Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
Simulator.Company financial management specialist. Use when the user wants to manage financial and metric accounts on actors (balances, counters, plan vs fact), record transactions, transfer value between accounts, work with currencies and account-name categories, track non-financial metrics, read balances and…
Simulator.Company graph structure specialist. Use when the user wants to build, edit, analyze, inspect, or ask questions about business process graphs, flowcharts, algorithms, actors (nodes), links (edges), or layers (visual views) in Simulator.Company. Trigger on any of these intents: — Creating: "create graph"…
Author and evolve the Corezoid backend that powers a Simulator.Company Smart Form. Use whenever the user wants a Smart Form to do anything beyond a static layout — load dynamic viewModel data, react to submits, drive page-level changes, trigger notifications, write back to actors — OR wants to modify existing backend…
A post-coding self-check checklist for reviewing implementation quality and tests. It checks user-visible behavior, data consistency, dependencies, compatibility, code quality, and—when relevant—visual details against a design.
A skill for producing technical plan documents from requirements and clarification records. It describes expected behavior, acceptance checks, tasks, boundaries, dependencies, and unresolved questions.
Search and score AI-ready websites via MCP. Find MCP servers, check site AI-readiness scores, and verify MCP endpoint compliance using the Not Human Search API at nothumansearch.ai.
Stress-test any idea, proposal, or plan by finding its weakest points, probing hidden assumptions with Socratic questions, and identifying failure modes through red team analysis. Use when the user asks to stress-test, poke holes, find weaknesses, red team, challenge, or ask 'what could go wrong' or 'what am I…
Full adversarial analysis of any idea, proposal, or argument. Runs steelman, crucible, and verdict in sequence for a complete challenge drawing from 10 reasoning traditions. Use when the user asks to play devil's advocate, run a full challenge, or says 'tear this apart' or 'give me the full treatment'.
Deliver a structured verdict on any idea, argument, or proposal, identifying what survives scrutiny, what doesn't, and what needs more work. Includes the gadfly sting, the one uncomfortable truth nobody wants to say. Use when the user asks for a verdict, bottom line, final assessment, 'what survives', or 'give it to…
This skill should be used when the user says "check in", "clock in", "standup", "guild check in", "what's the status", "let's get to work", "start working", "daily standup", "guild standup", "I'm here", "reporting in", or any phrase indicating they want to begin or resume a guild work session. Acts as the guild…
Pre-loaded SvelteKit knowledge for the developer-svelte agent. Covers project structure, file-based routing (+page, +layout, +server, +error), load functions (universal vs server), form actions, page options (prerender / ssr / csr), building for production, and deployment via adapters (auto, node, static, vercel…
Pre-loaded Svelte 5 core knowledge for the developer-svelte agent. Covers the component model, runes ($state, $derived, $effect, $props, $bindable), basic markup, control flow, snippets, bindings, scoped styles, lifecycle, and context. Load this skill before writing or editing any .svelte, .svelte.ts, or .svelte.js…
Create a governed session override for a policy that would otherwise deny — mandatory justification, server-clamped TTL, blocked for critical-risk policies.
Surface the user's recent AxonFlow governance decisions — answers "what just got blocked", "show me my recent denials", or feeds a decision-history forensic flow.
Use when the user asks to read or change data in 101; routes every 101 goal to one available primary workflow while preserving the current chat context.
Use when the user asks how their finances, account, company, project, or object are doing; including vague questions such as "how are things going?" and requests to review financial risks.