xiaolai

Detect language and docs framework from markers like package.json and mkdocs.yml.

Docusaurus docs: detection, config parsing, doc root, code-to-doc mapping, template.

MkDocs docs: detection, config parsing, doc root, code-to-doc mapping, template.

Plain Markdown docs: detection, doc root, layout, code-to-doc mapping, template.

Sphinx docs: detection, config parsing, doc root, code-to-doc mapping, template.

VitePress docs: detection, config parsing, doc root, code-to-doc mapping, template.

Docs for languages with no dedicated skill: docstrings, API extraction, heuristics.

Go documentation: doc comment conventions, API doc extraction, Go-specific patterns.

Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.

How to write Claude Code hooks: events, matchers, blocking vs advisory, paths.

How to write LLM system prompts: role, structured output, injection resistance.

How to write .claude/rules/ files: golden format, enforceability, budget, scope.

How to write SKILL.md files that trigger reliably, for any tool (open spec).

Claude Code artifact schemas: plugin.json, frontmatter, hooks, settings, tools.

Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.

NL artifact anti-patterns: vague quantifiers, bare prohibitions, oversized skills.

Coverage thresholds plus test quality: coverage without behavioral assertions fails.

Test lanes (unit, integration, e2e, contract): what goes where, triggers, coverage.

Mutation testing gate: per-language tools (Stryker, PIT, mutmut), weak assertions.

Core TDD policy: plan-first development, assertion and spec levels, completion gates.

Findings-first code review: severity order, test-gap findings, test-quality audit.

Test matrix for changed behavior, with an explicit assertion strategy per case.

Per-language test runners, coverage tools, mutation tools and dry-run probe commands.

Coverage thresholds plus test quality: coverage without behavioral assertions fails.

Audit the book-level callback graph that tracks setup → payoff edges across chapters. Verifies every planted anchor has its declared downstream payoff and every payoff still has its upstream plant. Catches orphaned plants and orphaned payoffs. Reads…

Build a structured responsibility-laundering case file from a historical, political, legal, corporate, war, or AI event.

Turn approved case files into chapter architecture for serious trade nonfiction.

Diagnose a chapter against the 10 reader-experience values in rule 12 (5 core + 5 craft) and build a defect map naming which values fail, with cited prose evidence, and recommending one of the five treatment classes from rule 08. Output is…

Prepare citation-ready notes for drafting, fact-checking, and legal review.

Audit chapter prose for verbose inline `[CITE:]` markers that violate rule-13's slug-only invariant. Inline `[CITE:]` brackets must carry only card slugs (separated by `;` for multi-source claims); full citation apparatus lives in the source-ledger card and…

Audit the book's cognitive arc — the discriminations and concepts the reader acquires chapter by chapter — against the actual prose. For each discrimination, verifies introduction, consolidation, and application in every required chapter. For each concept,…

Audit a chapter against its declared per-chapter contract (Hoare triple of reader-state pre/postconditions) and verify the chapter delivers the declared `knows`, `can_discriminate`, `feels`, and `primed_for` slots. The `feels:` slot resolves through rule 12…

Audit a generated candidate EOU set for boundary quality, minimality, overlap, authority, operational value, and governance risk.

Create a formal EOU Change Proposal from a diagnosed failure or refactor option.

Audit EOU specs for Foundry V2 faceted classification, authority limits, schemas, validation, failure modes, trace, blast radius, and responsibility ownership.

Diagnose EOU failures using the Foundry failure taxonomy and recommend the smallest repair path.

Use when the user asks to initialize, scaffold, or create a new EOU-governed application. Creates a sibling directory with foundry/, instance copies of plugin templates, a starter constitution, and an initial git repo. Refuses to overwrite an existing…

Evaluate whether an EOU should be promoted, deprecated, or retired based on evidence, maturity model, audits, and owner approval. Produces a recommendation only — does not execute any lifecycle transition.

Generate candidate EOU refactor options from an audit or incident. Does not apply changes directly.

Convert an approved candidate into a formal EOU spec using Foundry V2 faceted classification and governance constraints.

Use for a sentence-level clarity review of developer prose: flags run-on sentences, ambiguous pronouns and references, deeply nested clauses, zombie subjects, buried leads, and terminology drift (one concept called by several names across a README or doc).…

Recurring non-native English slips: articles, prepositions, tense, 'I am agree'.

Use when the user wants to see or change english-buddy settings: auto-correction on/off, summary language, strictness (gentle / standard / strict), or domain terms the coaching hook must never correct. Shows the merged project + global config with the source…

Use when the user wants to practise their recurring English mistakes: a spot-quiz that shows one developer-context sentence per round with an intentional error from their top-3 mistake categories, asks them to correct it, then grades the answer and states the…

Use for a fast, mechanical grammar and punctuation pass on developer prose: flags spelling, agreement, tense, article, preposition, punctuation, and recurring non-native (L2) errors sentence by sentence, and returns a minimally corrected version. Does not…

English grammar for developer prose: articles, agreement, tense, prepositions.

Use when the user asks for their top recurring English mistakes across all their history (default top 20), grouped by category with the rule behind each. For a dated trend use $english-buddy-stats; to practise the mistakes use $english-buddy-drill.

Use when the user wants a dry run: show what WOULD be corrected in a prompt, commit message, or PR description before they submit it, without logging anything to the correction history. Runs the full grammar, tone, and clarity review and adds a…

Build or update MCP server/client integrations for VMark. Use when configuring MCP servers, adding MCP tools, or updating MCP-related docs and settings.

Implement or modify VMark's Rust/Tauri backend. Use when adding Tauri commands, menu items, filesystem integration, or platform behaviors in src-tauri.

Implement or adjust VMark frontend <-> Tauri v2 integration. Use when adding invoke/emit bridges, menu accelerators, or IPC-related UI behaviors.

E2E testing expert for Tauri applications using Tauri MCP server. Use when testing running Tauri apps - session management, webview interaction, IPC verification, screenshot capture, and debugging. ALWAYS use tauri_* tools, NEVER Chrome DevTools MCP for Tauri…

Translate VMark documentation and app strings to all 9 supported locales with subagent-driven audit, proofreading, and cultural polish. Use when adding or updating website pages, React locale JSON (src/locales/en/*.json), or Rust locale YAML…

Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.

Audit an implementation against a plan (dev-docs/plans/*). Use when a user asks to check for gaps, logic errors, or missing tests relative to a plan or Work Items.

Verify a completed implementation against a plan by running gates and checking acceptance criteria. Use when the user asks to verify work items or confirm completion.

Use when creating, editing, or reviewing a cc-suite advisor agent (a value-over-rules persona under `.cc-suite/agents/`). Covers system-prompt phrasing, model choice, tool restrictions, working-dir scoping, budget/turn limits, and the file format. Use…

Full audit→fix→verify cycle: Claude audits, Codex fixes, Claude verifies. Repeats up to 3 rounds until all issues are resolved or the user stops. Claude does all code reading and judgment; Codex does all file editing.

Ask Claude Code to audit a file or set of files and return structured findings. Claude reads the code with fresh eyes and independent judgment — Codex does not self-review. Supports mini (5-dimension) and full (9-dimension) depth.

Send a bug or failing test to Claude Code for root-cause analysis and fix. Use when you've hit an error you can't trace, a test is failing for unclear reasons, or a behavior is wrong and the cause is deep in the codebase.

Delegate an implementation task to Claude Code. Use when you want Claude to write, edit, or refactor code directly in the project. Claude has full read/write access and will make the changes autonomously.

Ask Claude Code to produce an implementation plan before you write code. Use when the task is complex, touches multiple files, or has unclear requirements. Claude returns a numbered step-by-step plan with file paths and interfaces — you implement it.

Delegate a code review task to Claude Code via the claude_code MCP tool. Use when you want Claude's judgment on architecture, security, correctness, test coverage, or code quality for files you've just written or modified.

Ask Claude Code to verify that a list of reported issues has been fixed. Continues the same Claude session from a prior audit if session_id is available, so Claude has full context of what it flagged. Returns FIXED / NOT FIXED / PARTIAL / REGRESSED per issue.

Claude Code (the CLI) reference. Use for .claude/settings.json / settings.local.json, hooks (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, etc.), slash commands, agents, MCP servers in .mcp.json, plugins and marketplaces, ANTHROPIC_* / CLAUDE_*…

Anthropic news + research digest, refreshed daily from anthropic.com/news + /research. Use for TIME-SENSITIVE questions: model launches ("did Claude X just release?"), product announcements, partnerships, region launches, research papers, recent policy,…

Anthropic Messages API reference. Use for POST /v1/messages, tool_use/tool_result, count_tokens, batches, streaming, prompt caching (TTL, breakpoints), anthropic-beta headers, admin API (API keys, workspaces), compliance (residency, audit logs), model…

Anthropic platform features above the raw API. Use for Agent Skills, hosted MCP connector + Tunnels, computer use/code execution/bash, extended thinking, batches, prompt caching strategy, citations, Bedrock/Vertex, embeddings, fast mode, context editing,…

Claude Agent SDK (TS @anthropic-ai/claude-agent-sdk, Python claude_agent_sdk), wrapping Claude Code. Use for query()/ClaudeSDKClient, SDK hooks, subagents (AgentDefinition), SDK MCP servers, permissionMode/permission_mode, structured outputs, Docker/K8s…

Claude Connectors (user-facing MCP integrations on claude.com). Use for enabling a connector, building a custom connector, OAuth + tokens, submitting to the connectors directory, GitHub/Google/Microsoft/Slack connectors, Desktop extensions (MCPB), MCP Apps…

Claude Cowork (Claude for Work on third-party clouds) and Office agents. Use for deploying Claude for Work on Bedrock or Microsoft Foundry, LLM gateways, enterprise SSO, telemetry / audit logs, the M365 connector, enterprise policy controls, Claude in Excel,…

Model Context Protocol (MCP) open spec. Use for writing an MCP server or client (any language; TypeScript @modelcontextprotocol/sdk, Python mcp), JSON-RPC framing, initialize handshake, capability negotiation, stdio/streamable HTTP/SSE transports, defining…

Use when the user asks to grill, roast, audit, interrogate, deep-review, or do a multi-angle architecture review of a codebase or directory. Orchestrates 4-6 specialized analysis skills (recon, architecture, error-handling, security, testing, optionally…

Conventions for grill agents: output format, severity ratings, evidence standards

Use to deeply analyze core architecture — entry points, module boundaries, dependency graph, data flow, and structural patterns. Part of the grill deep-dive phase. Also useful standalone when suspecting circular dependencies, inappropriate coupling, or…

Core conventions for all grill analysis skills — output formatting, severity ratings, evidence standards, and untrusted-input handling. Load whenever a grill analysis skill is active.

Use to hunt for edge cases, race conditions, boundary values, partial failures, and implicit assumptions across a codebase. Part of the grill deep-dive phase under Paranoid Mode. Also useful standalone after a production incident from unexpected input, to…

Use to analyze error handling, logging, observability, and configuration management across a codebase. Part of the grill deep-dive phase. Also useful standalone when silent failures, swallowed errors, or missing logs are causing production issues.

Use for initial codebase reconnaissance — quickly survey project structure, tech stack, config files, and existing documentation to establish context before deeper analysis. Always the first skill run during a grill review, and also useful standalone when…

Use to analyze the security surface of a codebase — authentication, authorization, input validation, secrets handling, and dependency vulnerabilities. Part of the grill deep-dive phase. Also useful standalone before an external pen test or security audit, to…

Use when the user asks to grill, roast, stress-test, red-team, pressure-test, or deep-review an argument, claim, essay, proposal, memo, or piece of reasoning. Maps the claim, attacks it from five adversarial angles (logic, evidence, counter, assumptions,…

Hunt an argument's silent load-bearing premises and the boundaries where its claim breaks — hidden assumptions, over-generalization, boundary failures, and base-rate/context-transfer errors. Part of the reason-grill deep-dive.

Core conventions for all reason-grill analysis skills — the calibration gate, severity scale, repair-cost tags, finding format, three-finding budget, and untrusted-input handling. Load whenever a reason-grill analysis skill is active.

Red-team an argument — build the strongest steelmanned case against the thesis and test whether the argument survives it. Part of the reason-grill deep-dive; also useful before defending a position, to surface the objections it fails to pre-empt.

Test whether an argument's premises are true, supported, and calibrated — unsupported claims stated as fact, confidence miscalibration, cherry-picking, correlation-as-causation, unfalsifiable claims. Part of the reason-grill deep-dive.

Test whether an argument's framing is honest and how it behaves under objection — motte-and-bailey structure, dodged objections, loaded framing, authority/emotion substituting for reasoning, and uncalibrated certainty. Part of the reason-grill deep-dive.

Test the validity of an argument's inference — does the conclusion follow if you grant the premises? Hunts non-sequiturs, circularity, equivocation, and quantifier slips. Part of the reason-grill deep-dive.

Map an argument before critique — extract the central claim, explicit and implicit premises, inference structure, claim type, and evidence offered. Runs first in a reason-grill interrogation; also useful standalone to disentangle what a piece of writing is…

Decision logic for home network work — isolating whether a problem is the device, the Wi-Fi, the router, or the ISP before spending money; the fix ladder from free to hardware; router and mesh buying judgement; and the boundaries of whose network may be…

Core conventions for all mac-it-guy-pro commands and agents — the safety contract, plain-language rules, report formats, and state file layout. Load before any IT task (checkup, cleanup, organize, fix, automate, backup, onboard).

How the IT guy remembers, refreshes, and retires what it knows about this machine — the profile schema, provenance classes, expiry by evidence, the belief ledger, demotion to history, the visit log, and undo manifests. Load when reading, writing, reviewing,…

Exact macOS commands for IT diagnostics and safe actions — disk, memory, startup items, updates, Time Machine, battery, SMART, duplicate detection, Trash-based deletion, HEIC conversion, photo dates, launchd scheduling. Load before running any diagnostic or…

Decision logic for building a personal unrestricted-internet connection from a censored network — which architecture to use (CDN-fronted vs direct), which protocols work and which are detectable, and the boundaries of what to help with. Load before any…

The micro-product contract for the IT Guy toolbox — acceptance criteria, directory layout, README template, registry schema, dry-run requirement, double-clickable wrappers, the evolution ladder, and the pattern catalogue used to offer a user automations they…

How the IT guy explains rather than just fixes — the two teaching modes (just-in-time and deliberate study), the learning-map structure, grounding lessons in the user's own measurements, depth scaling, and the pull-not-push rule. Load before any…

Use when the user wants help looking after their Mac — a health checkup, reclaiming disk space, organising files, diagnosing a problem in plain language, setting up backups, fixing Wi-Fi or a home network, automating a repetitive chore, or understanding what…