Results for “fr”

World-class voiceover expertise combining the narrative craft of documentary producers, the commercial precision of advertising agencies, and the accessibility of modern AI voice technology. Voiceover is the invisible art that makes or breaks video content. Great voiceover isn't just speaking clearly—it's performing the script in a way that creates the intended emotional response. The best voiceover work understands pacing, tone, emphasis, and the subtle art of making scripted words sound natural. It knows when to use human talent versus AI, and how to get the best from both. Use when "voiceover, voice over, VO, narration, narrator, voice recording, voice talent, voice actor, AI voice, text to speech, audio narration, voice direction, voiceover, audio, narration, voice, recording, AI-voice, talent, direction" mentioned.

Apply Boyd's OODA loop to navigate fast-moving, uncertain, or competitive situations — Observe what is actually happening, Orient through mental models and context, Decide on the clearest path, Act quickly, then loop again. Load when the situation is changing faster than the current plan, when a competitive response is needed, when the user is stuck in analysis paralysis in a dynamic environment, when shipping under uncertainty, or when deep-thinking diagnoses a fast-moving / competitive frame. Triggers on "what should we do right now", "the situation is changing", "how do we respond to this", "competitive response", "we need to move fast", or "we're stuck deciding". Based on John Boyd's OODA loop — Observe, Orient, Decide, Act — adapted for product and business contexts (OODA Canvas 2026).

Azure Cosmos DB SDK best practices for .NET, Java, Python, Spring Boot, and LangChain: singleton client, async APIs, connection modes, retry handling, diagnostics, serialization, emulator configuration, ETags, and framework-specific patterns. USE FOR: CosmosClient singleton, async API, Direct vs Gateway mode, retry 429, preferred regions, excluded regions, availability strategy, circuit breaker, SDK diagnostics, serialization enums, emulator SSL, ETag concurrency, conditional create, patch increment, continuation token, content response, Spring Data Cosmos, Spring Boot versions, Newtonsoft dependency, namespace collision, Python async deps, local dev config, LangChain Cosmos DB saver, LangGraph checkpointer, MCP persistent session, tool content format, tool filtering, LangChain JS vectorstore, chat history, semantic cache. DO NOT USE FOR: data modeling (use cosmosdb-data-modeling), queries (use cosmosdb-query-optimization), partition keys (use cosmosdb-partition-key).

Expert India Digital Personal Data Protection Act, 2023 (DPDPA) compliance advisor. Use this skill whenever a user asks about the DPDPA, DPDP Act, DPDP Rules 2025, India data privacy law, Data Fiduciary obligations, Data Principal rights, Significant Data Fiduciary, Data Protection Board of India, consent under DPDPA, notice requirements, breach notification India, children's data India, cross-border data transfer India, India privacy compliance, DPDPA gap analysis, DPDPA vs GDPR, or any obligation under India's personal data protection framework. Also trigger for: "Section 6 consent", "Section 7 legitimate uses", "Section 9 children's data", "Section 10 SDF", "Section 16 cross-border", "Rule 6 breach notification", "Rule 13 SDF obligations", "Data Protection Board complaint", "verifiable parental consent India", "DPDPA compliance roadmap", or "India privacy law global company".

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

BOM (Bill of Materials) management for electronics projects — the primary orchestrator skill that coordinates DigiKey, Mouser, LCSC, element14, JLCPCB, PCBWay, and KiCad skills into a unified workflow. Create, update, and maintain BOMs with part numbers, costs, quantities stored as KiCad symbol properties. ALWAYS trigger this skill for any task involving component sourcing, pricing, ordering, distributor searches, BOM export, or fabrication preparation — even if the user names a specific distributor or fab house (e.g. "search DigiKey for...", "generate JLCPCB BOM", "order from Mouser"). This skill decides which distributor/fab skills to invoke and in what order. Also trigger on phrases like "what parts do I need", "order components", "how much will this cost", "export for JLCPCB", "find parts for this board", "cost estimate", "compare pricing", or "check stock".

Compact the current conversation into a handoff document for another agent to pick up. Save to a user-configured location (OS temp, home folder, or per-project .handoff/), redact secrets before write, suggest skills for the next session, and auto-load the latest handoff on the next SessionStart. First-run setup asks where to save so the project folder never gets cluttered. Use when the user says 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact this conversation', 'I'm ending this session', 'pick this up later', or any variation signaling intent to pass work to a fresh agent. Also trigger on implicit signals: the user announcing they're switching machines, ending the day mid-task, or context is growing long without a natural stopping point.

UniFFI by Mozilla — generates idiomatic Kotlin, Swift, Python, and Ruby bindings from a Rust crate. Covers UDL definition, proc-macro mode, async support, callback interfaces, error handling, custom types, and the Kotlin Multiplatform fork (uniffi-kotlin-multiplatform-bindings) used by BDK, Breez SDK, CDK, LWK. USE WHEN: user mentions "UniFFI", "Rust to Kotlin", "Rust to Swift", "FFI bindings", "uniffi-rs", "UDL file", "uniffi-bindgen", "BDK bindings", "Breez SDK bindings", "kotlin-multiplatform-bindings", "Mozilla UniFFI" DO NOT USE FOR: Raw C FFI - use `languages/swift` interop quick-ref + Rust core DO NOT USE FOR: WebAssembly bindings - use wasm-bindgen DO NOT USE FOR: Flutter/Rust bridge - use `flutter_rust_bridge` skill if exists DO NOT USE FOR: React Native - use `uniffi-bindgen-react-native` (out of scope here)

Deep API security assessment beyond surface scanning. Covers the full OWASP API Security Top 10 (2023): Broken Object Level Authorization (BOLA / IDOR), Broken Authentication, Broken Object Property Level Authorization (mass assignment + excessive data exposure), Unrestricted Resource Consumption, Broken Function Level Authorization (BFLA / vertical privilege escalation), Unrestricted Access to Sensitive Business Flows, Server-Side Request Forgery via API parameters, Security Misconfiguration, Improper Inventory Management (shadow/zombie/deprecated endpoints, v1/v2 drift), and Unsafe Consumption of third-party APIs. Works across REST, GraphQL, gRPC, SOAP, and MCP servers. Discovers APIs from OpenAPI/Swagger specs, GraphQL introspection, gRPC reflection, .well-known endpoints, JS bundles, and traffic capture. Uses kiterunner, ffuf, schemathesis, restler-fuzzer, openapi-fuzzer, graphql-cop, clairvoyance, batchql, inql, jwt_tool, postman, mitmproxy, and manual http(action="request", ...) payloads. Every techniqu

Use BEFORE generating, refactoring, reviewing, or debugging code. Trigger phrases include "write a function/script/class for X", "review this code/diff/PR", "refactor this", "debug this error", "is this implementation correct", "what's wrong with this code", "improve this code", "translate from X to Y", or any prompt with a code block the user wants you to act on. Also fires when planning architectural changes, picking algorithms or data structures, or evaluating dependency upgrades. Calls the code MCP tool to retrieve an engineering scaffold (failure pattern, procedure, correct-pattern example, verification step) before generating. Catches hallucinated APIs, lost edge cases, premature algorithm commitment, silent contract violations, refactors that change behavior masked by passing tests. Do NOT trigger for pure code reading with no action requested, simple syntax questions, file...

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/image-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on "image to video", "image-to-video", "i2v", "animate image", "make this move", or any explicit ask to turn a still into video.

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/image-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on "image to video", "image-to-video", "i2v", "animate image", "make this move", or any explicit ask to turn a still into video.

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/image-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on "image to video", "image-to-video", "i2v", "animate image", "make this move", or any explicit ask to turn a still into video.

Universal LaTeX document skill: create, compile, and convert any document to professional PDF with PNG previews. Supports resumes, reports, cover letters, invoices, academic papers, theses/dissertations, academic CVs, presentations (Beamer), scientific posters, formal letters, exams/quizzes, books, cheat sheets, reference cards, exam formula sheets, fillable PDF forms (hyperref form fields), conditional content (etoolbox toggles), mail merge from CSV/JSON (Jinja2 templates), version diffing (latexdiff), charts (pgfplots + matplotlib), tables (booktabs + CSV import), images (TikZ), Mermaid diagrams, AI-generated images, watermarks, landscape pages, bibliography/citations (BibTeX/biblatex), multi-language/CJK (auto XeLaTeX), algorithms/pseudocode, colored boxes (tcolorbox), SI units (siunitx), Pandoc format conversion (Markdown/DOCX/HTML ↔ LaTeX), and PDF-to-LaTeX conversion of handwritten or printed documents (math, business, legal, general). Compile script supports pdflatex, xelatex, lualatex with auto-detect

Use when developing in packages/agent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI/Scope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the /api/v1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.

Federal Organizational Conflict of Interest (OCI) sweeper backed by FAR Subpart 9.5 (9.501-9.508) and the active Theseus workspace knowledge graph. USE WHEN the user asks about OCI risk on a bid, organizational conflicts, incumbent conflicts, biased ground rules, unequal access to information, impaired objectivity, or any pre-bid OCI due diligence. Pulls `company`, `incumbent`, `subcontractor`, `customer`, `program_office`, and prior-contract relationships from the workspace KG, classifies each potential conflict into one of the three FAR 9.505 classes (biased ground rules, unequal access, impaired objectivity), and emits a structured findings envelope with mitigation recommendations (firewall, NDA, recusal, novation). DO NOT USE FOR FAR clause coverage audit (use `compliance-auditor`), proposal prose (use `proposal-generator`), competitor research (use `competitive-intel`), or pricing (use `price-to-win`).

Application-level business logic security testing for any domain. Takes an understanding-first approach: map the intended workflows before probing them. Covers: value/quantity logic abuse (negative, zero, overflow, rounding on any numeric field), workflow and state machine bypass (skipping required steps, forcing illegal state transitions, reusing one-time tokens), trust boundary violations (BOLA horizontal/vertical, BFLA, cross-tenant access, negative ownership attacks), idempotency and replay attacks (duplicate submissions, double-spend, same-reference reuse), multi-step flow integrity (checkout, registration, approval, verification), quota and rate limit bypass, time/date manipulation, and authorization code / reference number predictability. Domain-agnostic — applies to SaaS, e-commerce, banking, gaming, social platforms, APIs, or any multi-user application with stateful workflows. Chains from /pentester; chains into /param-fuzz when boundary violations or mass assignment are confirmed.

Generates a structured developer-facing markdown document that teaches how a specific feature, module, or piece of functionality works in the codebase. Use this skill whenever the user runs `/teach`, asks "how does X work", "explain the auth flow", "document how payments work", "walk me through the webhook system", or any request to understand and document internal codebase functionality. Also trigger when the user wants to produce onboarding docs, feature walkthroughs, or "how it works" references for developers. Always use this skill even if the user only gives a vague description — use the provided context or file hints to locate the relevant code yourself and build the teaching doc from there. This skill writes for developers reading the codebase — for end-user/customer-facing help docs, use the eli5-features skill instead.

Conduct a design interview, generate 5 distinct UI variations in a temporary route, collect real click-to-comment feedback on the live rendered variants via human-review, and produce an implementation plan. Use when the user wants to explore UI design options, redesign an existing component/page, or create new UI with multiple genuinely different approaches to compare — before writing production code or committing to a direction. For a lighter, single-component variant picker with no interview, use `prototype` instead. For reviewing a UI that's already real (not exploring new directions), use `visual-review`. Source: adapted from github.com/0xdesign/design-plugin's design-lab skill (interview + 5-variant structure), with feedback collection replaced by this repo's own `visual-review` skill (human-review) instead of a bespoke overlay component.

EMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair skew, board edge radiation, PDN impedance, return paths, crosstalk, ESD protection, shielding, and magnetic leakage from switching inductors. Produces severity-ranked risk report with pre-compliance test plan. Supports FCC Part 15, CISPR 32, CISPR 25 (automotive), MIL-STD-461G. SPICE-enhanced when available. Use when the user asks about EMC, EMI, radiated/conducted emissions, FCC compliance, CE marking, CISPR, ground plane issues, decoupling strategy, clock routing EMC, switching noise, differential pair skew, or whether their board will pass EMC testing. Also for "will this pass FCC?", "check my EMC", "is my ground plane okay?", "check my decoupling", or "generate an EMC test plan".

Complete SEO + GEO (Generative Engine Optimization) system for SaaS companies wanting to rank on both Google and AI search engines (ChatGPT, Perplexity, Gemini, Claude). Use this skill whenever the user asks about SEO strategy, keyword research, content planning, writing SEO-optimized articles, auditing their search performance, creating a content calendar, analyzing competitors, or optimizing for AI search visibility. Trigger on: "seo", "keyword research", "content calendar", "rank on google", "search traffic", "write an article", "blog post", "serp", "backlinks", "competitor analysis", "content cluster", "seo audit", "geo optimization", "ai search", "search console", "organic traffic", "content strategy", "publish article", "seo setup", "ranking", "impressions", "ctr", "meta description", "schema markup", "faq schema". Also trigger when a user wants to set up their SaaS blog SEO from scratch, analyze their current rankings, or create a publishing workflow.

>- Analyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. Reviews designs for bugs, traces nets, cross-references schematic to PCB, extracts BOM data, checks DRC/ERC, DFM, power trees, and regulator circuits. Every finding carries a confidence label and evidence source with trust_summary rollup. Analyzes PDF schematics from dev boards, reference designs, eval kits, and datasheets. Supports KiCad 5–10. Use whenever the user mentions .kicad_sch, .kicad_pcb, .kicad_pro, PCB design review, schematic analysis, PDF schematics, reference designs, Gerber files, DRC/ERC, netlist issues, BOM extraction, signal tracing, power budget, DFM, or wants to understand, debug, compare, or review any hardware design. Also for "check my board", "review before fab", "what's wrong with my schematic", "is this ready to order", "check my...

Import recorded driving sensor data (GPS, camera, lidar, actor tracks, lanes) into scenariobuilder.* objects (GPSData, CameraData, LidarData, ActorTrackData, Trajectory, laneData) and run preprocessing — synchronize, offset correction, crop, normalizeTimestamps, convertTimestamps. Also: compute actor tracks from lidar when no annotations exist, attach camera/lidar mounting + intrinsics, export to MAT/workspace/timetable/script. Use for raw driving dataset files (KITTI, nuScenes, Waymo, Pandaset, ROS/ROS2 bags, .mat, .csv, .mp4) or driving/vehicle/sensor logs that need wrapping. drivingLogAnalyzer (DLA) is OPT-IN ONLY — invoke only on explicit user request ('DLA', 'open in DLA', 'inspect/explore/analyze the recording') or reported sensor problem (sync drift, timestamp mismatch, overlay misalignment). NEVER auto-launch DLA after wrapping (Rule 0). For 'build scenario / export to RoadRunner / drivingScenario / OpenSCENARIO / Unreal / simulate', hand off to matlab-use-scenario-builder.

Guide users through writing a systematic literature review (SLR) following the PRISMA 2020 framework. Use this skill whenever the user mentions 'systematic review', 'systematic literature review', 'SLR', 'PRISMA', 'PRISMA 2020', 'PRISMA flow diagram', 'PRISMA checklist', or asks for help writing, structuring, or auditing a literature review that follows reporting guidelines. Also trigger when the user asks about inclusion/exclusion criteria for a review, search strategies for databases like Scopus/WoS/PubMed, study selection processes, risk of bias assessment, or narrative synthesis for a review paper. This skill covers the full PRISMA 2020 checklist (27 items), produces a Word document manuscript in strict journal article format, generates an annotated PRISMA flow diagram, and enforces APA 7th Edition referencing throughout. It does NOT cover meta-analysis or statistical pooling. By Chuah Kee Man.

Deep web exploitation beyond initial scanning. Covers SQLi (blind, OOB, second-order), NoSQL injection (MongoDB, operator bypass), GraphQL injection (introspection, batching, mutation abuse), XSS (reflected/stored/DOM with full source-sink analysis), SSTI (Jinja2/Twig/Freemarker/ERB engine identification and RCE), SSRF chains, file upload bypass (polyglot creation), XXE (blind, DOCX/SVG injection, Content-Type switching), deserialization (Java/PHP/Python/.NET), command injection, path traversal (LFI wrapper bypasses), race conditions, CSRF, JWT attacks (none/key confusion/kid injection), HTTP request smuggling (CL.TE/TE.CL/H2), CRLF injection, open redirect bypass chains, CORS exploitation, web cache deception/poisoning, OAuth misconfiguration, prototype pollution, session management, and business logic flaws. Uses sqlmap (advanced modes), commix, xsser, wapiti, davtest, and manual http(action="request", ...) payloads. Every technique includes actual payloads, commands, and code snippets for immediate use. Ch

Build, modify, and ship Grafana dashboards as JSON via the HTTP API — panel types (timeseries / stat / gauge / table / heatmap / logs / traces / node-graph), `gridPos` 24-column layout, units, thresholds, template + datasource + chained variables, transformations (`organize` / `calculateField` / `filterByValue`), panel + dashboard links with `${__field.labels.x}` / `${__from}`, and Loki/Prometheus annotations. Use when scripting dashboard creation, writing the dashboard JSON for a new service, adding a `$job` dropdown variable, computing an "Error %" column with a transformation, overlaying deploys as annotations, or pushing a dashboard via `POST /api/dashboards/db` — even when the user says "create a dashboard for this metric", "add a service dropdown", "show errors as percentage", "overlay our deploys", or "export the dashboard JSON" without naming the API or schema. After every API push, verify with the returned `version` plus a GET on the dashboard UID.

Restructure existing code without changing its behavior, through a test-gated refactoring loop: a named target, a green suite over that target before any edit, a planned sequence of small named refactorings, and the full suite re-run after every step. Use when the user wants to refactor, restructure, clean up, simplify, or improve the design of existing code, or to apply refactoring recommendations from a code-review or architectural-analysis report. This skill changes code; it does not review code (use code-review), assess architecture (use architectural-analysis), or build new behavior test-first (use tdd). Do not use it on code inside an active tdd loop; the refactor step of tdd owns that cleanup. Runs its planned sequence to completion without pausing for review; to review each named refactoring as it lands, use pairing.

Drive Airship (`@airshiplabs/cli`), a CLI that puts a visual, pannable design canvas in front of a running dev server so an engineer can click an element, describe a change, and have Claude Code, Codex, or OpenCode edit the underlying source file directly — no plugin, no build config, nothing added to the project. Use when the user wants to launch a visual editor over a local dev server (`npx @airshiplabs/cli --target <port>`), pick or compare coding agents (`--agent claude|codex|opencode`) for live UI edits, sandbox agent edits with `--safe`, scaffold an `airship.config.json` (`airship init`), or diagnose a broken setup (`airship doctor`). Triggers on: "airship", "@airshiplabs/cli", "visual editor for my codebase", "click to edit UI", "design canvas over dev server", "airship doctor", "airship init", "pair Claude Code with a visual editor on localhost".

Route goalflow (wanmol/goal-flow) work — a LangGraph framework that combines workflow graphs with agent loops — into exactly one mode: fit check, transpiling a Dify DSL export into runnable LangGraph Python, authoring workflow nodes and edges, building an `agent_kit` loop with middleware and a harness, wiring the serving layer (data adapters, SSE streaming, HITL, Redis/MySQL, API-key registration), or running the pre-publish security gate. Use when the user wants Dify's visual design without Dify's runtime, a graph node that hosts an agent loop, an OpenAI-compatible wire protocol over their own workflows, or prompt-injected `SKILL.md` capabilities. Triggers on: goalflow, goal-flow, dify to langgraph, dify transpiler, dify DSL export, BaseWorkflow, agent_kit, AgentBaseNode, DataAdapter, chunk processor, HITL interrupt, dify2langgraph. Route plain graph-API questions to `langgraph-fundamentals` and `langgraph-workflow`.

Deep OAuth 2.0 / OpenID Connect security assessment. Covers the full attack surface: redirect_uri validation bypass (path traversal, open redirect chains, subdomain confusion, URL parsing tricks, parameter pollution, response mode switching), missing/broken state parameter CSRF, PKCE downgrade and absent-challenge attacks, implicit grant token leakage (Referer, browser history, XSS fragment theft), authorization code injection, scope escalation, client confusion attacks, mutable-claims account takeover (iss+sub confusion, email-keyed identity merging), pre-account takeover via unverified registration, OpenID Connect dynamic client registration SSRF (logo_uri, jwks_uri, sector_identifier_uri, request_uri), nonce replay, ID token validation failures, Device Code phishing flow, mobile custom URI scheme hijacking, refresh token persistence, token introspection enumeration, consent screen clickjacking, host header injection, and cross-IdP mix-up attacks. Uses KOAuth, jwt_tool, nuclei oauth templates, and manual ht

Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Generate driving scenes, scenarios, road surfaces, and 3D content from scenariobuilder.* sensor data (GPS, camera, lidar, actor tracks) using Scenario Builder for Automated Driving Toolbox. BUILD, EXPORT, or AUGMENT a virtual scenario/scene/map: ego or actor trajectories, trajectory smoothing, OpenCRG road-surface extraction, 3D asset generation, static-object placement, point-cloud georeferencing + elevation, lane-based ego localization, sensor-fusion tracking, scenario-event extraction (cut-ins, hard brakes, near-misses, ADAS disengagements), or export to RoadRunner, drivingScenario, OpenDRIVE, OpenCRG, OpenSCENARIO, or Unreal Engine. Also: log-to-scenario, scenario harvesting, accident/near-miss reconstruction, SOTIF (ISO 21448) and ISO 26262 scenario coverage, USGS-aerial-lidar augmentation, traffic-sign placement, vision-based vehicle classification for actor assets. NOT for raw-data import or multi-sensor sync/crop/offset/timestamp normalization — route those to matlab-import-driving-data.

Tactical fast path: turn a small problem, bug report, edit request, or narrow refactor into three deliverables — a brief change-spec (docs/specs/), a detailed implementation-ready plan (docs/plans/), and a TODO.md with agent-pickable tasks and milestones. Load when the user describes a tactical problem and wants quick planning artifacts, says "plan this change", "create a TODO", "write a plan for this", "problem to plan", "break this into tasks for agents", "I want to change X — plan it", or when process-decomposer routes here after determining the user needs lightweight planning deliverables. Also triggers on "create tasks from this problem", "make this actionable", or "turn this into a plan agents can execute". For feature-sized work that needs an executable spec + constitution + cross-check gate, route to `spec-driven-development` (or `feature-spec`) instead.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in...

Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to devnet", or "explain Solana concepts" (rent, accounts, PDAs, CPIs, etc.). Also use for quick on-chain lookups via public RPC + curl — "what's the balance of <wallet>", "look up transaction <sig>", "token balance for <account>", "check this address on mainnet/devnet". End-to-end Solana development playbook covering wallet connection, Anchor/Pinocchio programs, Codama client generation, LiteSVM/Mollusk/Surfpool testing, security checklists, and JSON-RPC curl lookups against public clusters. Integrates with the Solana MCP server for live documentation search. Prefers framework-kit (@solana/client + @solana/react-hooks) for UI, wallet-standard-first connection (incl. ConnectorKit), @solana/kit for client/RPC code, and @solana/web3-compat for legacy boundaries.