superagent

Designed to assist users with ADHD (Attention Deficit Hyperactivity Disorder) by mitigating task paralysis, managing distractions, providing dopamine-driven progress tracking, and using executive-friendly visual formatting. Triggered by keywords or topics: - Focus/Distraction: "adhd", "fokus", "distracted", "gampang bosan", "pecah fokus", "distraksi", "sulit konsentrasi". - Task Initiation/Paralysis: "bingung mulai", "task paralysis", "mager", "banyak tugas", "tumpuk", "stuck", "overwhelmed". - Motivation/Rewards: "dopamine", "reward", "game", "poin", "xp", "checkpoint". - Formats: "bionic reading", "visual salience", "micro-step", "body double".

Execute detailed plans in batches with review checkpoints

Prevent task duplication, file conflicts, and coordination failures when multiple subagents work in parallel on the same Superagent project. Covers both Superagent→Subagent coordination and Master Agent→Superagent worktree coordination. Uses manage_plan and manage_tasks as the coordination hub.

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

Create isolated git worktrees with smart directory selection and safety verification

Triggered when the agent needs to audit, discover, and resolve missing features, architectural or functional gaps, performance/process bottlenecks, and structural complexity liabilities across a codebase, delivering lean and pragmatic improvement blueprints.

Triggered when the agent needs to solve complex, multi-faceted problems by simulating the collective intelligence of 100 specialized minds divided into 6 functional teams (Strategy, Domain Experts, Red Team, Empirical Testers, Consensus Council, and Execution Ops) within a single agent session.

Triggered when the agent needs to debug complex errors, analyze obscure runtime failures, find subtle bugs, or trace system anomalies using non-linear, multidimensional hypothesis graphs, backward-forward triangulation, behavioral state inversion, and dynamic perturbation instead of slow sequential linear step-by-step debugging.

This skill is triggered when the agent needs to perform deep reasoning, complex refactoring, system-wide bug investigation, multi-hypothesis evaluation, or high-throughput batch resolution (up to 100 problems per round) within a single agent session without spawning excessive subagents or wasting tokens.

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search

Guide for creating valid implementation plans and task checklists using the manage_plan tool in Superagent to prevent validation errors.

Skills wiki intro - mandatory workflows, search tool, brainstorming triggers

TDD for process documentation - test with subagents before writing, iterate until bulletproof

Behavioral rules to minimize common LLM coding pitfalls. Applies to all code creation, modification, review, and validation tasks.

Enforces lean coding, minimizes codebase footprint, and reviews/audits for over-engineering or complexity. Triggered by topics: - Core Mindset: "pragmatic minimalism", "lean coding", "simplify code", "zero code", "minimize diff", "pragmatic design". - Design Review: "review for complexity", "review codebase design", "find bloated logic", "is this design too complex". - Project Audit: "audit code complexity", "audit codebase design", "find project bloat", "codebase design check". - Simplification Ledger: "pragmatic debt", "simplification ledger", "shortcut list", "what did we simplify". - Reference Help: "minimalism help", "how do I use minimalism".

Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions.

Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding

Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

Contribute skills back to upstream via branch and PR

RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Guide for the Master Agent to orchestrate, monitor, and merge tasks across the 3-tier multi-agent architecture

Create, configure, and develop custom automation hooks, slash commands, event hooks, and dynamic skills under internal-hooks/