AI-first React Native and Expo boilerplate. Feature-first architecture, TypeScript, auth, i18n, theming, Redux Toolkit, plus Cursor and Claude rules. Lite tier of AI Mobile Launcher.
This repository also configures its own agents. See what expo_boilerplate tells them →
Skill Claude Code
Health-check the memory bank, rules, and index — flag stale, contradictory, or redundant entries and spec↔code drift. Use when Malik says 'audit the bank', 'is the memory stale', 'check spec harness health', or 'clean up the rules'.
Skill Claude Code
Run the SDD pipeline over tasks.md: implement → test → VERIFY → review, one task at a time, under the ratchet. Use when Malik says 'build it', 'run the pipeline', 'implement the tasks', or 'ship this feature'. Each task gated by the separate verifier; lessons harvested by learn.
Skill Claude Code
Bind the 6 SDD agents to THIS project's rules — fill each agent's GEN:rules region with its concern's real rules (implementer←Coding, tester←Testing+commands, reviewer←Reviewing, researcher/planner←Architecture, verifier←goal). Use when Malik says 'generate the agents', 'make the agents project-specific', 'bind agents…
Skill Claude Code
Add or refresh Spec Harness in a repo — greenfield (new) or existing (integrate), idempotent. Use when Malik says 'install spec harness', 'set this repo up with spec harness', 'integrate spec harness into X', or 'start a new spec-harness project'. Runs the interview (mode, stack, constraints, work-intake source…
Skill Claude Code
The learning loop — turn feedback, a correction, or a verifier-FAIL root cause into one enforced rule injected into the ratchet (AGENTS.md/airules), dated. Use when Malik says 'learn this', 'remember not to do X', 'capture this lesson', 'don't do that again', or right after he corrects you. Closes the loop the…
Skill Claude Code
Turn a spec into a design.md (the 'how' — architecture decisions). Use when Malik says 'plan the implementation', 'how should we build this', or 'design this'. Second SDD step.
Skill Claude Code
Per-directory rules — resolve the nearest RULES.md for a path (coding/architecture/packages/testing/reviewing), or generate it from a directory's real code when missing. Use when Malik says 'different directories have different rules', 'add rules per directory', 'each package needs its own rules', 'what rules apply…
Skill Claude Code
Turn a rough brief into a structured, testable spec.md (the 'what'). Use when Malik says 'spec this', 'write the spec for X', or 'what are the requirements'. First SDD step.
Skill Claude Code
Break a design into atomic, ordered, testable tasks.md. Use when Malik says 'break this into tasks', 'task it out', or 'what are the steps'. Third SDD step.
Skill Claude Code
Intake work into the SDD pipeline — pull tickets from a connected ticket MCP (Linear/GitHub/Jira) or define an inline plan. Use when Malik says 'pull my tickets', 'grab the Linear issues', 'turn this into specs', 'plan this work', or 'what should I build next'. Produces specs/NNN-/ ready for build.
Skill Claude Code
Run the verifier alone — a separate clean-context agent that returns PASS/FAIL against goal.md (not the agent that wrote the code). Use when Malik says 'verify it', 'is it actually done', 'check against the goal', or 'did this pass'. Tests passing ≠ goal met.
Skill Claude Code
The Spec Harness orchestrator — spec-driven development wrapped in a harness (ratchet + verifier + learning loop) over a persistent memory bank. Use when Malik says 'use spec harness', 'run the spec harness', 'spec-harness this feature', or wants the full spec→plan→tasks→build→verify→learn flow. Routes to the…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: