Husk

Dual-context skill: Personal TELOS reads and updates goals, beliefs, narratives, strategies, and more with timestamped backups; Project TELOS analyzes .md/.csv directories for dependency chains, bottlenecks, and alignment, generating reports, narrative points, or dashboards. USE WHEN Telos, life goals, projects, dependencies, update TELOS, narrative points, McKinsey report, dashboard, what am I wrong about, life frames, mental models. NOT FOR conversational constitutional review (use Interview).

Static visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Flux, Nano Banana Pro, and GPT-Image-2. USE WHEN art, illustration, diagram, flowchart, infographic, header image, blog social thumbnail, visualize, generate image, mermaid, architecture diagram, comic, icon, blog art, framework diagram, D3 chart, remove background, wallpaper. NOT FOR locked house-style YouTube/channel/video thumbnails (use _THUMBNAIL — it orchestrates Art's Generate/PickExpression/ThumbnailText tools), video or animation (use Remotion), or web UI design and integrated frontend layout (use Webdesign).

Meta-prompting standard library for generating, optimizing, and composing prompts programmatically via Standards, Handlebars Templates, and Tools; output is always a prompt to use elsewhere, not final content. USE WHEN meta-prompting, template generation, prompt optimization, prompt engineering, write a prompt, create system prompt, Handlebars template, eval prompt, judge prompt. NOT FOR generating final content (use the appropriate domain skill).

3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis — to surface design tensions, scope recommendations, and coherence assessments invisible at any single zoom level. USE WHEN aperture oscillation, oscillate scope, zoom in and out, tactical vs strategic, scope framing, design tension, system coherence check, local vs global design, wrong scope, scope negotiation. NOT FOR lens rotation across angles (use IterativeDepth).

Curated aphorism collection with CRUD — content-based matching, themed search, thinker research, DB maintenance. Quotes organized by author/theme/context/usage to prevent repetition. Four workflows: FindAphorism, AddAphorism, ResearchThinker, SearchAphorisms. Themes: Stoicism, Wisdom, Truth-seeking, Excellence, Resilience, Curiosity. USE WHEN aphorism, quote, find a quote, research thinker, add aphorism, quote for newsletter, what did X say about, quote bank. NOT FOR creative writing or social posts.

Scrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls — filtering in code. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business intelligence, multi-platform social listening, competitive analysis, lead generation, social monitoring, Apify actors, web crawl, extract contacts. NOT FOR X/Twitter operations (use _X), 4-tier progressive scraping with proxy escalation (use BrightData), or real-Chrome bot bypass and computer use (use Interceptor).

Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses arXiv Atom API across cs.AI/cs.LG/cs.CL/cs.CR/cs.MA/cs.SE/cs.IR. Three workflows: Latest, Search, Paper. USE WHEN arxiv, papers, latest papers, research papers, recent ML papers, paper lookup, summarize paper, latest LLM papers, AI safety papers, cs.AI latest. NOT FOR general research (Research), URL parsing (_PARSER), or annual reports (_ANNUALREPORTS).

AI audio editing pipeline: Whisper word-level transcription → Claude segment classification (KEEP/CUT_FILLER/CUT_FALSE_START/CUT_STUTTER/CUT_DEAD_AIR) → ffmpeg with 40ms qsin crossfades and room-tone fill → optional Cleanvoice cloud polish. Distinguishes rhetorical from accidental pauses; breaths attenuated 50%. Modes: --preview, --aggressive, --polish. Workflow: Clean. USE WHEN clean audio, edit audio, remove filler words, clean podcast, remove ums, cut dead air, polish audio, trim recording, cut stutters. NOT FOR video composition (use Remotion).

Divergent ideation and corpus expansion via Verbalized Sampling plus extended thinking — single-shot generates several internally diverse candidates and surfaces the strongest, or expands a seed corpus into a diverse dataset for evals and test sets. USE WHEN be creative, brainstorm, divergent ideas, creative solutions, maximum creativity, tree of thoughts, radically different, name this, creative angle, expand this corpus, synthetic data, generate diverse examples, create test set. NOT FOR multi-cycle evolutionary ideation with Lamarckian meta-learning (use Ideate).

Three-layer bias analysis on any URL, file, or text — auto-fetches the content and any cited study, then audits data-level biases, source conflicts of interest, and journalism-added distortions, separating what the data supports from what's editorialized. USE WHEN bias analysis, analyze bias, bias check, check this study, who funded this, is this source biased, fact-check article, methodological flaws, source credibility, what's wrong with this claim. NOT FOR psychological author analysis (use _CRITICAL_ANALYSIS), research synthesis (use Research), entity due diligence (use _OSINT).

Audits any AI instruction set for over-prompting using the core test — would a smarter model make this rule unnecessary? Applies Five Questions to every rule (Claude already does this? Contradiction? Redundant? One-off fix? Vague?) then classifies as CUT/RESOLVE/MERGE/EVALUATE/SHARPEN/MOVE/KEEP. Workflows: Audit (full system, token savings), QuickCheck (single file). Principle: less scaffolding = better output. USE WHEN BPE, bitter pill, audit setup, over-prompting, trim instructions, dead weight, simplify setup, clean up CLAUDE.md. NOT FOR attacking logical flaws in ideas (use RedTeam).

4-tier progressive web scraping that auto-escalates WebFetch to curl to Interceptor to Bright Data proxy for bot detection and CAPTCHAs, with single-URL and multi-page crawl modes, output as markdown. USE WHEN Bright Data, scrape URL, web scraping, bot detection, crawl site, CAPTCHA, can't access, site blocking, extract page content, scrape whole site, spider domain, convert URL to markdown, getting blocked. NOT FOR simple public content (use WebFetch directly), social platform scraping with named actors (use Apify), or real-Chrome bot bypass with logged-in sessions and zero CDP fingerprint (use Interceptor).

Drives cmux as an agent cockpit to boot, race, and monitor visible agent teams. Mac-only. USE WHEN cmux, agent cockpit, boot an agent team, orchestrate agents, three-tier orchestration, agent race, needle-in-haystack hotfix, agent fleet, 2x2 fleet, watch/monitor my agents, scale compute to scale impact, send a prompt to a running agent, multiplexer, terminal cockpit, orchestrator lead worker. NOT FOR one-shot in-harness subagents with no terminal to watch (use Delegation/Agent/Workflow), the Pulse dashboard itself (cmux feeds it, use Pulse), browser deploy-verification (use Interceptor), or Linux/Windows (cmux is Mac-only — use tmux).

Find prior LifeOS work — sessions, ISAs, conversations — by topic or date phrase; searches the work registry, titles, dir names, ISA bodies, and conversation logs, ranked by relevance. USE WHEN context search, prior work, browse sessions, recall, remember, previous sessions, context recovery, what did we do, find session, search history, what was that project, pick up where we left off, resume, look up old work, cold start, yesterday's work, last week, find that session, the one about. NOT FOR searching published content like blog posts/newsletters/tweets (use _CONTENTSEARCH) or the typed-graph Knowledge Archive (use Knowledge).

Multi-agent collaborative debate producing visible round-by-round transcripts with real intellectual friction — members are topic-briefed custom agents, run as a 3-round DEBATE or a 1-round QUICK check, to find the best path. USE WHEN council, debate, multiple perspectives, weigh options, deliberate, get different views, what would experts say, pros and cons. NOT FOR pure adversarial attack (use RedTeam).

Generates production-ready TypeScript CLIs via a 3-tier template system (manual arg parsing, Commander.js, oclif), each shipping full implementation, docs, package.json, strict config, JSON output, and exit-code compliance. USE WHEN create CLI, build CLI, command-line tool, wrap API, add command, upgrade tier, TypeScript CLI. NOT FOR LifeOS skill scaffolding (use CreateSkill).

Mandatory orchestrator for all LifeOS skill work — creating, editing, adding a workflow or tool, renaming, validating, or canonicalizing any skill. Handrolling skill files is forbidden; owns the full lifecycle: scaffold, validate, canonicalize, test, improve. USE WHEN create skill, new skill, make a skill, build a skill, set up a skill, private skill, make a X skill, add a workflow, add a tool, edit/change/update/rename a skill, skill frontmatter, validate skill, check skill, canonicalize, scaffold skill, test skill, improve skill, optimize description, skill not triggering, overtriggering. NOT FOR TypeScript CLI generation (use CreateCLI).

Manage the public daemon profile — a digital representation of what you're working on. DaemonAggregator reads LifeOS sources (TELOS, KNOWLEDGE, PROJECTS, MEMORY/WORK, identity) → daemon-data.json. SecurityFilter strips names/paths/credentials via deterministic patterns (NOT LLM). Workflows: UpdateDaemon, ReadDaemon, PreviewDaemon, DeployDaemon. USE WHEN daemon, update daemon, daemon profile, deploy daemon, preview daemon, read daemon, public profile, digital presence. NOT FOR LifeOS system management (use _LIFEOS).

Parallelizes work across six patterns — built-in agents, worktree-isolated agents, background agents, custom inline-brief agents, multi-turn agent teams, and parallel task dispatch — choosing teams when agents must share state, subagents when independent. USE WHEN parallel execution, agent team, swarm, spawn agents, fan out, divide and conquer, multi-agent, coordinate agents, custom agents.

AI agent evaluation framework with three grader types (code-based, model-based, human) and pass@k/pass^k scoring over agent transcripts, tool-call sequences, and multi-turn conversations; covers capability and regression evals. USE WHEN eval, evaluate, benchmark, regression test, compare models, create judge, test agent, pass@k, scenario simulation. NOT FOR scientific method framing (use Science).

Content-adaptive wisdom extraction that reads content first, detects which wisdom domains are present, and builds custom sections around them, with five depth levels and mandatory contrarian takes; pulls YouTube via fabric and articles via WebFetch. USE WHEN extract wisdom, analyze video, analyze podcast, extract insights, key takeaways, summarize interview, distill content. NOT FOR static Fabric extract_wisdom pattern (use Fabric).

Execute any of 240+ specialized prompt patterns natively across Extraction, Summarization, Analysis, Creation, Improvement, Security, Rating. Common: extract_wisdom, create_threat_model, analyze_claims, improve_writing, review_code, mermaid, youtube_summary. CLI used only for YouTube transcript (-y) and URL fallback (-u). Two workflows: ExecutePattern, UpdatePatterns. USE WHEN fabric, fabric pattern, run fabric, update patterns, threat model, analyze claims, improve writing, review code, mermaid, STRIDE, sigma rules. NOT FOR multi-agent investigation (Research) or content-adaptive extraction (ExtractWisdom).

Physics-based reasoning framework (Musk methodology) that deconstructs a problem to irreducible fundamental truths, classifies every element as hard constraint, soft constraint, or assumption, then reconstructs the optimal solution from fundamentals alone. USE WHEN first principles, fundamental truths, challenge assumptions, real constraint, rebuild from scratch, start over, physics first, question everything, reasoning by analogy. NOT FOR structural feedback loops (use SystemsThinking).

Hardens LifeOS tests via property/mutation testing. USE WHEN harden, hardening, property test, property based testing, PBT, fast-check, mutation test, mutation testing, Stryker, CRAP score, CRAP analysis, DRY scan, jscpd, acceptance test mutation, strengthen tests, sharpen ISCs, find bugs example tests miss, universal quantified claim, shrink counterexample, what bugs am I missing, test the tests, test of the test. NOT FOR writing new feature tests (use bun test directly), grading agent output quality (use Evals), UI verification with real Chrome (use Interceptor), finding security vulnerabilities (use _HELIOS), or building new functionality.

Mines a single piece of content (URL, YouTube, article, text, file) for anything useful to LifeOS, ranks the findings, then ingests the content into the Knowledge Archive. USE WHEN harvest, harvest this, harvest <URL>, harvest <YouTube>, harvest this video, harvest this article, /harvest, /ha, mine this for the system, anything useful in this for us, what can LifeOS take from this, analyze this for LifeOS-usefulness, should we adopt anything from this. NOT FOR ingestion-only saves with no system-mining (use _HARVEST directly), broad multi-source upgrade or bookmark scans (use Upgrade / pu), or general research synthesis (use Research).

Evolutionary ideation engine — loop-controlled multi-cycle idea generation through phases of dreaming, cross-domain stealing, recombination, fitness testing, selection, and Lamarckian meta-learning, producing ranked novel solution candidates with provenance. USE WHEN ideate, id8, novel ideas, evolve ideas, dream up solutions, innovate, breakthrough ideas, idea evolution, multi-cycle creativity, need genuinely new approaches. NOT FOR quick single-pass brainstorming (use BeCreative).

Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation bug, jank, transition stutter, scrub a flow, console logs/errors, runtime/JS/react errors, mismatch warning, network traffic/log, HAR/pcapng export, hydration/blank-page debug, flash then blank/page broken, why is this not working/what's happening on the page, authenticated page, bot detection bypass, reproduce bug, drive native app, about to ask the operator to click/navigate/fill a form/log in/approve OAuth, OAuth consent flow, complete a web login, do this in your browser. NOT FOR residential-proxy crawling (BrightData) or social actor scraping (Apify).

Reads seven constitutional files (TELOS, DA_IDENTITY, PRINCIPAL_IDENTITY, PROJECTS, system prompt, PRINCIPAL_TELOS, ARCHITECTURE_SUMMARY) via TelosFreshness, surfaces stalest items, drives contextual peer conversation. Routes to ContextCheckin; falls back to Phase0Setup on fresh install. ContextAudit surfaces TBD markers. USE WHEN /interview, resume interview, context check-in, telos check-in, what's stale, freshness check, fresh LifeOS install, configure DA name, review TELOS, quarterly context refresh. NOT FOR single edits (Telos), bulk intake (Migrate), identity-only (_PROFILE).

Owns the Ideal State Artifact — the primitive holding a project or task's articulated ideal state; scaffolds, interviews, scores completeness, reconciles feature excerpts to master, seeds from a repo, and appends decisions/changelog/verification across a locked fourteen-section order. USE WHEN ISA, ISC, ideal state, ideal state criteria, project specification, hill-climb, articulating done. NOT FOR creating new skills (use CreateSkill).

Structured multi-angle exploration running 2-8 sequential passes over the same problem, each through a different scientific lens, to surface hidden requirements and edge cases invisible from one angle; each pass yields new ISC criteria. USE WHEN iterative depth, explore deeper, multi-angle analysis, surface hidden requirements, blind spot check, what am I missing. NOT FOR scope/zoom analysis (use ApertureOscillation).

Manage the LifeOS Knowledge Archive — a curated, typed graph of People, Companies, Ideas, and Research notes with typed related: links; search, add, harvest, develop, ingest, and graph-navigate. USE WHEN knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, ingest, contradictions, knowledge graph, retrieve, mine conversations. NOT FOR session/ISA context recovery (use ContextSearch), published content semantic search across blog/newsletter/X/LinkedIn (use _CONTENTSEARCH), or one-shot URL/YouTube ingestion via the Arbol harvester pipeline (use _HARVEST).

Install and onboard a user into LifeOS — the Life Operating System (current state → ideal state via TELOS + the Algorithm). The agentic installer detects your OS + harness, wires hooks with permission, scaffolds your USER tree, pulls in sources you provide, and runs the TELOS / current→ideal interview that seeds your Pulse dashboard. USE WHEN install LifeOS, set up LifeOS, lifeos setup, lifeos-setup, lifeos interview, onboard me, run the interview, integrate LifeOS into my harness, update LifeOS, uninstall LifeOS, first-time setup. NOT FOR building or cutting a LifeOS release (private release tooling), editing TELOS after onboarding (use Telos / Interview), or LifeOS system maintenance (use the private maintenance skill).

Generic civic intelligence aggregator for any US city — daily local digest of construction permits, crime, new businesses, public officials, legislation, elections, arrests, and local news, keyed off principal's Hometown. Writes JSON consumed by Pulse LOCAL tab. Crime delegates to _CRIMESTATS. Workflows: DailyBrief, Construction, Crime, Business, Officials, Legislation, Elections, Arrests, News. USE WHEN local news, hometown news, council meeting, building permits, mayor, ballot measures, ordinance, recent arrests, civic intel, local digest. NOT FOR national news or arbitrary-city crime.

Iterative improvement loop — refine a target across multiple Algorithm cycles toward ideal state. USE WHEN loop, iterate, refine, multiple passes, keep improving, revisit, rework.

Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with --approve-all/--approve-target/--review/--dry-run. Confidence ≥70% auto, 40-70% confirm, <40% walk-through. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import CLAUDE.md, bulk import, Obsidian/Notion/Apple Notes import. NOT FOR single-file edits, conversational interviews, identity edits.

Autonomous optimization loop — hill-climb any target. Code with metrics, or skills/prompts/agents with LLM-as-judge. USE WHEN optimize, hill climb, improve metric, reduce latency, optimize skill, optimize prompt, eval mode.

Ethical people-finding and identity verification via parallel research agents across people-search sites, social media, public records, and reverse phone/email/image/username lookups, with confidence-scored results requiring 3+ matching identifiers. USE WHEN find person, locate person, reconnect, lost contact, old friend, reverse phone lookup, who owns this email, reverse image search, find by username, verify identity, people search, public-data background check, who is this caller. NOT FOR structured due-diligence or company/entity intelligence investigations (use _OSINT) or general web research synthesis (use Research).

Adversarial analysis deploying parallel expert agents to stress-test ideas, strategies, and plans — decomposes into atomic claims, attacks them, then steelmans and counter-argues, producing severity-ranked findings with remediation. USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, strongest objection. NOT FOR collaborative debate to find best path (use Council).

Creates programmatic video with React via Remotion — compositions, sequences, and motion graphics animated with useCurrentFrame() and rendered to MP4. USE WHEN video, animation, motion graphics, video rendering, React video, render video, animate content, make a short, create animations, video overlay, explainer video, animated explainer, content to video, programmatic video. NOT FOR static images, diagrams, or illustrations (use Art), tight-cut filler removal from raw recordings (use Video), or audio-only podcast cleaning (use AudioEditor).

Multi-agent web research with mandatory URL verification, confidence-tagged output, and four depth modes (quick to deep investigation). USE WHEN research, do research, quick research, extensive research, deep investigation, find information, investigate, extract alpha, analyze content, retrieve content, AI trends, enhance content, extract knowledge, web scraping, YouTube extraction, map landscape, competitive analysis, find it, find this, find this product, identify this, what is this, what's that thing, track down, locate, help me find, I can't find X online, can't find it online, source this — never substitute raw WebSearch/WebFetch for a multi-source find/identify/investigate request. NOT FOR people/company/entity deep background (use _OSINT), academic papers (use ArXiv), JSON entity extraction (use _PARSER), or content-adaptive wisdom extraction (use ExtractWisdom).