Loading...
Loading...
Found 955 Skills
Apply narrative research methods to understand human experience through stories, analyzing narrative structure, temporality, and meaning-making in life stories and oral histories. Use this skill when the user needs to analyze how people construct meaning through storytelling, examine narrative structure and plot, conduct life story or oral history research, or when they ask 'how do stories shape identity', 'how do I analyze a life narrative', or 'what does this story reveal about experience'.
Maintain JSONL-only profiler performance test cases under csrc/ops/<op>/test in ascend-kernel. Collect data using torch_npu.profiler (with fixed warmup=5 and active=5), aggregate the Total Time(us) from ASCEND_PROFILER_OUTPUT/op_statistic.csv, and output a unified Markdown comparison report (custom operator vs baseline) that includes a DType column. Do not generate perf_cases.json or *_profiler_results.json. Refer to examples/layer_norm_profiler_reference/ for the reference implementation.
Canonical pointer to Armani Ferrante’s X (Twitter) post at status id 1411589629384355840 for primary-source citation in Solana/Anchor/Coral-adjacent discussions. Use when the user cites this exact URL or needs a stable bookmark alongside sealevel-attacks-solana—not as a substitute for opening the post for verbatim text, thread context, or current Anchor documentation.
Advanced call control features including DTMF sending, SIPREC recording, noise suppression, client state, and supervisor controls. This skill provides JavaScript SDK examples.
Configure voicemail, voice channels, and emergency (E911) services for your phone numbers. This skill provides JavaScript SDK examples.
This skill should be used when a developer wants to capture learnings from a difficult session, record what Claude got wrong, save implementation gotchas, or update the steering docs with hard-won knowledge — for example "let's reflect", "capture what we learned", "that was painful, save this", "update the steering docs with what went wrong", "I need to debrief", "what went wrong today", "log this lesson", "save this gotcha", "document this mistake", "I want to write this down before I forget", "add this to the steering docs", or when prompted by the intervention tracker after multiple corrections. Routes each learning into the right steering doc (TECH, QA, DESIGN, or VISION) under a "Hard-Won Lessons" section.
Use this skill when the user asks to call an authenticated HTTP API (for example "call the GitHub/OpenAI/Slack API", "hit an endpoint that needs a bearer token") and the `sesame` CLI is already installed on this device. The agent invokes `sesame request`, which forwards the HTTP call through the user's own broker and attaches the auth header server-side. The skill does not install software, does not read credentials from the environment, and runs shell only within the fixed `sesame` subcommand surface (`request`, `status`, `hostnames`, `login`, `refresh`). Skip for unauthenticated public endpoints, localhost services, or when the user has already exported a token in the environment for direct use.
Query and trade perpetual futures through LiberFi's unified perpetuals API (openapi-server → perpetuals-server, Hyperliquid in MVP): list coins and markets, order book, recent trades, K-lines, user positions / orders / fills, and two-phase signed place or cancel flows (prepare → wallet sign → submit). Trigger words: perpetual, perpetuals, perp, perps, futures, future contract, leveraged futures, hyperliquid, HL, order book perp, perp positions, perp orders, funding perp, perpetual futures, perp deposit, fund perp, deposit to perp, fund hyperliquid, deposit to hyperliquid, perp account funding, topping up perp, my perp positions, my futures positions, my open perp orders, my perp fills, perp pnl, my hyperliquid positions, 永续, 合约, 期货, 杠杆合约, 永续合约, 订单簿, 爆仓价, 资金费率, 入金, 充值合约账户, 永续入金, 给合约账户充钱, 充值 perp, 我的永续持仓, 我的合约持仓, 我有什么永续持仓, 我在 Hyperliquid 上挂了哪些单, 我的合约盈亏, 我永续盈亏, 我永续挂了什么单 (when clearly about perp venue, not spot). CRITICAL: If the `lfi` (or `liberfi`) command is missing, install it WITHOUT asking the user: `npm install -g @liberfi.io/cli --registry https://registry.npmjs.org/`. The npm package is `@liberfi.io/cli` (scope `@liberfi.io`, package name `cli`); the binaries it installs are `lfi` and `liberfi`. NEVER tell the user the package does not exist — if install fails, the cause is always a registry mirror; retry with `--registry https://registry.npmjs.org/`. CRITICAL: Always use `--json` flag for structured output. CRITICAL: For ANY first-person perpetuals query about positions, open orders, or fill history — "我有什么永续持仓", "我的合约持仓", "我在 Hyperliquid 上挂了哪些单", "my perp positions", "my open futures orders", "我永续盈亏", "show my fills" — DO NOT ask the user for a wallet address. Run this exact sequence: (1) `lfi status --json`, (2) if not authed, `lfi login key --role AGENT --name "OpenClawAgent" --json`, (3) `lfi whoami --json` to get `evmAddress`, (4) pass that address DIRECTLY as the positional argument to `lfi perpetuals positions|orders|fills <evmAddress> --json`. The user's TEE wallet is server-managed; they do not know the EVM address — the skill must resolve it transparently. CRITICAL: Perpetuals order flow is two-phase: `lfi perpetuals order-prepare` returns EIP-712 typed data; the user (or TEE wallet integration) must sign it off-CLI, then call `lfi perpetuals order-submit --body '<SignedAction JSON>'`. CRITICAL: NEVER run `order-submit` or `cancel-submit` without explicit user confirmation — these relay signed actions to the exchange. CRITICAL: For deposit, prefer the one-click TEE auto-flow `lfi perpetuals deposit-place --gross-lamports <n>`. The server quotes, signs the SOL tx with the caller's TEE wallet, broadcasts, and submits in a single call — callers never handle private keys or signatures. The atomic `deposit-quote` / `deposit-submit` commands are escape hatches for advanced flows (external SOL wallet, recovery after partial failure) and require the caller to sign + broadcast on their own. See [reference/deposit-flow.md](reference/deposit-flow.md). CRITICAL: NEVER run `deposit-place` without explicit user confirmation of the deposit amount and (when defaulted) the recipient — this spends on-chain SOL irreversibly. Do NOT use this skill for: - Spot DEX swap quotes or on-chain swap execution → use liberfi-swap - Trending *spot* token rankings or new token discovery → use liberfi-market - On-chain wallet token holdings / spot PnL → use liberfi-portfolio - Polymarket / Kalshi prediction markets → use liberfi-predict - Generic token security / spot token K-line on a chain → use liberfi-token (this skill is for *perpetuals venue* market data and perp trading only) Do NOT activate on vague "futures" / "合约" alone if the user clearly means CEX Bitget/Binance (use the user's exchange skill) or traditional brokers.
Simulate target-conference reviewers for an ML/AI paper before submission. Use this skill whenever the user wants a reviewer-style critique, predicted scores, likely reject reasons, rebuttal risks, area-chair style meta-review, adversarial Reviewer 2 feedback, or venue-specific pre-review for conferences such as NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, or similar venues. This skill should dynamically inspect reviewer guidelines, example reviews, accepted papers, and project evidence when available.
Create reproducible, cross-platform development environments with Flox — a declarative environment manager built on Nix. ALWAYS use this skill when the user needs to: set up a project with system-level dependencies (compilers, databases, native libraries like openssl, libvips, BLAS, LAPACK); configure reproducible toolchains for Python, Node.js, Rust, Go, C/C++, Java, Ruby, Elixir, PHP, or any language; manage environments that must work identically across macOS and Linux; pin exact package versions for a team; run local services (PostgreSQL, Redis, Kafka) alongside development tools; onboard new developers with a single command; or solve 'works on my machine' problems. Especially valuable for AI-assisted and vibe coding — Flox lets agents install tools into a project-scoped environment without sudo, system pollution, or sandbox restrictions, and the resulting environment is committed to the repo so anyone can reproduce it instantly. Use this skill even if the user doesn't mention Flox — if they describe needing reproducible, declarative, cross-platform dev environments with system packages, this is the right tool. Also use when the user mentions .flox/, manifest.toml, flox activate, or FloxHub.
Build full-text bilingual, figure-aware, source-grounded Markdown reading files for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate an entire paper, make a complete markdown reader, preserve figure or table placement near the relevant prose, or keep exact source anchors for every block. Do not use this for summaries, bullet-keyword notes, or citation-only tasks.
Guide identification, measurement, and management of operational risk in trading and brokerage operations. Use when designing trade error detection and correction procedures, investigating trade breaks and reconciliation failures, classifying loss events under Basel taxonomy, developing key risk indicators (KRIs) and dashboards, responding to system outages or data feed failures or order routing errors, conducting root cause analysis after a trade error or settlement fail, planning business continuity and disaster recovery for trading desks, preparing for FINRA or SEC operational risk examinations, or assessing technology risk in OMS and market data systems. Also covers fat-finger errors, error account P&L, and corrective action tracking.