Use when the user wants a concept, spec, RFC, protocol, API or mechanism explained as a published interactive HTML page in the visual-harness repo — "/explain X", "make a page for X", "visualise X", "add X to the index", "explain and push". Also use when they paste a link and ask to turn it into an explainer.

Ingest a source into the wiki — read it in full, compile durable cited pages, and update the index, log, and overview in one commit. Accepts files in raw/, URLs to fetch and archive first, a directory of a code repo read in place, or the answer /kb-ask just gave. Use when the user says ingest, compile this source, add this to the wiki, or pastes a link to read into it.

Answer a question from a knowledge base, read-only, with citations to wiki pages and raw sources. Use for any question about the wiki's subject matter, or when the user says ask the wiki, what do we know about, or query.

Scaffold a new LLM-maintained markdown wiki — ask what it is about, then write CLAUDE.md, the wiki skeleton, and the first commit. Use when the user asks to start, bootstrap, or set up a new wiki or knowledge base.

Health-check a knowledge base and report structural, content, and cross-reference problems by severity — dead links, index drift, orphans, stale claims, unresolved contradictions. Reports only; never repairs without approval. Use when the user says lint, health check, review the wiki, or check consistency.

Wallet tracking and monitoring on Binance Web3. Monitor token/trade activity for private groups or public Smart Money/KOL data. Four domains: (A) Discovery — consensus, pioneer, leaderboard diff, token buyer lookup, time-window summaries, similar wallets; (B) Evaluation — token risk (tokenRiskLevel ≥ 3), group rhythm, follow list assessment, token heat; (C) Replay — 4h summary, Accumulation/Distribution, sector rotation, anomaly orders, round-trip, first-mover/leader-follower, wake-up, bot-like; (D) Management — group create/rename, batch import, label update, link, follow list; (E) Real-time — WebSocket push for Smart Money, KOL, wallet-level, and address-level trade events. Trigger on: wallet tracker, monitoring, consensus, pioneer, accumulation, Distribution, Sector Rotation, Anomaly Large Order, round-trip, first-mover, wake-up, bot-like, token risk, token heat, group profile, similar wallets, group management, address import, follow list, real-time push, WebSocket — even without "tracker" explicitly.

On-chain trading signals and custom signal strategy management on Binance Web3. Three signal sources: smart money (wallet buy/sell events), platform strategies, and user-created strategies (meme / fomo). Four scenario domains: (A) Reports — daily report, monthly backtest review (BSC vs Solana, protocol comparison); (B) Signal discovery — feed, sort by maxGain or multi-strategy hit, token buyability ("can I still buy"); (C) Analysis — backtest interpretation, strategy comparison by golden/silver/bronze rate, indicator impact (KOL holdings, protocol, liquidity); (D) Management — create/update/delete strategies, enable/disable strategies, trigger/schedule backtests, query credits, auto-scan, copy strategies from the strategy hall. Trigger whenever the user mentions trading signals, smart money, custom signal strategies, backtesting, strategy management, daily or monthly reports, token buyability, or indicator impact analysis — even if they don't say "signal" or "strategy".

Development workflows for the playwright-cli repository. Use when the user asks about rolling dependencies, releasing, or other repo maintenance tasks.

Generates architecture diagrams from Terraform code. Use when user has .tf files or asks to visualize Terraform infrastructure.

Visualizes Azure infrastructure from ARM templates, Azure CLI, or descriptions. Use when user has Azure resources to diagram.

Visualizes AWS infrastructure from CLI output, CloudFormation, or descriptions. Use when user has AWS resources to diagram.

Generates architecture diagrams from code, infrastructure, or descriptions. Use when user asks to visualize, diagram, or document system architecture.

Use to design, understand, tune, or audit a non-trivial model workflow, including framework-undecided designs, partial implementations, and production reviews: model-node responsibilities, input/output completeness, data-flow correctness or redundancy, model-versus-Host/workflow ownership, topology, evidence, lifecycle, concurrency, or observed execution effects. The user need not say Prompt review or name Agently. Use agently-request for one request family and agently-triggerflow for already-decided executable orchestration details.

Create source-grounded paid-ad campaign concepts, messaging, copy, creative briefs, and production plans from a validated brand profile, campaign objective, platform requirements, and optional audit evidence. Triggers on: campaign brief, campaign concepts, create a campaign, ad concepts, ad copy, ad messaging, creative brief, headlines, descriptions.

Query the Pulumi Context API, a graph query interface over an organization's infrastructure in Pulumi Cloud. Use when a question is about relationships or reachability across resources and stacks: the impact of a change ("what breaks if I change this?", blast radius), what depends on a resource or a stack's outputs, which provider instances manage which resources and at what versions, orphaned or unreferenced resources, or references that cross stacks and cloud accounts, including resources Pulumi doesn't manage. Don't load it for finding a single resource by name, type, or property (Resource Search covers that), or for update history and failure debugging (use skill `pulumi-debug-failed-operation`).

cli reference to help with the development of constructor fabric gears framework. It helps with the development of the framework from its initialization, adding/removing gears, modifying configuration files, build and/or run project, lint the project and managing applications through its manifest. Always load this skill whenever you detect Gears.toml or you locate a reference to gears, cargo-gears, gears-toolkit, gears, plugins or packages that include the prefix cf- in its name.

Use this skill whenever delegating work to subagents — whether a single Task call or a full team via TeamCreate. Guides delegation, task decomposition, agent selection, and coordination. Covers when to spawn architect (design decisions, trade-offs), researcher (explorations, technical investigation), developer (FEATURE specs and code), tech-writer (documentation), qa (post-implementation validation), and architecture-critic (stress-testing architect output). Trigger on any subagent spawn, team creation, multi-agent coordination, or parallel work request.

Invoke when user asks to do something with Cypilot, or wants to analyze/validate artifacts, or create/generate/implement anything using Cypilot workflows, or plan phased execution. Core capabilities: workflow routing (plan/analyze/generate/auto-config); deterministic validation (structure, cross-refs, traceability, TOC); code↔artifact traceability with @cpt-* markers; spec coverage measurement; ID search/navigation; init/bootstrap; adapter + registry discovery; auto-configuration of brownfield projects (scan conventions, generate rules); kit management (install/update with file-level diff); TOC generation; agent integrations (Windsurf, Cursor, Claude, Copilot, OpenAI).

Review Rust changes against idiomatic Rust guidelines and ToolKit framework rules. PR mode posts inline comments on GitHub; local mode reviews a branch against main and writes a markdown report.

Use when reviewing the architecture & structure of Skylark code — a PR diff, the whole codebase, or one module. Hunts duplication, hard-to-test code, cleverness, deep nesting, files over 1k lines, weak seams (loose coupling + acyclic deps), and chances to do the same work in far fewer lines. Ambitious by design — for a crew with a high craft bar.