45 composable capabilities.
One DA.

Compose CUSTOM agents from Base Traits + Voice + Specialization, and manage predefined functional TEAMS.

3-pass scope oscillation that holds a question constant while shifting the scope envelope — narrow/tactical, wide/strategic, then synthesis — to surface design tensions invisibl…

Curated aphorism collection with CRUD — content-based matching, themed search, thinker research, DB maintenance.

Scrape social media platforms, business data, and e-commerce via Apify actors — Instagram profiles/posts/hashtags/comments, LinkedIn profiles/jobs/posts, TikTok profiles/hashtag…

Static visual content across 20+ formats via Flux, Nano Banana Pro (Gemini 3 Pro), and GPT-Image-2 (OpenAI flagship).

Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews.

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 cr…

Divergent ideation and corpus expansion via Verbalized Sampling + extended thinking.

Audits any AI instruction set for over-prompting using the core test — would a smarter model make this rule unnecessary?

4-tier progressive scraping with automatic escalation: Tier 1 WebFetch (fast, built-in), Tier 2 curl with Chrome headers (basic bot bypass), Tier 3 agent-browser (headless JavaS…

Headless browser automation via agent-browser — Rust CLI daemon with persistent auth profiles for fast, scriptable, parallel browser work.

"Find prior PAI work — sessions, ISAs, conversations — by topic, partial words, or date phrases like 'yesterday' / 'last week' / 'YYYY-MM-DD'.

Multi-agent collaborative debate producing visible round-by-round transcripts with real intellectual friction.

Generate production-ready TypeScript CLIs via 3-tier template system: Tier 1 llcli-style manual arg parsing (zero deps, Bun + TS, 80% of cases), Tier 2 Commander.js (subcommands…

MANDATORY for ALL skill work — you MUST invoke this skill BEFORE creating, modifying, adding a workflow/tool to, renaming, validating, or canonicalizing ANY skill.

Manage the public daemon profile — a digital representation of what you're working on.

Parallelize work via six patterns: built-in agents (Engineer/Architect/Algorithm/Explore/Plan via Task), worktree-isolated agents (conflict-free parallel edits), background agen…

Comprehensive AI agent evaluation framework with three grader types (code-based: deterministic; model-based: LLM rubric; human: gold standard) and pass@k / pass^k scoring.

Content-adaptive wisdom extraction — reads content first, detects what wisdom domains are present, then builds custom sections around what it finds instead of forcing static hea…

Execute any of 240+ specialized prompt patterns natively across Extraction, Summarization, Analysis, Creation, Improvement, Security, Rating.

Physics-based reasoning framework (Musk methodology) that deconstructs problems to irreducible fundamental truths rather than reasoning by analogy.

Evolutionary ideation engine — loop-controlled multi-cycle idea generation through 9 phases (CONSUME, DREAM at noise=0.9, DAYDREAM at 0.5, CONTEMPLATE at 0.1, STEAL cross-domain…

Real Chrome/Brave browser automation + full macOS Computer Use via the Interceptor extension and bridge — controls the actual browser from inside (zero CDP fingerprint, passes B…

Reads seven constitutional files (TELOS, DA_IDENTITY, PRINCIPAL_IDENTITY, PROJECTS, system prompt, PRINCIPAL_TELOS, ARCHITECTURE_SUMMARY) via TelosFreshness, surfaces stalest it…

Owns the Ideal State Artifact — universal primitive holding articulated ideal state of any project, task, application, library, or work session as a hard-to-vary explanation.

Structured multi-angle exploration that runs 2-8 sequential passes through the same problem, each from a different scientific lens, to surface requirements and edge cases invisi…

"Manage the PAI Knowledge Archive — a curated, typed graph of notes across four entity domains: People, Companies, Ideas, and Research.

"Iterative improvement loop — refine a target across multiple Algorithm cycles toward ideal state

Intakes external content, classifies chunks against PAI taxonomy, commits with provenance.

"Autonomous optimization loop — hill-climb any target.

Ethical people-finding and identity verification using 15 parallel research agents (5 types x 3 each = 45 concurrent search threads) across people search aggregators, social med…

Meta-prompting standard library — the PAI system for generating, optimizing, and composing prompts programmatically.

Military-grade adversarial analysis deploying 32 parallel expert agents (engineers, architects, pentesters, interns) to stress-test ideas, strategies, and plans — not systems.

Creates programmatic video with React via Remotion — builds compositions, sequences, and motion graphics rendered to MP4.

Comprehensive research and content extraction with 4 depth modes: Quick (1 Perplexity agent, ~10-15s), Standard (4 agents — Claude + Gemini + Grok + Perplexity, cross-checked, ~…

Structured incident investigation grounded in Toyota TPS, Ishikawa, Reason's Swiss Cheese, Gano's Apollo, Google SRE blameless culture.

Transforms product documentation into sales-ready narrative packages combining story explanation, charcoal gestural sketch art, and talking points.

The scientific method as a universal problem-solving algorithm — goal-first, hypothesis-plural, falsifiable experiments, honest measurement.

Structural analysis of complex systems grounded in Donella Meadows, Senge, Forrester, Ackoff, Santa Fe Institute.

Dual-context Life OS skill.

TELOS-driven recommender — what to work on next.

Analyze and update 68 US economic and social indicators from five government APIs (FRED, EIA, Treasury, BLS, Census) across 10 categories: GDP, Inflation, Employment, Housing, C…

Design and integrate web interfaces via two paths: ClaudeDesign (drive claude.ai/design through Interceptor) or DirectDesign (write design directly with Anthropic frontend-desig…

Persistent world-model harness that stress-tests ideas, strategies, and investments against 11 time horizons from 6 months to 50 years.

Scaffolding that helps a writer build a story they already want to tell — it fills in the hard parts (structure, the character's hidden wound, the theme they can feel but can't …