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.

Run a deep root-cause investigation on the AWS DevOps Agent. Use when the user describes an incident, alarm, outage, or unexplained behavior — keywords like "5xx", "503", "OOM", "latency spike", "deployment failure", "rollback", "sev1", "investigate", "root cause", "debug", "alarm fired", "service down". Polls and streams progress, then surfaces recommendations.

Prepare a guarded release of hacs_waste_collection_schedule. Use when a maintainer asks for the next release, a target version, changelog drafting, a manifest bump, or a release pull request.

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

caddy-security crypto directive configuration for authentication portals and authorization policies. Use when creating, reviewing, or debugging crypto Caddyfile lines, JWT signing or verification keys, token names and lifetimes, key IDs, HMAC/RSA/ECDSA/Ed25519 key loading, auto-generated keys, env or secrets-backed crypto values, System API crypto keys for remote Basic/API-key authentication, and authenticate/authorize key compatibility.

caddy-security authorization policy Caddyfile configuration. Use when creating, reviewing, or modifying security authorization policy blocks, route-level authorize directives, ACL rules, allow or deny shortcuts, bypass rules, crypto verification keys, auth redirects, bearer token validation, basic or API key auth proxy settings, user identity fields, and injected claim headers.

caddy-security authentication portal Caddyfile configuration. Use when creating, reviewing, or modifying security authentication portal blocks, route-level authenticate directives, portal crypto, token refresh blocks, enabled identity stores, OAuth or SAML identity providers, SSO app providers, trusted redirects, source address validation, or portal wiring. For cookies, UI, and user transforms use the focused authentication subskills.

Reviews GitHub pull requests through specialist review agents, runs repository validation, verifies corrections, aggregates findings, and posts the result. Defaults to code, seam, and simplification review; the operator can add scopes or explicitly request only selected scopes. Use when the operator asks to review a PR, re-review fixes, check whether a PR is ready to merge, run review agents, or invokes /prp-review.

Interactive PRD generator - problem-first, hypothesis-driven product spec. Use when the user wants to create a PRD, write a product or feature spec, scope a new product, or invokes /prp-prd.

Convention for reporting errors from multiprocessing TTS workers to the main process frontend. Use this skill when modifying, adding, or debugging TTS workers in tts_client.py to ensure connection errors, quotas, and API limits correctly display Toast notifications to the user rather than failing silently.

This skill should be used when the user asks to "review the prompt", "audit the system prompt", "check prompt quality", "inspect what the LLM sees", "debug prompt issues", or "find prompt engineering problems". Pulls the live rendered prompt via the API, explains how it's composed, and reviews it for issues.

Look up official Svelte, SvelteKit, and Svelte CLI documentation.

Use when neutralizing powerful local elites without violence. Relocates wealthy families (豪桀并兼之家) to the capital region, simultaneously strengthening the center (内实京师) and dissolving regional power bases (外销奸猾).

Use when defending against cavalry in open terrain with no natural cover. Deploys armored wagons (武刚车) in a circular formation to create a mobile fortification, enabling cavalry sorties and counterattack when conditions shift.

Use when deciding the fate of a defeated general who returns after losing their forces. Convenes advisors, weighs strict versus lenient views, and defers to higher authority rather than unilateral execution.

Use when mapping Xiongnu governance hierarchy. Covers the Shanyu (单于), Four Great Kings, 24 Wanqi commanders, territorial east/west/center divisions, noble clans (呼衍, 兰, 须卜), and subordinate officer structures.

Use when captured by enemy forces and seeking to escape. Involves feigning death or injury, observing guards and resources, then seizing a sudden opportunity to commandeer a horse and flee to friendly territory.

Use when applying disciplined archery in combat or hunting. Prioritizes shot certainty over volume of fire, conserving ammunition and maximizing psychological impact through patience and precise target assessment.

Use when evaluating whether to wage war against nomadic or mobile enemies. Applies cost-benefit analysis using distance, terrain, force degradation, and the crossbow metaphor (彊弩之极) to recommend diplomacy or engagement.

Use when advising a ruler or superior during a political crisis. Employs historical analogies, proverbs, and consequence analysis to persuade leaders to take difficult but necessary action.