增值税税率分类顾问——判断应税销售行为适用的增值税税率 （13%/9%/6%/零税率/免税），避免税率适用错误导致的 税务风险。适用情形：用户说"我们的产品适用哪种增值税税率"、 "混合销售和兼营怎么区分"、"技术服务是6%还是13%"、 "农产品增值税税率"、"不动产租赁和销售税率"、 "出口退税零税率适用条件"。
Archive a completed vault by moving it out of the active vaults/ directory. Optionally promote reusable knowledge first.
Create a new LLM Wiki vault with proper directory structure, index, log, and conventions. Use when user wants to create a vault, start a new wiki, or set up a new knowledge base.
Import an existing Obsidian vault, markdown folder, or git repo as an llm-wiki vault. Moves content into vaults/, adds missing structure (index, log, CLAUDE.md, frontmatter).
List wiki pages filtered by type, tag, or status. Use this for agentic search over the vault — narrow down relevant pages before reading them in full.
Search the vault for notes matching a natural language query. Triggers: "find notes about", "search vault", "which notes mention", "do I have anything on", "look up", "where did I…
Check context limits, optimize token usage, and debug context failures. Use when asking about rate limits, usage warnings, memory systems, or context-aware agent design.
Debug systematically with root-cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, CI failures, or system investigation.
Use when you need to analyze a codebase and initialize, update, or summarize project documentation.
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient…
Merge a git worktree branch back into the main Flowser checkout and clean up the worktree. Use when the user asks to merge, archive, or clean up a completed worktree.
Use when you need to inspect files or generate visual explanations, slides, diagrams, or HTML recaps.
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale…
Use when you need a read-only handoff summary of current branch state, local/remote refs, worktrees, active Flowser plans, selected-plan hints, and suggested next checks.
Use when you need to compare a local or remote repository, extract a feature idea, or prepare an adaptation study without planning or implementing it yet.
Run a comprehensive audit against all applicable VCP standards. Supports full audit, compliance-specific audit, and quick release readiness check.
View and modify VCP configuration. Add or remove ignore entries, toggle scopes, manage compliance frameworks, change severity threshold, and manage exclude patterns.
Initialize VCP configuration for this project. Creates global config (~/.vcp/config.json) if it doesn't exist, then creates project config (.vcp/config.json).
Analyze a proposed bug fix against VCP root cause analysis standards. Determines whether a fix addresses the root cause or just patches a symptom.
Cluster vectors by similarity using npx ruvector k-means or density-based methods with labeled group summaries
Generate embeddings via npx ruvector (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index
Embed hierarchical data in hyperbolic space via npx ruvector Poincare ball model, compute geodesic distances
First-run setup for
[email protected] — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`
Veda investment-advisor pipeline. Use when the user asks any investment, portfolio, buy/sell, sizing, valuation, cycle, macro, or risk-management question.
Check the status of existing agreements with a vendor across all connected systems — CLM, CRM, email, and document storage — with gap analysis and upcoming deadlines.
Identifies consolidation opportunities across the active vendor base — overlapping scopes, dual-source savings, single-source risk that should be split.
Scores a draft against ONE venue's real published reviewer criteria — per-criterion verdict with evidence quoted from the draft, plus the concrete gap for anything short.
Run a parallel veracity audit on any document, website, or portfolio. Launches 19 agents per run in 5 waves (1 decomposition + 3 waves of 5 verification agents + 1 relational…
Launches a built app and verifies it against the spec using browser/electron automation. Includes fix loop. Use after implementation to verify the app works as specified.
Compare provider DTOs and WireMock test payloads with live responses from the real public API (currently NBP), and capture real responses as test fixtures.
Audit whether a repo's docs actually ANSWER the questions a reader has — by spawning fresh, cheap (Haiku) agents that cold-read ONLY the docs and measuring how fast they reach the…
TRIGGER when: user asks 'is everything ready for opening night', user says 'check opening night readiness', session is an opening-night session for a Broadway or West End show.
Verify and fix a draft Xero payslip against expected figures. Reads employee config, calculates expected values, inspects Xero, compares, and applies corrections with user…
Verify implementation plans before execution using a 4-agent pipeline. Use when you have a written plan (from /bdk:create-plan or manual) and want to check if it will actually…
Check out a candidate PR locally, restart the MCP server on the PR branch, re-run the exact same MCP tool call that failed in /2-repro-issue, diff the outputs, and audit the fix…
Use when the user invokes /verify-release or asks to check whether a release has propagated, whether the marketplace is up to date, or whether installed plugins reflect the latest…
PR/구현 검증을 PM·비개발자도 이해할 수 있는 캡처 중심 HTML 리포트로 만든다. Jira/Notion/Slack/와이어프레임/PR test plan 같은 기획 근거를 사용자-facing 동작과 매핑하고, 핵심 UI 흐름은 스크린샷/GIF를 primary evidence로 증명한다.
Use for a technical incident, disputed diagnosis, bug fix, or claim that a change works. Reproduce, isolate, test competing causes, and repeat the original check before reporting…
Scans directory structure, detects missing documentation, and verifies code-doc synchronization. Use when checking module completeness, README presence, or DESIGN.md alignment.
Convert classical Chinese verses into image generation prompts — ink painting (default) or tech-noir variant.
Check boolean properties of version numbers — type checks (IsBeta, IsStable, IsRC, etc.) and comparison predicates (IsNewerThan, IsOlderThan, IsBetween).
Compare two versions to determine which is newer, older, or if they are equal. Use when implementing update-check logic, dependency resolution, or any ordering decision between…
Check whether a version satisfies a constraint expression (caret, tilde, wildcard, range operators). Use when resolving dependency compatibility, filtering versions by semver…
Read version lists from files, write sorted versions to files, or stream versions from any io.Reader.
Group versions by their version number series (major.minor). Use when you need to organize a large collection of versions into groups, find versions within a specific series, or…
Bump version numbers, modify version components, strip suffixes, or construct versions from parts.
Parse, validate, and extract structured components from version strings via SDK, CLI, or MCP. Covers NewVersion/MustParse, all Is* type checks, Segments, Core, Clone,…
Extract segments, sub-version, suffix weight, pure prefix, or group ID from a parsed version.
Query versions within a specific range, check if a version falls between two boundaries, or implement version constraints with inclusion/exclusion policies.
Sort a list of version strings or Version objects in natural (semantic) order. Use when you need to order versions, find the latest/oldest in a collection, or display versions in…
Check the status of a Verso project — phase progress, ticket states, blockers. Use when the user asks about progress, what's done, or what's blocked.
Pre-configured finance vertical pack for the ai-brain-starter substrate. Ships typed-memory categories for deals, counterparties, SOX 404 controls, and audit evidence; retention…
Pre-configured healthcare vertical pack for the ai-brain-starter substrate. Ships typed-memory categories for patient-scoped facts, clinical decisions, PHI-tagged docs, BAA…
Pre-configured legal vertical pack for the ai-brain-starter substrate. Ships typed-memory categories for matter management and privilege handling, retention defaults aligned with…
Summarizes very long texts (books, handbooks, biographies, codebases) using hierarchical multi-pass extraction with cheap model armies.
Improve by removing problems rather than adding solutions — use when a system or process has accumulated complexity and improvement by addition has hit diminishing returns
Open an app in Playwright and explore it as a real user with no prior knowledge. Report UX findings per page, test core flows, and suggest improvements.
Translate plan markdown files to Chinese and render as a tabbed HTML page with EN/CN toggle, served locally via Bun.
Generate a self-contained HTML viewer for any Claude Code session, including agent team sessions with full inter-agent DM timelines.