Pre- and post-implementation validation with parallel subagents: /replan validates plans before execution, /recheck verifies implementations match the plan. On real code changes /recheck also runs a full /code-review high pass. Includes a per-run audit trail, lessons-learned feedback loop (interactive + autonomous)…
Skills for AI-assisted project orchestration following best practices for software development lifecycle, architecture documentation, and quality automation.
★not rated 15 yesterdayA
tokens not measured
originalMIT
Bootstrap any new project with a production-grade AI-Human collaboration framework. Generates README.md, CLAUDE.md, .claude/ registry files, git version hooks, and sprint planning templates through interactive dialogue.
★not rated 15 5mo agoA
tokens not measured
originalMIT
Portable Socratic roadmap workflow for Claude Code, OMP, Codex, and solo sessions. Interviews for the real objective, researches through available capabilities, delegates bounded read-only work to native agents, adversarially reviews the draft, and renders a self-contained offline HTML roadmap.
★not rated 15▲
+1
changed yesterdayA
tokens not measured
originalMIT
Spec-Driven Development workflow: /sdd: commands, portable skill, machine-checked gate. Bilingual EN/ES. No code before approved spec and consistent plan.
★not rated 15▲
+1 5d agoA
tokens not measured
originalMIT
Run Claude Code like a specialist software team: planning, implementation, QA, fix/retest loops, and durable serial or parallel harness state for long-running project delivery.
★not rated 14 4mo agoA
tokens not measured
originalMIT
An evidence-graded library of agent-executable thinking-method skills (premortem, problem restatement, and more). Each skill is reduced to its working mechanism, graded honestly on how strong its evidence actually is, and produces a concrete artifact rather than prose. Use to reframe a problem, challenge assumptions…
★not rated 14 19d agoA
tokens not measured
originalApache-2.0
An adversarial truth-extraction skill that interrogates you — with your consent — past your own self-deception to what is actually true. Built on declassified interrogation doctrine (KUBARK, Scharff, PEACE, HIG), ethics-first: questions, never answers; consent, never coercion.
★not rated 14▲
+2 1mo agoA
tokens not measured
originalMIT
Your AI argues before it answers. Five-step decision loop for builders — GATE, LOOK, RESHAPE, ATTACK, CARD — built from Bezos's letters, Musk's algorithm, and Farnam Street's mental models. No more "you're absolutely right!".
Planning session mode for complex tasks. Enter Fathom Mode to build shared understanding through structured dialogue before execution. Use this when you want to plan, think through, or clarify something complex before acting on it.
★not rated 13 4mo agoA
tokens not measured
originalMIT
Lightweight standalone ControlFlow plugin for Claude Code: high-quality plan generation in the shared ControlFlow format, inline adversarial plan verification (zero subagents), and evidence-backed review with proactive vulnerability/error search layered over the native Claude Code toolset. 3 skills, 0 subagents …
Spec-driven agentic engineering as graph engineering: shape (pitch) -> decide (ADR) -> execute (delegated cycle with adversarial review) -> measure -> eval, with /graph to fan work out across a fleet of subagents (diamond / router / verifier / cycle). Dark-launch eval-gated. Distilled from a real practice.
★not rated 13 1mo agoA
tokens not measured
originalMIT
Orchestrator plugin that weaves planning-with-files, DESIGN.md, memory routing, agent teams, and session handoff into one composable contract for any modern coding agent. Composes existing skills without altering their core. Includes code-to-DESIGN.md harvest and critique.
★not rated 13 4mo agoA
tokens not measured
originalApache-2.0
Idea-to-MVP pipeline: validate a startup idea, scope the MVP, design the architecture, and generate implementation-ready specs.
★not rated 13 1mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: