nobrainer-tech/nobrainer-tech-flow
From task to done. nobrainer-tech-flow is one workflow of 18 modules for AI coding agents and the AI-native SDLC: it scopes the task, does the work in one main loop, checks the result and hands over the evidence, including what was not checked.
Use when setting up nobrainer-tech-flow for the first time, or when client capabilities, model routing, context or useful parallelism need recalibration. Alias: nb-auto-fine-tune.
Use when a skill or prompt needs to improve and a measurable, bounded baseline-variant-evaluation loop should replace one subjective rewrite. Aliases: nb-autoimprove, deep-autoresearch, code-autoresearch, nobrainer-capture-lesson, nobrainer-continuous-improvement.
Use when you need to inspect or operate a rendered website, attach to an existing approved Chrome/Edge session, restart an approved non-default Chromium profile for loopback CDP, reproduce a browser flow, run Playwright tests, or record and analyze a Playwright trace. Prefer a current Playwright CLI with an explicit version readback; do not set up MCP or extra browser plugins by default. Aliases: nb-browser, nobrainer-browser.
Use when outcome and acceptance are clear and an approved, bounded code, configuration, documentation or test change must be implemented or simplified; apply the smallest verified edit with calibrated KISS, DRY, SOLID, YAGNI and anti-slop gates. Aliases: nb-build, engineering-standards, nobrainer-simplifier.
Use when one project's instructions for coding agents (AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, Copilot instructions) need setup, an audit or tidying: find what each client loads and its size against documented limits, report duplicates and contradictions, then propose one source of truth with short pointers, applied only after approval and read back. Alias: nb-context.
Use when choosing between options: just decide for a quick choice, decide or nb-decide for standard analysis, deep decide or deep-decide for deep analysis. Evaluate feasibility, reliability, total cost, delivery time, scale and reversibility.
Use when an approved plan has multiple queued work units that require ready-set selection, dependency-aware ordering, bounded parallel batches, retry scheduling, or routing audited results to the next queued unit; do not use for one coherent task, one bounded delegate, a standalone receive-audit, requirements, team design, or session transport. Aliases: nb-dispatcher, nobrainer-dispatcher.
Use when an incident, regression, test failure, outage, wrong value or unexpected system behavior has an unclear cause and needs an evidence-bound diagnosis before anyone proposes a fix. Aliases: nb-rca, deep-rca.
Use when a task depends on current, niche, uncertain, high-stakes or source-attributed facts, when external information must be researched or verified, or when a problem needs current external evidence rather than a stable local diagnostic. Alias: nb-research.
Use when work needs an evidence-gated CLOSEOUT, an adversarial BUG_HUNT or a RELEASE_GATE, when someone asks for a DoD (Definition of Done) of a pull request or whether a PR is ready to merge, including after green CI, when someone asks for implicit or hidden state machines (states spread over flags, status strings or counters), or when final findings must be filtered to verified actionable defects. Use nobrainer-build for ordinary implementation and correction work. Aliases: nb-review, deep-audit, deep-code-review, deep-autoreview, nb-dod, PR DoD, nb-auto-fix.
Use when a change crosses authentication, authorization, secrets, untrusted input, sensitive data, dependency, installer or production trust boundaries, or when you need a threat model or security review. Aliases: nb-security, security-review.
Use when work needs visible, named, reusable sessions with exact identity, isolated write scopes, audited handoffs, recovery or controlled parallelism; do not use for a coherent one-session task. Aliases: nb-sessions, nb-multi, session-handoff, session-restart, nb-session-restart.
Use when a skill or task prompt needs a quality audit, or when instructions conflict across projects. For which instruction files coding agents load in one project, use nobrainer-context. Alias: nb-skill-doctor.
Use when implementation needs a durable, reviewable specification because it changes architecture, public contracts, migrations, several dependent components, or work that may span sessions. Alias: nb-sdd.
Use when an approved non-trivial plan from nobrainer-tech-flow needs an installed-capability inventory, bounded worker assignments, task-local specialist briefs or native parallel execution; do not use to elicit requirements, invent the plan, schedule work, or create sessions. Aliases: nb-team, nobrainer-skill-browser.
Use when you want to set up, start, resume or complete a coding or non-coding task: scope the outcome, use native workers only where they help, and verify delivery. Aliases: NBFlow, NBF, nobrainer-tech-flow.
Use when durable knowledge must be saved or found again, a wiki must be created or queried, or a Markdown knowledge base across projects or sessions needs a safe audit or upkeep; do not use for transient task state. Aliases: nb-wiki, nb-add, nb-get, nb-tidy, llm-wiki.
Use when a user-facing artifact needs prose quality work, such as drafting, rewriting, compressing, humanizing, editing or reviewing it; maximize useful information per word without dropping facts, evidence, caveats, voice or required action. Aliases: nb-write, nb-brief, nobrainer-writing, nobrainer-style, nobrainer-human-like.