core

Plugin core from marketplace claude-specs in vmaia00/claude-specs. Commands read from the repo's manifest — 1 month ago.

Skills (5)

• diagnose

  Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

• intended-vs-implemented

  The method for finding the gap between what a system is supposed to do and what the code actually does — the class of bug generic scanners miss because they have no model of intent. Defines what counts as documented intent, what counts as implementation evidence, which mismatches matter, and how to

• react-bits

  Animated, interactive React components (react-bits) for adding motion and visual flair to front-end UI — the part Claude builds weakest. Use when building React/Next.js interfaces and the user wants animation, a memorable hero/landing, scroll/text effects, animated backgrounds, or to escape the gene

• shipping-artifacts

  The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SE

• write-a-skill

  Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Slash commands (4)

• /core:derive-tests

  Turn documented intent into a test-coverage map — inventory the tests that exist today, derive use-case cases from the system docs, separate existing coverage from proposed tests and unverified gaps, mark each unit / guarded-live / manual, and recommend a green-before-merge CI gate

• /core:document-app

  Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply

• /core:init-repo

  Scaffold a minimal starter CLAUDE.md (+ AGENTS.md pointer) for the repo-specific layer

• /core:new-project

  Scaffold a new sub-project from this repo's _template/ folder

Subagents (4)

• builder

  Writes and edits code/docs to the repo's conventions. Use for any file creation or modification.

• explorer

  Read-only researcher. Use to find code, answer "where/how is X", and gather references. Returns concise findings with file:line citations — never edits.

• planner

  Read-only implementation planner. Use to design a change and assess its blast radius before any code is written. Returns a step-by-step plan.

• reviewer

  Read-only pre-commit reviewer. Use before committing to check secrets, convention compliance, tests, and link integrity. Returns a pass/fail checklist.

Hooks (5)

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/secret-scan.mjs"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs"

Similar plugins