TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Research an external API, vendor, or backend before writing integration code: check for a matching MCP server first, then fall back to docs/REST/scripts. Two phases — schema/contract first, sample/wire shape second — same discipline as the retired airtable-inspect skill, generalized to any vendor. Worked examples…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Bundles all uncommitted work from multiple Cursor agent threads on the same branch and checkout into one finish commit, then pushes. Use when the user runs /bundle-ship, /finish-all, or asks to finish and push everything across threads on one checkout.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Challenges and simplifies a concrete feature to reduce steps, clicks, and cognitive load (flow and code modes by default). Use when the user targets a workflow and asks whether it is overbuilt, or runs /challenge.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Systematically audit the codebase for consolidation, abstraction, and redundancy removal opportunities across features. Use when the user asks to find duplication, consolidate code, audit for redundancy, reduce repetition, or identify shared patterns that should be unified.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Author or refine a single project skill under .agents/skills/ (draft SKILL.md, optional evals, description triggering). Use when the user runs /create-skill or asks to create, edit, or optimize one skill in this repo. Primary outcome: a durable SKILL.md. Evals/benchmarks are optional phases when the user wants them …
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Structured scientific debugging for runtime bugs, regressions, flaky behavior, frontend/backend failures, Supabase/RLS/Auth/Storage issues, and user-reported errors. Use when the user invokes /debug, asks to debug, reports an error, or describes inconsistent behavior.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Runs systematic new-feature engineering with mandatory decision stops; produces product/requirements artifacts, not DEVELOPMENTPLAN.md (plan is SSOT for execution plans). Use for new feature requests before planning. Not implement, validate, or finish.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Completes implementation wrap-up: concurrent-agent smoke checks, version/changelog when required, commit, and coordination before push. Use when closing a job, after implement/validate, or when the user runs /finish. Not push-only (use push) and not planning (use plan).
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Optional warm-start interview until scope edges and interaction boundaries are aligned. Grounds every edge question in what already exists in the repo. Logs closed decisions to DECISIONS.md (shared with plan-grill). IF gate 1 fails (vision/tradeoffs) OR the user wants a stress-test OR says "grill me" THEN use this…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Debug by pre-registered hypothesis instead of guess-and-patch. Before touching code, the agent states the suspected root cause, predicts what a successful fix proves, and pre-registers what a FAILED fix would teach. IF the user invokes hypothesis mode OR naive fixes already failed ≥1 THEN use this skill; ELSE use…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Executes DEVELOPMENTPLAN.md phase by phase with gates, progress updates, and repo-rule compliance. Use when the user asks to implement a plan or continue a job. Not planning (plan), changelog (finish), or read-only audits (validate).
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Audit and improve the .agents/skills library so the skills form a symbiotic whole: clear separation of concerns, single source of truth (SSOT), and no routing or instruction conflicts. Runs parallel Task subagents per lens (inventory, separation/overlap, SSOT/duplication, conflicts, composition/handoffs) and ends with…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Product-facing front door for improving an existing product area, feature, or screen. Resolves target in plain language, checks vision only when missing, runs a silent multi-lens lite audit, shows at most three findings with one recommendation, then invokes the real skill (challenge, standards-align, consolidate…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
PROACTIVE on any request to change existing behavior (and on minimizer/exception language, first-of-a-kind instances, behavior-by-analogy): verify the user's assumption about how the system works before acting — they can't see the implementation, so the assumption is often wrong. REACTIVE when the diff matches a…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Turns recent code changes, failures, and conversation mistakes into durable guidance. Use when the user runs /learn, asks for a retrospective or to sharpen rules, or after resolving a multi-turn struggle (e.g. 3+ failed attempts, critical CI fix).
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Analyzes code for optimization across design, approach, efficiency, and complexity so fixes happen at the right level. Use when the user asks to optimize, reduce complexity, refactor thoughtfully, or assess whether code should be rewritten vs tweaked.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
PROACTIVE: Compare a development plan or implementation proposal to industry standards and common best practice before application code — without waiting for the user to ask. The agent selects relevant aspects (UX, APIs, identity, async, coupling, etc.) per change. Use at planning (especially M/L), feature…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Continuous grill rail during plan: same ask style as grill-me, anti-dup via DECISIONS.md, ask only on true ties (clear winners logged after naming alternatives). IF during plan Refine OR Investigate OR Create the agent is about to lock a product/scope/architecture-boundary choice AND has not yet run the fork checklist…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Creates DEVELOPMENTPLAN.md with repo-rule compliance researched first (file placement, architecture, patterns). Runs plan-grill as a rail beside Refine/Investigate/Create (mandatory fork checklist; anti-dup via DECISIONS.md). Use for new features, M/L work, or /plan. Not XS/S quick changes (quick-piv), product-only…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Fully removes a named feature, component, or module and cleans up trailing references (imports, routes, tests, flags, config, docs). Use when the user runs /purge or asks to delete, remove, rip out, decommission, retire, sunset, or fully clean up a feature/component/module — especially when prior deletions left dead…
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Pushes previously finished commits to remote only; never stages, commits, or amends. Use when finish has already run, the working tree is clean, and local commits exist. If uncommitted changes remain, stop and run finish first.
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Orchestrates compressed Plan → Implement → Validate for small XS/S scoped changes in one session without a full DEVELOPMENTPLAN.md. Use for focused fixes and tweaks. Not M/L work, migrations, or when plan review or pattern-review gates are required (use full plan cycle).
TMI-apps/boilerplate-vite-supabase-mui-cursor
Skill Claude CodeCodex
Stack-native React performance patterns for this Vite SPA (React 19, MUI, TanStack Query, Cloudflare Workers). Use when optimizing bundles, waterfalls, re-renders, or client fetch behavior — not for repo-wide refactors (optimize2) or Lighthouse audits (web-perf).