金融
个人理财、预算与财务工具
security-pattern-check
kjgarza
Identify security vulnerabilities and anti-patterns providing feedback on security issues a senior developer would catch. Use when user mentions security/vulnerability/safety concerns, code involves user input/authentication/data access, working with sensitive data (passwords/PII/financial), code includes SQL queries/file operations/external API calls, user asks about security best practices, or security-sensitive files are being modified (auth, payment, data access).
symfony-api-platform-filters
data219
Implement API Platform filters for search, date ranges, boolean, and custom filtering with proper indexing
circuit-breakers-and-retries
curiositech
Building resilient distributed systems with circuit breakers, retries with full-jitter exponential backoff, retry budgets (per-request 3-attempt + per-client 10% ratio per Google SRE), deadline propagation, and the cascading-failure math (4 layers × 3 retries = 64x amplification). Grounded in Resilience4j, Microsoft Cloud Patterns, AWS Architecture Blog (Marc Brooker), and Google SRE Book. NOT for server-side rate limiting, bulkhead isolation, backpressure protocols, or database-specific retry.
cursor-adversarial-review
aarontzeng
Run a read-only challenge review through Cursor's CLI (cursor-agent) in ask mode. Use when the user asks for a review via Cursor, or when the cross-family rule needs a reviewer family the standalone CLIs cannot field — one paid adapter serving GPT, Claude, Grok, Kimi, Composer, and auto.
dev-lead
aarontzeng
Orchestrate a feature or PR end-to-end as the lead — dispatch implementation to a delegate family based on task risk, model capability, and remaining quota; run bounded adversarial-review rounds with cross-family reviewers; verify everything independently; and hold the merge gate. Use when the user wants a whole feature/fix delegated and supervised, rather than a single implement or review pass.
always-on-agent-inputs
curiositech
How to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capture (screen, audio, calendar), context window budgeting, and retrieval strategies that keep the agent grounded in what's actually happening. Activate on: "what should the agent observe", "context inputs for agent", "ambient context capture", "agent triggers", "agent input design", "screenpipe integration", "context window budget", "what data to feed my agent", "/always-on-agent-inputs". NOT for: memory architecture and storage (use always-on-agent-architecture), application ideas (use always-on-agent-applications), safety concerns (use always-on-agent-safety).
agent-interchange-formats
curiositech
Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).
context-economics-for-agent-swarms
curiositech
Treat tokens as a coding swarm's cost-of-goods-sold AND its legibility engine. Covers per-agent context budgeting, compaction strategies (in-context summarization, structured note-taking, sub-agent isolation), the shared digest as compaction-for-humans- and-agents, the context-degradation cascade (lost-in-the-middle, context rot, recursive- summarization collapse), and mechanism design for metering token spend across a fleet. Activate on: "token budget", "context budget per agent", "compaction strategy", "digest / briefing as compression", "context window degradation / context rot", "summarization collapse", "COGS for agents", "metering agent token spend", "pheromone decay as forgetting", "/context-economics-for-agent-swarms". NOT for: memory storage architecture (use always-on-agent-architecture), single-prompt wording (use prompt-engineer), pure mechanism-design proofs (use nisan-et-al-2007-algorithmic-game-theory).
performance-budget-setter
patricio0312rev
Defines measurable performance budgets for bundle size, API latency, database queries, and render times. Provides enforcement strategies and monitoring plans. Use for "performance budgets", "performance monitoring", "web vitals", or "optimization targets".
agentic-calendar-coordination
curiositech
Design scheduling agents. Use for timezone-safe negotiation, focus protection, and privacy-safe free-busy handling. NOT for calendar UI, project planning, or general agent architecture.
morning-weather
rolandcanyon-cmd
Fetch today's weather from Tempest and Ambient Weather stations and send it via iMessage
us-gov-shutdown-tracker
Mann1988
Track and analyze US government shutdown liquidity impacts by monitoring TGA (Treasury General Account), bank reserves, EFFR, and SOFR data from FRED API. Use when user wants to (1) analyze current or past government shutdown effects on financial markets, (2) track liquidity conditions during fiscal policy disruptions, (3) assess "stealth tightening" effects, (4) compare shutdown episodes across different monetary policy regimes (QE vs QT), or (5) generate liquidity stress reports with historical context. Recommended usage frequency is weekly on Wednesdays after TGA/reserve data releases.
alphago-deep-rl
curiositech
Apply AlphaGo-style patterns: learned priors plus search, mixed evaluators, self-play, and asynchronous fast/slow loops. Use for intractable search and compute allocation. NOT for basic supervised learning, tractable optimization, or domains without search bottlenecks.
product-roadmap-focus
curiositech
"Chooses the most important product or roadmap work under ADHD, founder, budget, and multi-agent constraints. Use when asking what to work on next, prioritizing a roadmap, cutting scope, choosing an MVP slice, or deciding whether to split work across agents. NOT for executing an already-chosen task, generic project status reporting, personal financial advice, or long unbounded brainstorming."
opencode-adversarial-review
aarontzeng
Run an adversarial (red-team) review through the OpenCode CLI's free model pool (muse-spark, Nemotron, stealth models) under a machine-enforced read-only permission config. Use when a HIGH-risk change needs a second cross-family reviewer without spending paid quota, or as the cheap extra pair of eyes beside a primary review.
operate-gpu-spec
SyFI-ServingStudio
Use when reading, querying, verifying, or extending the GPU spec catalog at gpu/spec.json — the per-GPU datacenter hardware table (mem/BW, dense TFLOPS by dtype, interconnect, nvl_domain_size, dollar_per_hour). Covers how to INTERPRET each field (TFLOPS are DENSE not sparse, interconnect BW is BIDIRECTIONAL, fp32 is CUDA-core not tensor, dollar_per_hour is the getdeploying on-demand "medium" rate, nvl_domain_size is a deployment param), how to SEARCH for a value (jq/python), how to VERIFY a value is right (sparse-doubling trap, one-way vs bidir, SXM vs PCIe vs NVL form-factor distinction, GB200 combined-for-2-GPU), what to do when a GPU/field is NOT in the table (web-search the fallback and clearly tell the user it is a searched result, not catalog-backed), and how to ADD/refresh a GPU. Only compute_capability reaches the simulator timing path (capability-keyed rules such as the FlashInfer all-reduce budget); modeled kernel timings come from measured kernels in profile.db, not from these peaks.
token-optimizer
Asif2BD
Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
top-explore-models
SyFI-ServingStudio
"Use as the top-level entry point when the user asks to understand a new Transformer model or Hugging Face checkpoint before ServingStudio Sim modeling work. Answers high-level model questions such as parameter scale, overall architecture, attention type, layer/head/hidden dimensions, context length, MoE layout, multimodal branches, and public architecture notes by collecting Hugging Face metadata/config/model-card evidence first. Route KV cache size/capacity calculations and attention/cache classification for MHA/GQA/MLA/DSA/GDN/custom mechanisms to dev-calculate-kv-cache-capacity. Route deeper Torch implementation, operation-list, forward-path, or kernel-semantics questions to dev-lookup-transformers-model."
verify
ahmadzayan-hub
Run every check Agentic OS has (Python suite, brain check, typecheck, frontend unit tests, production build, interface budget, and optionally the Playwright suite) with one command, and report the real counts. Use before saying a change works, before a commit that touches behaviour, before the session-end skill logs results, or when the user says "verify", "run the checks" or "is it green?".
economist
dangeles
Use when order-of-magnitude cost estimates are needed to assess financial feasibility, compare cost-effectiveness of alternatives, or identify major cost drivers (not for detailed quotes—that's Procurement)
Commenting Intent
obra
Comment WHY code exists and non-obvious decisions, not WHAT code does (mechanics)
instruction-audit
weside-ai
Audits rules, skills and AGENTS.md against fresh Anthropic docs and a budget gate; findings go to the optimization inbox. Triggers: "/we:instruction-audit".
sec-edgar-skill
rebyteai-template
SEC EDGAR filing analysis using EdgarTools. Use when user asks about SEC filings, company financials, 10-K/10-Q analysis, insider trading, revenue trends, or financial comparisons. Triggers include "SEC filing", "10-K", "10-Q", "8-K", "EDGAR", "company financials", "revenue", "earnings", "insider trading", "financial statements". Do NOT use for real-time stock prices or market data (use market-data skill instead).
advertising-platform-operations
magnusthovsland
"Use for paid-ad campaign changes through platform APIs."