izmailovilya/ilia-izmailov-plugins
Agent
Research team module that stress-tests findings through 3 lenses: Evidence Quality (verify Source Tags), Pre-Mortem (imagine the research was wrong), and Frame Gap Detection (find missing perspectives). Actively adversarial, not a passive checklist. Context: All investigators have reported — challenger reviews their…
izmailovilya/ilia-izmailov-plugins
Agent
Research team module for quick landscape scanning. Identifies 3-7 distinct areas, suggests investigation angles with depth tiers, and estimates complexity. Fast (max 5 minutes) — maps terrain, doesn't investigate. Context: Research lead needs to understand codebase before spawning investigators lead: "Research…
izmailovilya/ilia-izmailov-plugins
Agent
Research team module spawned on-demand for domain-specific deep dives (security, database, external-api). Created when an investigator flags ESCALATE for a specific domain. Uses Depth Protocol for findings. Context: Investigator flagged security code needing expert review lead: "Investigator found auth/crypto code in…
izmailovilya/ilia-izmailov-plugins
Skill Claude CodeCodex
Launch Agent Team for parallel deep codebase/topic research — causal understanding, not just coverage. Use this skill whenever the user asks to 'research the codebase', 'understand how X works', 'investigate', 'explore architecture', 'analyze the codebase', 'how does this work', 'deep dive into', 'trace how data…
izmailovilya/ilia-izmailov-plugins
Plugin Claude Code
Interactive feature audit for vibe-coded projects. Finds dead code, unused features, and experiments through conversation with the developer.
izmailovilya/ilia-izmailov-plugins
Agent
Executes cleanup actions after user confirms what to delete. Handles safe removal with git backup. Context: User confirmed features to delete user: "Удали rat-hypothesis" assistant: "Запускаю cleanup-executor для безопасного удаления с git backup".
izmailovilya/ilia-izmailov-plugins
Agent
A codebase scanner that finds features which may be unused or still experimental. It returns a structured list for the developer to review through conversation.
izmailovilya/ilia-izmailov-plugins
Agent
This agent should be used when auditing src/features/ directory for dead code, unused exports, and duplication. Triggers on: "audit features", "find dead code in features", "clean up features/", "check features for unused code". Context: User wants to audit feature modules for cleanup user: "Проверь features на…
izmailovilya/ilia-izmailov-plugins
Agent
This agent should be used when auditing src/server/ directory for dead code, API inconsistencies, and unused routers. Triggers on: "audit server", "find dead code in server", "clean up routers", "check API for unused endpoints". Context: User wants to clean up server-side code user: "Проверь сервер на мёртвый код"…
izmailovilya/ilia-izmailov-plugins
Agent
This agent should be used when auditing src/stores/ directory for unused stores, redundant state, and Zustand patterns. Triggers on: "audit stores", "find unused stores", "clean up state management", "check Zustand stores".
izmailovilya/ilia-izmailov-plugins
Agent
This agent should be used when auditing src/design-system/ and UI components for unused components, style inconsistencies, and duplication. Triggers on: "audit design system", "find unused components", "clean up UI", "check design-system for dead code".
izmailovilya/ilia-izmailov-plugins
Agent
A detailed review of how one feature is used throughout a codebase. It follows references to that feature so you can understand its role before making a decision about it.
izmailovilya/ilia-izmailov-plugins
Skill Claude CodeCodex
Interactive feature audit — finds dead code, unused experiments, and abandoned features through conversation. Use this skill when the user asks to 'clean up the project', 'find dead code', 'audit the codebase', 'what can we delete', 'find unused code', 'project cleanup', 'remove old experiments', or wants to reduce…
izmailovilya/ilia-izmailov-plugins
Plugin Claude Code
Set up, harden, or audit deployment so releases don't interrupt service — with a rollback that has actually been rehearsed.
izmailovilya/ilia-izmailov-plugins
Agent
Read-only scout that maps how a deploy is SUPPOSED to work according to the repository: what starts the app, what sits in front of it, workers and cron, migrations, secrets, and what a rollback would look like. Every finding names the file it came from — it never claims to know what production actually runs. Context…
izmailovilya/ilia-izmailov-plugins
Agent
Read-only scout that finds out what is ACTUALLY running in production — process manager, proxy config in force, live version, instance count — and reports the drift against what the repository claims. Every fact carries the command that produced it, and anything unreachable is reported as unknown, never guessed.…
izmailovilya/ilia-izmailov-plugins
Agent
Adversarial reviewer of a finished deployment scheme. Its job is to prove two things wrong: that users will not see errors during a release, and that the rollback will work when it is actually needed. Spawned at the end of a zero-downtime deploy run, because whoever built the scheme is the worst judge of it. Context…
izmailovilya/ilia-izmailov-plugins
Skill Claude CodeCodex
A skill for setting up, strengthening, or checking zero-downtime deployments, where service continues while a new version is released.
Plugin Claude Code
Advanced Jobs To Be Done methodology plugins and tools.
Plugin Claude Code
Advanced Jobs To Be Done methodology plugin - analyze product risks, find market segments, generate landing pages using AJTBD framework.
Agent
Deep product analysis expert with full access to AJTBD methodology book.
Command
Generate 5 most attractive B2B segments using AJTBD methodology.
Command
Generate 5 most attractive B2C segments using AJTBD methodology.
Command
Generate a detailed jobs graph below Core Job level for a segment.