plugins/harness-powers/skills/harness-brainstorm/SKILL.md
Use before creative or behavioral changes to explore intent, constraints, options, and produce an approved Harness execution spec before planning.
npx skillsauth add Refinex-Space/Refinex-Skills harness-brainstormInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Turn an idea into an approved, implementation-ready design without starting implementation.
<HARD-GATE> Do NOT implement, scaffold, edit production files, or invoke implementation skills while using this skill. Harness brainstorm ends only after an approved spec is saved under `docs/exec-plans/specs/` and the next handoff is `harness-plan`. </HARD-GATE>Create a task for each item and complete them in order:
AGENTS.md, docs/ARCHITECTURE.md, and docs/PLANS.md, then inspect relevant source, tests, and recent changes.docs/exec-plans/specs/YYYY-MM-DD-<topic>-design.md.references/spec-reviewer-prompt.md when dispatching a reviewer.harness-plan.Start with repository guidance before asking detailed questions:
AGENTS.md and nested instruction files for local rules.docs/ARCHITECTURE.md for system boundaries and design vocabulary.docs/PLANS.md for active, planned, and completed work.If the request spans independent subsystems, stop and propose a decomposition. Each coherent subsystem gets its own spec, plan, and execution cycle.
Ask one question per message. Prefer multiple-choice questions when they reduce user effort, but use open-ended questions when the answer space is genuinely unknown.
Focus on:
Present 2-3 viable approaches. For each, include:
Lead with the recommended approach and the reason it best satisfies the constraints.
Once requirements are clear, present the design in reviewable sections. Keep simple designs short. For larger designs, cover:
Ask for confirmation after each major section. Revise until the user approves.
After approval, write the validated design to:
docs/exec-plans/specs/YYYY-MM-DD-<topic>-design.md
The spec should be decision-complete enough for harness-plan:
TBD, TODO, or unresolved alternativesReview the written spec before asking the user to proceed:
Fix issues inline before the user review gate.
After the spec review passes, ask the user to review the file:
Spec written to `docs/exec-plans/specs/<filename>.md`. Please review it and tell me what should change before I create the implementation plan.
If the user requests changes, update the spec and repeat the review. Continue only after approval.
The terminal state is harness-plan. Do not invoke implementation, dispatch, verification, or finish skills from this skill.
development
Deep initialization of project AGENTS.md hierarchy and control plane for AI coding agents. Use this skill whenever the user wants to set up, initialize, bootstrap, or create AGENTS.md / CLAUDE.md files for their project, or when they mention "init-deep", "harness setup", "control plane", "agent context", "project initialization for agents", or want to make their codebase agent-ready. Also trigger when a user says things like "set up my repo for Claude Code", "make this project work better with agents", "create agent instructions", "bootstrap harness", or "initialize agent docs". This skill handles both existing large codebases (where hierarchical, module-scoped AGENTS.md files are needed) and new/small projects (where brainstorming with the user comes first). Do NOT use this skill for routine code changes, bug fixes, or general documentation — it is specifically for creating the structured agent control plane.
development
Detect and fix drift in project AGENTS.md files and agent control plane. Use this skill whenever the user wants to audit, recalibrate, refresh, update, or fix their existing AGENTS.md files, or when they mention "drift", "stale AGENTS.md", "outdated agent instructions", "recalibrate", "sync agents", "audit control plane", "AGENTS.md is wrong/old/broken", or when they suspect their agent harness has fallen out of sync with the codebase. Also trigger when a user says things like "my agents keep making wrong assumptions", "Claude doesn't understand the new structure", "we refactored but the AGENTS.md is old", "check if my AGENTS.md is still accurate", or "update my agent docs". This skill is the companion to init-deep — init-deep creates the control plane from scratch, drift-doctor maintains it over time. Do NOT use for initial creation of AGENTS.md (use init-deep instead). Do NOT use for general code review or documentation updates unrelated to agent context.
development
Use when adding, fixing, reviewing, or generating code comments, docstrings, Javadoc, JSDoc/TSDoc, rustdoc, SQL comments, or documentation comments for source, markup, configuration, or database files.
development
Enforce production-grade Java development standards when writing, reviewing, or architecting Java code. Covers commenting, core Java idioms (Stream, collections, concurrency, generics), 23 GoF design patterns, SonarQube/Alibaba p3c/Lombok rules, Spring Boot MVC structure, Spring Cloud DDD microservices, MyBatis/JPA/transaction management, exception handling, logging, REST API design, testing, and security. Trigger whenever the user writes Java code, reviews Java code, designs a Spring Boot or Spring Cloud project, implements a design pattern, fixes code smells, discusses architecture, or asks about Java best practices. Also trigger when Java code is pasted for feedback or the user asks about package structure, DTO/VO/PO conventions, or coding standards.