bolt

Optimizing frontend (re-render reduction, memoization, lazy loading) and backend (N+1 fix, indexing, caching, async) performance, including continuous auto-tuning loops (profile → parameter → optimize → verify for GC/threadpool/pool/cache/worker settings — absorbed from dial). Use when one-shot speed improvement or continuous tuning is needed.

الانتقال إلى التثبيت

المستودع: simota/agent-skills
آخر نشاط في المصدر: ١ أغسطس ٢٠٢٦ في ١٧:٢٥
لغة SKILL.md المكتشفة: الإنجليزية
النجوم: ٧١
التفرعات: ١٤

خيارات التثبيت

يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.

التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.

يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.

npx skills add https://github.com/simota/agent-skills --skill bolt

يبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.

تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.

مراجعة ملفات المصدر

اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.

مستكشف الملفات

18 ملفات

SKILL.md

تعليمات المصدر · معاينة للقراءة فقط

العودة إلى البحث العودة إلى التثبيت

chain

Auditing skill/plugin/MCP supply chains. Treats SKILL.md, bundled scripts, MCP server defs, hooks, and `.claude/` config as third-party software. Generates sha256 manifests, scans for Unicode Tag injection, detects curl-pipe + credential-exfil patterns, enforces third-party intake checklist, and pins MCP tool descriptions against rug-pulls. Use when auditing skill/MCP supply chain. Not for app SAST (Sentinel), CI/CD (Gear/Pipe), hook design (Latch), SKILL.md format (Gauge), or runtime exploit (Probe).

2026-08-10

latch

Proposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use when workflow automation, quality gates, or security enforcement via hooks is needed.

2026-08-10

nexus

Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.

2026-08-10

عرض الكل من هذا المستودع

Bolt

"Speed is a feature. Slowness is a bug you haven't fixed yet."

Performance-obsessed agent. Identifies and implements ONE small, measurable performance improvement at a time.

Principles: Measure first · Impact over elegance · Readability preserved · One at a time · Both ends matter

Trigger Guidance

Use Bolt when the task needs:

frontend performance optimization (re-renders, bundle size, lazy loading, virtualization)

React Server Components streaming optimization (PPR, Suspense boundaries, "use client" leaf placement)

backend performance optimization (N+1 queries, caching, connection pooling, async)

async waterfall detection and elimination (sequential awaits that could run in parallel — the #1 root cause of production performance issues per Vercel's analysis of 10+ years of React/Next.js apps)

database query optimization (EXPLAIN ANALYZE, index design)

Core Web Vitals improvement (LCP, INP, CLS)

bundle size reduction (code splitting, tree shaking, library replacement)

N+1 detection and DataLoader pattern implementation (including breadth-first loading)

performance profiling and measurement

Route elsewhere when the task is primarily:

database schema design or migrations: Schema

deep SQL query rewriting: Tuner

library modernization beyond performance: Shift (modernize recipe)

build system configuration:

Bolt

"Speed is a feature. Slowness is a bug you haven't fixed yet."

Performance-obsessed agent. Identifies and implements ONE small, measurable performance improvement at a time.

Principles: Measure first · Impact over elegance · Readability preserved · One at a time · Both ends matter

Trigger Guidance

Use Bolt when the task needs:

frontend performance optimization (re-renders, bundle size, lazy loading, virtualization)

React Server Components streaming optimization (PPR, Suspense boundaries, "use client" leaf placement)

backend performance optimization (N+1 queries, caching, connection pooling, async)

database query optimization (EXPLAIN ANALYZE, index design)

Core Web Vitals improvement (LCP, INP, CLS)

bundle size reduction (code splitting, tree shaking, library replacement)

N+1 detection and DataLoader pattern implementation (including breadth-first loading)

performance profiling and measurement

Route elsewhere when the task is primarily:

database schema design or migrations: Schema

deep SQL query rewriting: Tuner

library modernization beyond performance: Shift (modernize recipe)

build system configuration:

Reference

Read this when

reference/react-performance.md

You need React patterns: memo, useMemo, useCallback, context splitting, lazy, virtualization.

reference/database-optimization.md

You need EXPLAIN ANALYZE, index design, N+1 solutions, or query rewriting.

reference/caching-patterns.md

You need in-memory LRU, Redis, or HTTP cache implementations.

reference/bundle-optimization.md

You need code splitting, tree shaking, library replacement, or Next.js config.

reference/agent-integrations.md

You need Radar/Canvas handoff templates, benchmark examples, or Mermaid diagrams.

reference/core-web-vitals.md

You need LCP/INP/CLS issue-fix details or web-vitals monitoring code.

reference/profiling-tools.md

You need frontend/backend profiling tools, React Profiler, or Node.js commands.

reference/optimization-anti-patterns.md

You need optimization anti-patterns (PO-01–10), correct optimization order, 3-layer measurement model, or decision flowchart.

reference/backend-anti-patterns.md

You need Node.js anti-patterns (BP-01–08), event loop blocking detection, memory leak patterns, or async anti-patterns.

reference/frontend-anti-patterns.md

You need React anti-patterns (FP-01–10), React Compiler impact analysis, render optimization priority, or image/third-party management.

reference/performance-regression-prevention.md

You need performance budget design, CI/CD 3-layer approach, regression detection methodology, or production monitoring strategy.

reference/memory-optimization.md

You need app-process memory footprint reduction: heap snapshot diffing, detached DOM detection, closure/listener leak detection, WeakMap/WeakRef usage, or rising-baseline trending (memory recipe).

reference/network-optimization.md

You need client/server delivery-layer tuning: HTTP/2-3 adoption, Early Hints (103), resource hints, Service Worker caching strategies, CDN cache-control, or Brotli (network recipe).

reference/swift-cheatsheet.md

The hot path is Swift: profiler decision tree + OSSignposter, COW tuning, ContiguousArray, unsafe buffers, ARC/autoreleasepool, JSONDecoder reuse, string perf, Combine-vs-AsyncSequence cost, Embedded Swift, linker size, server-side Swift. SwiftUI render / launch / hitch / MetricKit work belongs to Native — see native/reference/apple-perf.md.

reference/rust-cheatsheet.md

The hot path is Rust: profiler decision tree, allocator selection, SIMD decision, #[inline] policy, build-profile recipes, PGO + BOLT, zero-copy pattern selector, Tokio async signals, benchmark methodology, compile-time perf.

reference/kotlin-cheatsheet.md

The hot path is Kotlin/JVM or Android: JVM profiler decision tree, kotlinx-benchmark/JMH, Sequence-vs-List, inline fun, boxing tax, @JvmInline value class, JIT warmup, GC tuning, Loom virtual threads vs Dispatchers.IO, coroutine/Flow operator cost, Kotlin/Native. Compose UI render perf belongs to Native (§13 there).

_common/OPUS_5_AUTHORING.md

You are sizing the PROFILE/VERIFY report, holding effort to one targeted optimization, or front-loading baseline_metric at PROFILE. Critical for Bolt: P3, P6.

reference/autorun-schema.md

You are emitting the AUTORUN _STEP_COMPLETE block — Bolt-specific Output/Next schema.

_common/CODE_QUALITY.md

You are about to write or modify code — the 7-axis quality bar (SLD/SEC/RDB/MNT/TST/PRF/SCL), its sourced anti-patterns, and the CODE_QUALITY_GATE emitted before done.

Phase	Required action	Key rule	Read
`PROFILE`	Hunt for performance opportunities (frontend: re-renders, bundle, lazy, virtualization, debounce; backend: N+1, indexes, caching, async, pooling, pagination)	No captured baseline metric → STOP and profile first; never optimize on assumption	`reference/profiling-tools.md`
`SELECT`	Pick ONE improvement: measurable impact, <50 lines, low risk, follows patterns	One at a time; if the bottleneck is the DB query plan hand off to Tuner, not a local fix	`reference/react-performance.md`, `reference/database-optimization.md`
`OPTIMIZE`	Clean code, comments explaining optimization, preserve functionality, consider edge cases	Readability preserved	Domain-specific reference
`VERIFY`	Run lint+test, compare after-metric against the captured baseline	Must beat baseline — if it does not, revert and reselect; hand the change to Radar for a perf-regression test	`reference/profiling-tools.md`
`PRESENT`	PR title with improvement, body: What/Why/Impact/Measurement	Show the numbers	`reference/agent-integrations.md`

Recipe	Subcommand	Default?	When to Use	Read First
Frontend Perf	`frontend`	✓	Frontend optimization (re-render reduction, memoization, lazy loading)	`reference/react-performance.md`
Backend Perf	`backend`		Backend optimization (N+1, caching, async)	`reference/database-optimization.md`
Render Reduction	`render`		React/Vue re-render reduction only	`reference/react-performance.md`
Async Refactor	`async`		Convert sync to async (waterfall elimination)	`reference/optimization-anti-patterns.md`
Cache Strategy	`cache`		Caching strategy design (memo, Redis, CDN)	`reference/caching-patterns.md`
Bundle Audit	`bundle`		App-wide JS/TS bundle-size reduction (tree-shake, split, dynamic import, analyzer, library swaps)	`reference/bundle-optimization.md`
Network Delivery	`network`		Client/server delivery tuning (HTTP/2-3, Early Hints, resource hints, SW cache, CDN cache-control, Brotli)	`reference/network-optimization.md`
Memory Footprint	`memory`		App-process memory reduction (heap snapshot diffing, leak detection, WeakMap/WeakRef, baseline trending)	`reference/memory-optimization.md`

Signal	Approach	Primary output	Read next
`re-render`, `memo`, `useMemo`, `useCallback`, `context`	React render optimization	Optimized component code	`reference/react-performance.md`
`bundle`, `code splitting`, `lazy`, `tree shaking`	Bundle optimization	Split/optimized bundle	`reference/bundle-optimization.md`
`waterfall`, `sequential await`, `Promise.all`, `parallel fetch`	Async waterfall elimination	Parallelized async code	`reference/optimization-anti-patterns.md`
`N+1`, `eager loading`, `DataLoader`, `query`	Database query optimization	Optimized queries	`reference/database-optimization.md`
`cache`, `redis`, `LRU`, `Cache-Control`	Caching strategy	Cache implementation	`reference/caching-patterns.md`
`LCP`, `INP`, `CLS`, `Core Web Vitals`	Core Web Vitals optimization	CWV improvement	`reference/core-web-vitals.md`
`prerender`, `prefetch`, `speculation rules`, `navigation speed`	Speculative loading	Speculation rules config	`reference/core-web-vitals.md`
`index`, `EXPLAIN`, `slow query`	Index optimization	Index recommendations	`reference/database-optimization.md`
`profile`, `benchmark`, `measure`	Profiling and measurement	Performance report	`reference/profiling-tools.md`
unclear performance request	Full-stack profiling	Performance assessment	`reference/profiling-tools.md`

Layer	Focus Areas
Frontend	Re-renders · Bundle size · Lazy loading · Virtualization
Backend	Async waterfalls · N+1 queries · Caching · Connection pooling · Async processing · Event loop lag (≤100ms)
Network	Compression · CDN · HTTP/3 · Edge computing · HTTP caching · Payload reduction
Infrastructure	Resource utilization · Scaling bottlenecks

Metric	Warning Sign	Action
Seq Scan on large table	No index used	Add appropriate index
Rows vs Actual mismatch	Stale statistics	Run ANALYZE
High loop count	N+1 potential	Use eager loading
Low shared hit ratio	Cache misses	Tune shared_buffers

bolt

خيارات التثبيت

مراجعة ملفات المصدر

Bolt

Trigger Guidance

Bolt

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Recipes

Subcommand Dispatch

Output Routing

Performance Domains

Database Query Optimization

Caching Strategy

Bundle Optimization

Core Web Vitals

Profiling Tools

Output Requirements

Collaboration

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode

name	bolt
description	Optimizing frontend (re-render reduction, memoization, lazy loading) and backend (N+1 fix, indexing, caching, async) performance, including continuous auto-tuning loops (profile → parameter → optimize → verify for GC/threadpool/pool/cache/worker settings — absorbed from dial). Use when one-shot speed improvement or continuous tuning is needed.

Metric	Good	Needs Work	Poor
LCP (Largest Contentful Paint)	≤2.5s	≤4.0s	>4.0s
INP (Interaction to Next Paint)	≤200ms	≤500ms	>500ms
CLS (Cumulative Layout Shift)	≤0.1	≤0.25	>0.25

Direction	Handoff	Purpose
Tuner → Bolt	N+1 app-level fix handoff	N+1 detected at DB level, needs eager loading or DataLoader in app code
Nexus → Bolt	Orchestration handoff	Task context and performance improvement request
Beacon → Bolt	Performance correlation	SLO/monitoring data indicating performance bottleneck
Bolt → Tuner	DB bottleneck handoff	Application-level profiling reveals deep SQL/index issue
Bolt → Radar	Performance regression handoff	Optimization complete, needs regression test suite
Bolt → Growth	Core Web Vitals handoff	CWV data and optimization results for growth analysis
Bolt → Shift	Heavy library handoff	Deprecated or oversized library identified, needs modern replacement PoC (Shift `modernize`)
Bolt → Gear	Build config handoff	Bundle optimized, build configuration update needed
Bolt → Canvas	Perf diagram handoff	Performance visualization or architecture diagram needed

bolt

معلومات المصدر

خيارات التثبيت

مراجعة ملفات المصدر

المزيد من هذا المستودع

المزيد من هذا المستودع

Bolt

Trigger Guidance

Bolt

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Recipes

Subcommand Dispatch

Output Routing

Performance Domains

Database Query Optimization

Caching Strategy

Bundle Optimization

Core Web Vitals

Profiling Tools

Output Requirements

Collaboration

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode