abid-agents

Use for /he:plan; stage 1 readiness with Treehouse, Grill Me, owner, proof path, PASS/FAIL.

Use for UI components, design systems, atomic design, tokens, themes, hardcoded visuals, or missing design SSOT.

Use for module boundaries, public APIs, ownership, abstractions, wrappers, test seams, or architecture review.

Use for visual PDFs: create, polish, export, verify decks, reports, proposals, one-pagers, or HTML-to-PDF.

Use for hard bugs, failing behavior, flaky tests, exceptions, regressions, or unexplained slowness before fixing.

Use for real UI E2E smoke/regression proof across web, Flutter, browser, Chrome, or device flows, with artifacts.

Interview one clear question before planning/building ideas, features, codebase maps, specs, UI flows, prototypes, or final plans.

Use for /he:implement; owner-first implementation after PASS, deterministic owner reuse, and lint/scanner/gate coverage.

Use for /he:learn; durable guard after repeated misses, review loops, or workflow gaps.

Use for /he:ship; committed final gate with status, hook readiness, no-mistakes axi, PR evidence, CI.

Use for /he:verify; verification loop with tests, risk review, thermo review, E2E artifacts.

Use for no-mistakes validation, safe push, PR/CI gate, or `/no-mistakes` after committed code changes.

Use for slowness, latency, p50/p95, efficiency, benchmarks, or making apps, APIs, queries, or UI faster.

Use only when product video, demo recording, walkthrough, explainer, onboarding reel, or launch clip is explicit.

Use when repeated fixes, trial-and-error, recurring misses, or "same issue again" require durable learning before final.

Use for defensive appsec review: auth, secrets, deps, APIs, LLMs, data exposure, OWASP.

Always use for user-facing replies. Be brief; preserve exact code/API names, paths, commands, errors, dates, user wording.

Use for tests/specs/QA/TDD/mutation: design, write, review, repair, behavior assertions, failure proof.

Use for strict maintainability review: diffs, PRs, commits, wrappers, abstractions, spaghetti, giant files, weak tests.

Use to turn a PRD, plan, or resolved feature discussion into agent-ready vertical-slice issues.

Use to turn resolved conversation, repo evidence, or a plan into a concise PRD, spec, or implementation brief.

Use for Treehouse CLI, tree house/treehouse, reusable worktrees, leases, status, return, or worktree isolation.

Website launch readiness for SEO, Cloudflare, analytics, performance, security.txt, and AI-agent discovery.

Use for workflow, skill, next-step, BMAD comparison, or feature-to-PR routing questions.

Use codebase graph for symbols, callers, deps, routes, impact, dead code, Cypher, search_graph, trace_path.