ai-cost-manager-reducer
openbooklet.com/s/ai-cost-manager-reduceropenbooklet.com/s/[email protected]GET /api/v1/skills/ai-cost-manager-reducerAudit AI-powered features, API calls, agent workflows, prompt chains, tool calls, embeddings, vector search, retries, streaming flows, background jobs, cron tasks, caching layers, logs, and model selection logic to detect token waste, repeated AI calls, and inefficient prompt chains. Produces severity-ranked findings with safe optimization strategies that preserve reasoning quality and chain reliability. Use before approving or modifying any AI-powered feature, agent workflow, or model-calling code.
Review Supabase RPC/PostgREST API contracts for DTO correctness, response consistency, validation quality, and backward-compatibility risk. Use when changing libs/api/*, shared response types, or API-facing behavior.
Fix performance issues in apps/arena for leaderboards, battles, rankings, vote/reaction summaries, and high-cardinality result pages.
Use the CLI app for reproducible scale diagnostics, seed validation, benchmark execution, and performance investigation for Supabase and frontend-facing query paths.
Review consistency between API contracts, DTOs, domain types, and consumer expectations. Use for payload design, serialization issues, nullable mismatch, naming drift, and transport/domain boundary checks.
Create or refine compact technical documentation, READMEs, public docs, and contribution guides. Use for OSS-facing docs, internal docs cleanup, navigation design, and converting implementation details into concise Claude-style markdown.
Use when implementing the /lenser route, restricted profile shell, lock-state UI, follow request UX, and route-state rendering for public, private, deactivated, and deleted profiles.
Review design decisions using GRASP, OOAD responsibility assignment, and standard refactoring rules. Use when code placement, object responsibility, coupling, cohesion, or refactoring direction is unclear.
Implement full i18n support for **$ARGUMENTS** across the LenserFight monorepo.
Assess Supabase/Postgres migration blast radius, rollback difficulty, data loss risk, permission regression risk, and rollout safety. Use before applying migrations to shared environments or bundling schema changes into a release.
Deprecated alias for the canonical `mobile-ruleset` mobile workspace rules.
Use when implementing new mobile features in apps/mobile or libs/* with Expo/React Native and the shared mobile design system.
Use when planning mobile app features, roadmaps, or research-backed product decisions for apps/mobile.
Use when reviewing apps/mobile or libs/* for mobile performance, security, storage, network, permissions, or render-cost risks.
Shared mobile workspace rules for apps/mobile and libs/* in lenserfight. Use when navigating native UI boundaries, shared tokens, verification defaults, or the canonical mobile design ruleset.
The strategic authority for LenserFight. Translates ambiguous requests into product decisions, scope cuts, acceptance criteria, and implementation priorities.
Use when validating schema migrations, privacy regressions, deletion workflows, sign-in cancellation logic, and rollout safety for social graph and profile access changes.
Review React and Vite web app code changes for browser performance, memory usage, CPU pressure, bundle size, network cost, rendering speed, hydration cost, and behavior under high traffic, slow devices, weak networks, and large datasets. Use when reviewing apps/web, libs/* used by the web app, or any React component, hook, route, Vite config, code split boundary, dynamic import, asset, state manager, API call, form, table, chart, animation, or third-party library. Activate when the user says "review", "check perf", "slow page", "heavy bundle", or whenever React/Vite browser code is in scope. Detects: unnecessary re-renders, unstable props/callbacks, context churn, missing memoization, memory leaks, large bundle growth, unused dependencies, inefficient asset loading, render-blocking resources, over-fetching, repeated network requests, poor cache strategy, large JSON payloads, expensive sync computations, layout thrashing, slow startup paths, and weak error/retry behavior.
Review whether a change set is ready for release across code, migrations, tests, docs, and rollout planning. Use before production releases, high-risk merges, or milestone sign-off.
Audit Nx monorepo structure, layer responsibilities, dependency drift, public APIs, and misplaced logic. Use for architecture review, library placement, boundary erosion, duplication, and repo health checks.
Enforce performance-safe query and rendering patterns across this Nx monorepo. Use when working on Vite freezes, Supabase overfetching, pagination, caching, CPU hotspots, memory pressure, or large seeded datasets.
Auto-indexed from conectlens/lenserfight
Are you the author? Claim this skill to take ownership and manage it.
Related Skills
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
audience-aware-communication
Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.
Refactoring Expert
Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.
Research Expert
Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.
clarify-ambiguous-requests
Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.
structured-step-by-step-reasoning
Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.