MCP App StoreMCP App StoreThe /learn skill extracts actionable findings from completed campaigns or evolve pattern libraries and integrates them into the project's knowledge wiki. It structures successful patterns, anti-patterns, key decisions, and candidate quality rules, writes staged JSONL records, and compiles them into topic wiki pages with evidence and confidence metadata.
Use /learn after a campaign or evolve cycle completes to capture lessons and make them discoverable across future sessions. Also use --lint, --compile, or --memory modes for maintenance passes (linting, wiki-only compile, or semantic memory block generation).
Designed for orchestration harnesses and agent runtimes that support file-system access and Node/Python hooks (Claude Code-style orchestration, local automation runners).
Citadel Learn is a knowledge compiler skill that extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into a structured project wiki. It has no bundled scripts — all logic is defined procedurally in SKILL.md. The skill is well-structured with clear steps, edge cases, and quality gates, but it's tightly coupled to the Citadel framework's `.planning/` directory structure and requires that ecosystem to be useful. Without existing campaigns or the Citadel harness, the skill cannot function.
Well-written skill with comprehensive documentation, clear steps, and thoughtful edge case handling. The flush→compile→lint pipeline is a solid pattern. However, it's niche — only relevant for projects using the Citadel campaign/evolve framework. The skill references external scripts (doc-sync.js, memory-compile.js) that aren't included, meaning those invocation paths will fail without the broader Citadel repo. Security is clean: no network calls, no credentials, no destructive operations — all writes are local and reversible via git. Deducted 5 points from security for referencing and attempting to execute external node scripts without checksums or pinned versions.
Marshal (Session Commander)
A single-session meta-orchestrator that parses a direction, chains existing skills, and executes multi-step tasks end-to-end without unnecessary user prompts.
Citadel Setup
Interactive first-run wizard that installs hooks, detects project stack, generates harness config, and runs a short live demo to register skills and protect the
/research — Focused Investigation
Structured research protocol that converts questions into focused findings with cited sources, confidence levels, and a written research document for follow-up.
Create App — End-to-End Application Generator
Generate a complete application or add features to an existing codebase from a single natural-language description, with tiered workflows, PRD/architecture chec
PRD (Product Requirements Document) Generator
Generates structured Product Requirements Documents from natural-language app descriptions, asking clarifying questions, researching references, and producing m
Do — Unified Intent Router
Route user intents to the cheapest capable handler (skill, marshal, archon, or fleet) using a multi-tier classifier for scope, complexity, persistence, and para
Fleet — Parallel Campaign Orchestrator
Orchestrate parallel campaigns in waves: spawn isolated agents/worktrees, coordinate discoveries, validate results, and merge work — for multi-stream engineerin
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
