Are you the author? Sign in to claim
12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, execu
A gated pipeline of 12 agent skills that turns an idea into deployed, production-grade software — design, spec, executable architecture, honest review loops, QA, safe deploy. Works with Claude Code, Codex, Cursor, opencode — any agent that speaks the skills format. No vibecode.
Disruptor is a set of 12 agent skills for AI-driven software development, stitched into one idea-to-ship pipeline. Skills are plain Markdown with YAML frontmatter — an open cross-agent format read natively by Claude Code, Codex, Cursor, opencode and others. Each stage consumes the artifact of the previous one and hands a new artifact to the next, while a router with Yes/No gates decides what happens next. The agent acts by rule, not by vibe: it doesn't improvise the process and doesn't declare "done" early.
The core premise: an agent's own feeling of "done" cannot be trusted — it is the main enemy. Every method here exists to survive a premature stop: the unread green test, the spec with a hidden default, the rubber-stamp review, the loop that only adds and never cuts. Each skill was extracted from real production runs by practitioners, not invented for a README.
Input → [ROUTER: on-ramps + gates G0–G5]
0 Setup ─► 1 Design ─► 2 Spec ─► 3 Guardrails ─► 4 Slices ─► 5 Build & converge ─► 6 QA ─► 7 Deploy
(once) 7w3 spec executable tracer ├ 5a reviewers
architecture bullets └ 5b unvibe
└────────► G3F: fleet lane (delivering-mvp-fleet) ─► 6 QA
Two kinds of skills. Methods trigger automatically when the situation matches (model-invoked). Prompt templates are /commands you invoke yourself (user-invoked).
| Stage | Skill | Kind | What it does |
|---|---|---|---|
| — | disruptor | /command | The router: on-ramps + gates G0–G5, routes any input to the right stage |
| 0 | setting-up-domain-model | auto | Repo conventions, shared glossary, ADRs → CONTEXT.md (once per project) |
| 1 | designing-with-7w3 | auto | 7w3 design interview: 10 facets per subject, a design tree per subject |
| 2 | write-spec | /command | Canonical build-ready specification, incl. golden case cards |
| 3 | architecture-guardrails | /command | Module boundaries as executable rules: linter + import graph + CI |
| 4 | slicing-into-tracer-bullets | auto | Breakdown into vertical slices (tracer bullets), each independently shippable |
| 5 | converging-and-polishing | auto | The engine: review loop until findings converge to near zero |
| 5a | spawning-reviewers | auto | Independent cross-family reviewers — fresh context, no rubber-stamping |
| 5b | unvibe-review | auto | The counter-force: cut, unify, rethink bloat instead of adding more |
| 4–5 | delivering-mvp-fleet | auto | Fleet lane: parallel subagent workers build an MVP from a board of nodes |
| 6 | qa-demo-stand | /command | Demo-stand testing to production quality; also the bug/incident on-ramp |
| 7 | setup-server | /command | Safe Ubuntu/Debian web server setup and deploy |
On-ramps besides an idea from scratch: bug/incident → straight to QA, fix through the engine · "bloated / architecture drifting" → unvibe + guardrails audit · existing design or spec → jump to the matching stage · vague idea, speed to testable MVP matters most → the fleet lane.
With the skills.sh installer (interactive, works across agents):
npx skills@latest add smixs/disruptor-skills
With install.sh (copies all 12 skills, no .git):
curl -fsSL https://raw.githubusercontent.com/smixs/disruptor-skills/main/install.sh | bash
# current project only:
curl -fsSL https://raw.githubusercontent.com/smixs/disruptor-skills/main/install.sh | bash -s -- --project
With git clone:
git clone --depth 1 https://github.com/smixs/disruptor-skills /tmp/disruptor-skills \
&& cp -R /tmp/disruptor-skills/skills/* ~/.claude/skills/
Done — skills are discovered by the presence of the folders; no extra registration command. The npx skills installer places them into the right directory for each agent you use (~/.claude/skills/, ~/.agents/skills/, …); install.sh and the clone target the ~/.claude/skills/ convention.
The repo ships .claude-plugin/plugin.json, so it can also be installed through the /plugin flow. For most users the installs above are enough.
You don't drive the pipeline by hand — the router does. Two ways in:
Just describe the task. The model-invoked methods trigger on matching situations, and the router places you at the right stage via its gates. Example phrasings:
"design this properly" · "slice this into tasks" · "review loop until it converges" · "what can we cut" · "this codebase feels bloated" · "build me an MVP of X fast"
Invoke a /command directly when you know what you need: /disruptor to run the full gated flow from any input, /write-spec, /architecture-guardrails, /qa-demo-stand, /setup-server.
The router asks Yes/No gate questions (G0–G5: is setup done? is the design build-ready? is the build parallelizable?…) and refuses to skip ahead — that refusal is the point.
Disruptor is a process pipeline — it says nothing about what good CSS, good SQL, or good motion design looks like. That's deliberate: domain taste lives in domain skill packs, and the two compose in your agent at runtime, not in this repo.
npx skills@latest add smixs/disruptor-skills emilkowalski/skills
With a pack like emilkowalski/skills (UI polish and animation craft) installed alongside, builders in stage 5 pick up the domain taste automatically, and stage 5a can spawn the pack's reviewer (e.g. review-animations) as a standards-conformance review — running beside, never instead of, the neutral cross-family defect review (see spawning-reviewers). The same shape works for any domain pack that ships expertise or a standards catalog.
Code that "technically works" but is bloated, fragile, and impossible to hold in your head — the default output of an agent left to trust its own sense of "done". Disruptor exists to prevent it: every stage gates on an artifact, not a feeling.
Spec-kit and BMAD own your whole process end-to-end with heavy scaffolding. Disruptor is 12 small composable skills tied by a lightweight router — you can enter at any stage, use one skill standalone, or run the full flow. Compared to obra/superpowers (a broad general-purpose library), Disruptor is one opinionated pipeline for shipping web-facing software, including a parallel worker-fleet lane.
Yes. Skills are plain Markdown with YAML frontmatter — a cross-agent format, not a vendor feature. npx skills@latest add smixs/disruptor-skills installs them into whichever agents you use; agents with skill auto-discovery trigger the methods on their own, and in any agent you can always load a skill file explicitly or hand a prompt template to a fresh session.
No. Each skill is standalone. But the router and the stage contracts assume the set is present — the full pipeline is where the compounding value is.
Seven methods are model-invoked (they fire when the situation matches). Five are user-invoked /commands: the router and the four prompt templates. See the table above.
v2 translated all prompts to English. The original Russian sources live in the git history (v1, tag v1.0.0 / the references/ directory) with full attribution.
The goal: a battle-tested discipline machine for agentic development, grown from real runs. If you have your own discipline, a fix born from a real failure, a new on-ramp or gate — send a PR. See CONTRIBUTING.md; discussion happens in t.me/aostrikov_agents_chat.
Assembled from the working methods of practitioners of @aostrikov_agents_chat (Alexey Ostrikov's chat), with per-skill attribution inside each SKILL.md:
converging-and-polishing, spawning-reviewers, unvibe-review) and the designing-with-7w3 design methodology.write-spec, architecture-guardrails, qa-demo-stand, setup-server).delivering-mvp-fleet, base-rules-travel-with-every-prompt invariant) and the assembly into a single gated flow.v2 translated all prompts from Russian to English; the RU originals remain in the git history.
Русская версия и обсуждение — в чате t.me/aostrikov_agents_chat.
MIT © @aostrikov_agents_chat.
⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u
Manage multiple Claude Code agents from TUI or Web with tmux and git worktrees
Project management using GitHub Issues + Git worktrees for parallel agent execution
Core skills library for Claude Code with 20+ battle-tested skills including TDD, debugging, and brainstorming