“fuse”的搜索结果

Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: "my agent hit a 402 while calling an API", "a tool call returned 402 Payment Required", "my agent needs to pay for x402-protected content", "let the agent pay for content, capped at $5 per session", "set a spend limit for the agent", "ProcessPayment failed", or "why did my agent refuse to pay". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references/payments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.

中文简介正在准备中。当前显示原文说明。

Builds, runs, debugs, and operates applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments running inside a container with up to 8 hr lifetimes. Applicable when workloads need strong isolation between tenants, isolated serverless compute, sandbox compute, or secure multi-tenant execution. Also suited for AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs, dev environments running user-supplied code), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, or isolated security scanners. Also applicable when the workload needs long-lived sessions, a real port-listening server (gRPC, WebSocket, custom TCP protocols), state preserved across periods of inactivity (suspend/resume), container-level access (FUSE, eBPF, custom syscalls), or session-affine routing.

中文简介正在准备中。当前显示原文说明。

Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits, Organizations quirks, and SAML/MFA specifics. Also provides structured workflows for IAM role management and baseline policy generation from application source code or a Terraform plan JSON. Covers condition operator safety (ForAnyValue/ForAllValues with Null checks), bucket policy deny patterns (VPC endpoint restrictions, org paths), confused deputy protection, and service role creation for AWS services (Glue, CloudTrail, Lambda, ECS, etc.) with aws:SourceAccount/aws:SourceArn trust conditions. Applies when creating IAM roles, writing IAM or bucket policies, generating policies from application source code or a Terraform plan JSON, working with STS, Organizations, or condition operators, or any task needing a service or execution role. Does not cover non-IAM authorization like Cognito user-pool policies or app-level RBAC.

中文简介正在准备中。当前显示原文说明。

Provisions, scales, and operates Amazon EC2 virtual-machine workloads: instance-type selection (Graviton/Arm64, burstable T credits, GPU, instance store vs EBS), launch templates, Auto Scaling groups (scaling policies, instance refresh, mixed instances, Spot, warm pools, lifecycle hooks), IMDSv2, placement groups, Elastic IPs, AMI lifecycle, and Systems Manager fleet operations (Session Manager, Run Command, Patch Manager). Applies to EC2 instance and fleet questions, InsufficientInstanceCapacity, CPU-credit/surplus charges, IMDSv2 401s, instances stuck in Pending:Wait, ASG not replacing unhealthy instances, status-check failures, SSH refused/timed out, or instances missing as SSM managed nodes. For a single secure instance launch, the launching-ec2-instance-with-best-practices skill is more appropriate; for instance profiles, see setting-up-ec2-instance-profiles; for Image Builder, see amazon-ec2-image-builder. Does NOT cover Lambda, ECS/Fargate, EKS, VPC/ALB/NLB design, or IAM policy authoring.

中文简介正在准备中。当前显示原文说明。

Doctrine for designing and evolving any **SDK** Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface rejects the wrong contents and keeps the package testable in isolation. Default is "core, not customizable"; customization is the exception, defended by a deciding table. Use when authoring or evolving any such surface — `@grida/*` published packages, engine crates (gridaco/nothing `crates/*`) published or FFI-exported, intent/message vocabularies, any contract a second author will compile against. Internal-only helper packages are welcome to follow, not forced. Companion skill for two-sided contract work: $sdk-seam. Critique partners: $pedantic, $etiology. Related: $naming.

中文简介正在准备中。当前显示原文说明。

How to think about names in the Grida repo — not conventions, but what a name commits you to, reveals about the system, and costs to change. The central discipline is that a strict, honest name refuses to grow, and that refusal drives the repo's shape (flat modules, small agnostic packages, suffix siblings). Use when planning a new package, crate, module, directory, route group, or test corpus — the name comes first.

中文简介正在准备中。当前显示原文说明。

Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving form-completion rates, or evaluating information architecture and navigation. Covers Krug's laws, Nielsen's 10 heuristics, severity ratings, dark-pattern recognition, and accessibility. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.

中文简介正在准备中。当前显示原文说明。

Build safe, local, defensive reproductions of ALREADY-PATCHED, publicly disclosed security vulnerabilities (CVEs, vendor advisories, AI-agent incidents) for whitepapers, control testing, and education. Use this skill whenever the user wants to reproduce, demonstrate, or write up a known vulnerability or security incident — phrases like "reproduce this CVE", "build a repro for", "demonstrate the EchoLeak/Cursor/postmark-mcp issue", "show how this exploit worked", "add a reproducibility guide", or "pull the NVD/CVE details for". It fetches advisory metadata from NVD and CVE.org, confirms the issue is fixed, and produces a vulnerable-vs-patched harness that is offline, loopback-only, and uses synthetic markers. It NEVER discovers, develops, or weaponizes new zero-days and refuses any unpatched or live-target request.

中文简介正在准备中。当前显示原文说明。

End-to-end methodology for reproducing AND patching publicly disclosed, already-fixed vulnerabilities: sourcing the advisory and the fix commit, reading the patch diff, rebuilding a pinned offline lab, building a vulnerable-vs-patched contrast harness with proper controls, minimizing the trigger, designing and validating the fix, and writing it up as a blog post or whitepaper. Use this skill whenever the user wants to reproduce, demonstrate, understand, teach, or write about a known vulnerability or security incident: "reproduce this CVE", "build a repro for", "how did EchoLeak / Log4Shell / the postmark-mcp package actually work", "show me how this exploit worked", "write a blog post about this vulnerability", "set up a lab for CVE-XXXX", "pull the NVD/CVE/OSV details", or "make a PoC I can publish". Use it just as eagerly for the patching half: "how should this be fixed", "is this patch correct", "what would have caught this", "review this security fix", "write a regression test for this CVE", "how do I backport this", or "what's the right fix for this bug class" - even when the user never says the word "reproduce". Reach for it on vague asks like "help me understand this security advisory", "I want to write about this incident", or "can we test whether we were vulnerable" when a disclosed vulnerability is in play. This skill only handles ALREADY-PATCHED, publicly disclosed issues and refuses zero-day discovery, live targets, and weaponization.

中文简介正在准备中。当前显示原文说明。

Owns legal, contracts, intellectual property, regulatory compliance, privacy, security governance, enterprise risk, and audit readiness. Use this to review a contract or commitment, assess regulatory or privacy exposure, evaluate an IP or licensing question, judge the risk in a business decision, prepare for an audit or certification, or when a plan may create obligations the business cannot meet. Also use to decide whether a risk should be accepted, mitigated, or refused.

中文简介正在准备中。当前显示原文说明。

Skip profile question when user explicitly refuses to answer. When user says 'I don't want to answer' or 'skip this question', use this tool to stop asking about that item.

中文简介正在准备中。当前显示原文说明。

Organizes the evidence and competitive landscape around a drug, target, or pathway by separating disease relevance, tractability, preclinical evidence, clinical evidence, modality fit, and crowding. Always map what is biologically supported, what is druggable, what has actually advanced, and what remains strategically open. Never confuse target relevance with druggability, preclinical activity with clinical promise, or narrative excitement with validated development maturity. Never fabricate references, trial status, approval status, company activity, or asset metadata.

中文简介正在准备中。当前显示原文说明。

Combine visual features (face detection, lip movement analysis) with audio features to improve speaker diarization accuracy in video files. Use OpenCV for face detection and lip movement tracking, then fuse visual cues with audio-based speaker embeddings. Essential when processing video files with multiple visible speakers or when audio-only diarization needs visual validation.

中文简介正在准备中。当前显示原文说明。

Writing plays and screenplays in the Chekhovian mode (契诃夫戏剧法) — distilled from the complete plays (没有父亲的人/普拉东诺夫, 伊凡诺夫, 林妖→万尼亚舅舅, 海鸥, 三姊妹, 樱桃园, nine one-acts) plus Chekhov's own letters, Stanislavsky's and Nemirovich-Danchenko's rehearsal notes and 焦菊隐/童道明 criticism. Covers the four-act mood-based structure without central climax, off-stage events, "correct answer stated in Act 1 and refused", the announced event that never happens, three-layer endings (hope monologue + nihilist line + household action), no-villain conflict with environment, every character's object and catchphrase, one-way love chains, half-step-off dialogue, philosophy cut by thirst, the shortest words for the deepest pain, stage-direction and sound discipline, and how Chekhov revised The Wood Demon into Uncle Vanya. Use when the user wants an ensemble drama, a "nothing happens" play, subtext-heavy dialogue, a family estate / provincial story, an anti-climactic structure, or asks how to "Chekhov-ize" a script.

中文简介正在准备中。当前显示原文说明。

Case studies of television series writing (剧集案例库) from primary texts; Sorkin's six West Wing teleplays (act-page tables, eight act-out types); Chase's five Sopranos scripts (the 35-beat A/B/C/D recipe, what a pilot refuses to explain); Fellowes's annotated Downton Abbey season two (19 storylines, 419 footnotes); Waller-Bridge's Fleabag Scriptures (the six-episode half-hour template); Calvisi's eight minute-by-minute pilot beat sheets (Breaking Bad, Mad Men, Game of Thrones and more); Landau's 47-series structure appendix; Miller's Hannibal and HTGAWM breakdowns; Goldberg & Rabkin's beat sheets; Sakamoto Yuji's We Made a Beautiful Bouquet (a feature) and Noh Hee-kyung's The Most Beautiful Goodbye. Use when you want a worked example of how an episode or pilot is built, need real act lengths, scene counts or storyline grids to imitate, are breaking a multi-thread ensemble episode, designing a bottle episode or a finale, writing a relationship or family drama, or ask 某一集是怎么写的 / 这部剧的结构表.

中文简介正在准备中。当前显示原文说明。

Research-brief + claim-record discipline for delegated or AI-assisted research work. Use when starting any substantive research task or long autonomous run (write the brief first), and when reporting results that will support a claim in a paper or decision (produce the claim record). Keeps faster execution from being confused with credible evidence.

中文简介正在准备中。当前显示原文说明。

Turn a company update into 3-7 structurally distinct, journalist-shaped story angles. Runs the fact through proven newsroom lenses (perspective, abstraction, news values, data, contrarian, news peg) and refuses rephrasings, invented facts, named-journalist guesses, and AI-marketing slop.

中文简介正在准备中。当前显示原文说明。

Opinionated startup-PR strategist that helps founders figure out audience, positioning, news pegs, and drumbeat before any tactical PR. Refuses outlet-naming-before-audience, mass blasts, vanity metrics, and premature agency spend.

中文简介正在准备中。当前显示原文说明。

Authors Vally conformance tests for prompts, instructions, agents, and skills, and refuses jailbreak, prompt-injection, harmful-elicitation, TOS, CoC, and PII-extraction stimuli

中文简介正在准备中。当前显示原文说明。

Continues interrupted Codex work only after read-codex-history verifies rollout identity and fork/compaction lineage — restores the original outcome, unfulfilled requests, and the next action. Use when given a Codex Session ID, asked to pick up a prior Codex run, told Codex was interrupted, fused, compacted or stuck, or asked to take over without `codex resume`. Not for a conversation Codex already natively resumed.

中文简介正在准备中。当前显示原文说明。

Make a crop or livestock insurance claim after drought, flood, pests, disease or hail: report it in time, record the loss properly, and follow up or appeal if the payout is too low or refused. Use when someone says 'my crop failed, how do I claim', 'the insurance company rejected my crop claim', 'what proof do I need for a crop loss', or 'how do weather-index insurance payouts work'. Produces a claim timeline, an evidence checklist, a loss record, a notification message, and an appeal plan.

中文简介正在准备中。当前显示原文说明。

Run the greploop workflow with the @greptile-apps trigger when the normal trigger refuses a large PR. Requires the greploop skill installed alongside this entrypoint.

中文简介正在准备中。当前显示原文说明。

Execute a single Todo task through In Progress to Review, meeting every acceptance criterion with tests and vibe-lint checks. Refuses Planning-status tasks. Invoked as /agiflow:run-task <task>. Uses get_task, update_task, create_task_comment.

中文简介正在准备中。当前显示原文说明。

Deterministic pre-publish scan that refuses AI-slop tells in anything about to be written, published, or sent: files, artifacts, slide titles, table headers, diagram labels, chat messages, commit messages. Use before publishing or sending any deliverable, in CI, or wired as a Claude Code hook so the check runs without being remembered. The editorial counterpart is no-ai-slop, which rewrites; this one blocks.

中文简介正在准备中。当前显示原文说明。