
End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase. Routes through PRD, architecture, and Archon campaign with verification at every step.
Creates new skills from the user's repeating patterns. Interview-driven: discovers the task, analyzes failure modes, generates a production SKILL.md, installs it, tests it on a real target, and teaches the user how to use it. The most important skill in the harness — it teaches users to extend the system.
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
Documentation generator with three modes: function-level (JSDoc/docstrings), module-level (directory READMEs), and API reference (endpoints/exports). Reads existing project doc style and matches it. Never generates docs that just restate what the signature already says.
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Playwright is an optional dependency (graceful skip if not installed).
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Does not make decisions — produces information that informs the next step.
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
Unified router that auto-routes user intent to the right orchestrator or skill. Classifies input by scope, complexity, persistence needs, and parallelism, then dispatches to the cheapest path that can handle it: direct action, skill, marshal, archon, or fleet. Single entry point for all work.
Parallel campaign coordinator. Splits work into non-overlapping waves, shares discoveries between waves, and records the state in `.citadel/fleet/`.
Parallel research using Fleet wave mechanics. Spawns multiple scout agents, each investigating a different angle of the same question. Findings are compressed between waves. Produces a unified research brief from multiple independent perspectives.
Summarize the current session into a compact HANDOFF block for the next session or delegated agent.
First-run experience for the harness. Detects the project stack, scaffolds the .citadel/ state directory, generates configuration, runs one real task as a demo, and prints a reference card of all available skills. Gets someone from install to first `do` command in 5 minutes.
Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that a campaign orchestrator can execute directly. Multi-candidate evaluation for key decisions.
Multi-session campaign orchestrator. Breaks larger work into phases, tracks progress in `.citadel/campaigns/`, and preserves decisions across sessions.
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Handles both issues and pull requests.
Generate and verify tests — happy path, edge cases, error paths — using the project's own framework and patterns
Four-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before code changes and stops guess-and-check debugging.
Generates a Product Requirements Document from a natural language app description. Asks clarifying questions, researches similar apps, defines scope, stack, architecture, and produces a structured PRD that can be decomposed into a campaign.
Safe multi-file refactoring with automatic rollback. Establishes a type/test baseline, plans all changes, executes file-by-file, and verifies zero regressions. Reverts if verification fails after two fix attempts. Handles renames, extracts, moves, splits, merges, and inlines.
5-pass structured code review — correctness, security, performance, readability, consistency
Automated optimization loop with scalar fitness function. Proposes changes in isolated worktrees, measures with a metric command, keeps improvements, discards failures. Supports convergence detection and diminishing returns.
Intake-to-delivery pipeline. Processes pending items from .citadel/intake/: briefs new ideas, executes approved work through research → plan → build → verify. Drop a file in .citadel/intake/ and invoke this skill.