reviews code or tests and needs a structural code fact.

nwave-ai Skill

PROCEDURE — migrate one legacy monolithic agent to a lean core plus routed skills. Trigger: an existing agent has measured size, embedded-configuration, duplication, aggressive-language, or multi-responsibility debt. Composes agent validation and requested skill optimization.

nwave-ai Skill

KNOWLEDGE (data) — the 19-item agent-spec validation checklist. The item definitions the validate-spec procedure RUNS against. No sequence of its own.

nwave-ai Skill

Cross-cutting normative invariants — routing core for the software/model boundary doctrine, gate/construction principles and on-demand knowledge lenses. Cite clause ids; never re-declare.

nwave-ai Skill

The METHOD for finding a design — name observations and equality before constructors, then follow any contradiction to the type or observation that causes it. Use when a design decision is contested, a law has exceptions, a census or model keeps producing wrong answers, or a representation change must preserve meaning. Complements nw-fp-algebra-driven-design, which catalogues the structures; this says how to arrive at one and what to do when it breaks.

raja21068 Skill

Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.

raja21068 Skill

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

raja21068 Skill

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.

raja21068 Skill

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.

raja21068 Skill

Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

raja21068 Skill

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.

raja21068 Skill

Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.