Provides a harness-agnostic protocol for converting human intent into bounded, inspectable, resumable agent work with classification, durable contracts, review triage, failure routing, and autonomy gates.
Use this skill to run BMad (Breakthrough Method of Agile AI-Driven Development) as a harness-agnostic control-plane protocol that turns human intent into bounded, inspectable, resumable agent work. Compress intent into a five-field contract (Why, Capabilities, Constraints, Non-goals, Success signal); classify work as direct/bounded/initiative and route to the smallest safe path; carry decisions in durable artifacts; review as triage; route failure to the layer where ambiguity entered; and gate autonomy on observable acceptance with machine-readable status (draft/ready-for-dev/in-progress/in-review/done/blocked). Use when a change request, feature, delegated build, or multi-agent epic needs intent capture, bounded implementation, review, and resumability in any agent harness. Do not use for validating whether a problem is real (product-discovery), shaping bets before planning (product-shaping), formal spec/gate pipelines (spec-driven-development), or the issue-to-PR delivery flow (neckbeard).
evals/evals.json
JSON
Other
README.md
Markdown
Other
templates/INTENT.md
Markdown
Other
templates/REVIEW.md
Markdown
Other
templates/SPEC.md
Markdown
Other
templates/STORY.md
Markdown
Reference
references/adoption.md
Markdown
Reference
references/autonomy.md
Markdown
Reference
references/classification.md
Markdown
Reference
references/lifecycle.md
Markdown
Reference
references/party-mode.md
Markdown
Reference
references/project-context.md
Markdown
Reference
references/protocol.md
Markdown
Reference
references/review-and-failure-routing.md
Markdown
Reference
references/spec.md
Markdown
Script
scripts/check-spec.py
Python
Script
scripts/test_check_spec.py
Python
SKILL.md
SKILL.md
Markdown
Guides agents in designing, reviewing, prototyping, measuring, and troubleshooting electronic circuits using component evidence, worst-case analysis, interface contracts, and stag…
Guides agents in developing, testing, deploying, and administering managed or self-hosted Supabase projects, including migrations, RLS, client types, services, backups, upgrades, …
Helps design, implement, evaluate, debug, and deploy stateful multi-agent workflows with LangGraph, including supervisor, swarm, hierarchical, persistence, subgraph, and human-in-…
Guides agents in designing, evaluating, governing, operating, evolving, and retiring digital twins and federated twin universes with synchronization, simulation, authority, and li…
Guides agents through safe cross-system migrations involving data, schemas, interfaces, infrastructure, and service ownership, using compatibility windows, dual-running, reconcili…
Guides system-level architecture decisions from business drivers through boundaries, tradeoffs, runtime behavior, evolution, evidence, and architecture reviews.
Helps agents build, customize, and debug Hugo themes, including templates, asset pipelines, shortcodes, render hooks, content organization, performance, SEO, accessibility, and CI…
Guides agents in designing and reviewing multi-tenant SaaS architectures, covering tenant semantics, system planes, isolation choices, onboarding, entitlements, billing handoffs, …