Abilityai

Add a memory system to an agent — file awareness, knowledge graph, structured state, or multi-session tracking

Modify an existing playbook based on conversation context or explicit instructions. Use when user wants to update, fix, extend, or refine a playbook they already have.

Create a new skill or playbook. Guides through requirements gathering and generates the appropriate template based on complexity.

Create an executive chief of staff agent — asks about your tools, team, and priorities, then scaffolds a Trinity-compatible agent for daily briefings, meeting prep, and decision tracking

Scaffold a new Trinity-compatible Claude Code agent from scratch on any topic. Creates directory, CLAUDE.md, skills, and Trinity files — ready for development.

Create a content writer agent — asks about your brand voice, platforms, and topics, then scaffolds a Trinity-compatible ghostwriter agent that writes in your voice

Create a knowledge-base agent — asks a structured 6-question interview about the domain's ontology, then scaffolds a Cornelius-shaped Trinity-compatible KB agent with a typed graph, 7-layer vault, subagents, and scheduled coherence jobs

Create a B2B SaaS sales research agent — asks domain-specific questions and scaffolds a Trinity-compatible prospector agent customized to your sales stack

Generate and update user documentation from code, feature flows, and recent changes into docs/user-docs/

Detect drift between architecture.md and the actual code. Validates 15 architectural invariants and flags stale doc claims with suggested edits.

Validate config hygiene — docker-compose env vars vs .env.example vs code references vs architecture docs. Flags missing, stale, or undocumented configuration.

Validate database schema consistency — DDL in schema.py vs migrations.py vs architecture.md. Flags drift between the three sources of truth.

Chief Security Officer audit — infrastructure-first security scan with secrets archaeology, dependency supply chain, CI/CD pipeline, LLM/AI security, OWASP Top 10, STRIDE threat modeling, and active verification. Two modes — daily (8/10 confidence gate) and comprehensive (2/10 bar).

Run the Playwright frontend e2e suite against a live Trinity stack, analyze failures, and update visual regression snapshots. Use after UI changes, before merging a PR with the `ui` label, or when the `frontend-e2e` CI workflow fails.

Validate a pull request against the Trinity development methodology and generate a merge decision report.

Full development cycle — pick issue, plan review, implement, code review, sync docs, commit to feature branch, and create PR. Orchestrates /cso, /autoplan, /implement, /review, /validate-pr, /sync-feature-flows.

Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report

Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative

Autonomous research pipeline - discover, extract, and integrate cutting-edge insights into knowledge base

Detect productive contradictions between notes - high semantic similarity with opposing conclusions that represent synthesis opportunities

Autonomous perception layer - scans KB for new notes matching domain watch configs, checks gap resonance with the Thinking Registry, probes external signals via web search, and auto-activates HIGH/MEDIUM signals into the Thinking Registry for the incubation loop.

Extract insights from external documents (research papers, books, articles). Spawns document-insight-extractor subagent. Requires session name.

Extract the transcript from a YouTube video by URL or video ID. Use when the user shares a YouTube link and wants the transcript, captions, or text content of the video. Falls back automatically if the requested language isn't available.

Autonomous iterative thinking loop - processes active topics using rotating analytical moves (ACH, Bayesian updating, steelmanning, cross-domain bridging, implication checks) and persists reasoning state across scheduled runs