harivansh-afk

Deep planning via Oracle CLI (GPT-5.2 Codex). Use for complex tasks requiring extended thinking (10-60 minutes). Outputs plan.md for planner to transform into specs.

Manages weaver execution via tmux. Reads specs, selects skills, launches weavers in parallel, tracks progress. Runs in background.

Interactive planning agent. Designs verification specs through Q&A with the human. Uses Oracle for complex planning. Hands off to orchestrator for execution.

Verification subagent. Runs checks from verification_spec in order. Fast-fails on first error. Reports PASS or FAIL with evidence. Does NOT modify code.

Base skill for all weavers. Implements specs, spawns verifiers, loops until pass, creates PR. Tests are never committed.

Use when encountering dependency conflicts, CocoaPods/SPM resolution failures, "Multiple commands produce" errors, or framework version mismatches - systematic dependency and build configuration debugging for iOS projects. Includes pressure scenario guidance for resisting quick fixes under time constraints

Use when adding/modifying database columns, encountering "FOREIGN KEY constraint failed", "no such column", "cannot add NOT NULL column" errors, or creating schema migrations for SQLite/GRDB/SQLiteData - prevents data loss with safe migration patterns and testing workflows for iOS/macOS apps

Use when writing raw SQL queries with GRDB, complex joins, ValueObservation for reactive queries, DatabaseMigrator patterns, query profiling under performance pressure, or dropping down from SQLiteData for performance - direct SQLite access for iOS/macOS

Commit Changes in CI with no user interaction

first step of planning

convert structure outline into a detailed implementation plan

generate research questions based on a task, spec, or ticket

research the codebase

create a phased implementation plan based on research and design decisions

Generate PR Description in CI (no user input)

phased implementation of a structured plan you must use this skill when asked to implement a plan file in .humanlayer/tasks/*

Bridge a remote Agent Computer machine agent into a local ACP-compatible stdio process using `computer acp serve`. Use when a local agent client or ACP tool needs to talk to Claude or another remote machine agent through one local command.

Control Agent Computer machines and remote agent sessions from a local agent using the aicomputer CLI. Use when you need to list machines, inspect installed agents, create or resume remote sessions, send prompts, stream progress, cancel or interrupt work, or close sessions cleanly.

Non-interactive X11 desktop control for AI agents. Use when the task involves controlling a Linux desktop - clicking, typing, reading windows, waiting for UI state, or taking screenshots inside a sandbox or VM.

Use when Hari shares a URL (article, YouTube, tweet, paper, repo) to save or read later. Fetch it, write a high-signal summary note into the KB staging dir so it becomes searchable, then confirm with a one-line gist.

Expert coding agent for this codebase. Learns from every session to improve code quality, catch edge cases, and apply proven patterns. Use for ANY coding task: writing, debugging, refactoring, testing. Accumulates project knowledge.

Implement code from a plan, create PRs with Graphite CLI (gt create/submit), wait for code reviews, and iterate on feedback. Use when the user says "implement", "implement the plan", "create PR", "review loop", or wants to go from plan to merged PR. This skill handles the full cycle - implement code, create branch with Graphite, submit PR, wait for reviews (without wasting tokens), read comments, fix code, and push updates.

Autonomous academic agent for Canvas LMS. Watches lectures, writes essays, completes assignments, and tracks deadlines. Use when the user asks about school, homework, Canvas, assignments, grades, lectures, coursework, study materials, or academic automation.

Generate evaluation specs with building and verification criteria. Use when setting up features, defining acceptance criteria, or before implementing anything significant. Triggers on "create evals", "set up verification", "define acceptance criteria", or "build [feature]".

Orchestrate Devin CLI subagents as background workers using tmux windows. Use when the user asks to spawn, coordinate, fan-out, or delegate work to multiple parallel agents, run background Devin sessions, or orchestrate long-running autonomous tasks from inside an existing Devin session.