Research and Audits
Research and audit skills help with investigation, competitive analysis, due diligence, and structured reviews of a product, market, or codebase. Use this category when the job is to understand something deeply, compare options, or surface risks before acting.
844 skills
Skills in this category
session-analyzer
by ai-native-camp/camp-2
Post-hoc analysis tool for validating Claude Code session behavior against SKILL.md specifications.
optimizing-attention-flash
by davila7/claude-code-templates
Flash Attention provides 2-4x speedup and 10-20x memory reduction for transformer attention through IO-aware tiling and recomputation.
symfony:controller-cleanup
by makfly/superpowers-symfony
Source details, install context, and public review data are available on the full page.
fastapi-code-review
by existential-birds/beagle
Source details, install context, and public review data are available on the full page.
quality-manager-qmr
by alirezarezvani/claude-skills
Quality system accountability, management review leadership, and regulatory compliance oversight per ISO 13485 Clause 5.5.2 requirements.
transformer-lens-interpretability
by davila7/claude-code-templates
TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.
botchan
by bankrbot/openclaw-skills
The onchain agent messaging layer on the Base blockchain.
qms-audit-expert
by alirezarezvani/claude-skills
ISO 13485 internal audit methodology for medical device quality management systems.
opc-architecture
by parcadei/continuous-claude-v3
OPC (Orchestrated Parallel Claude) extends Claude Code - it does NOT replace it.
startup-business-analyst-business-case
by sickn33/antigravity-awesome-skills
Generate a comprehensive, investor-ready business case document covering market opportunity, solution, competitive landscape, financial projections, team, risks, and funding ask for startup fundraising and strategic planning.
seo-content-optimizer
by onewave-ai/claude-skills
Comprehensive SEO analysis and optimization for content creators and marketers.
expo
by pproenca/dot-skills
Comprehensive performance optimization guide for Expo React Native applications. Contains 54 rules across 9 categories, prioritized by impact to guide automated refactoring and code generation.
kotlin-concurrency-expert
by new-silvermoon/awesome-android-agent-skills
Review and fix Kotlin Coroutines issues in Android codebases by applying structured concurrency, lifecycle safety, proper scoping, and modern best practices with minimal behavior changes.
mcp-management
by mrgoonie/claudekit-skills
Skill for managing and interacting with Model Context Protocol (MCP) servers.
migrate
by parcadei/continuous-claude-v3
Safe migrations for frameworks, languages, and infrastructure.
tldr-deep
by parcadei/continuous-claude-v3
Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.
tldr-router
by parcadei/continuous-claude-v3
Maps questions to the optimal tldr command. Use this to pick the right layer.
validate-agent
by parcadei/continuous-claude-v3
Note: The current year is 2025. When validating tech choices, check against 2024-2025 best practices.
agentica-server
by parcadei/continuous-claude-v3
Complete reference for running Agentica SDK with a local Claude proxy. This enables Python agents to use Claude CLI as their inference backend.
clip
by davila7/claude-code-templates
OpenAI's model that understands images from natural language.
codable-patterns
by dpearson2699/swift-ios-skills
Encode and decode Swift types using Codable ( Encodable & Decodable ) with JSONEncoder , JSONDecoder , and related APIs. Targets Swift 6.2 / iOS 26+.
sparse-autoencoder-training
by davila7/claude-code-templates
SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.
tdd-migrate
by parcadei/continuous-claude-v3
Orchestrate TDD migrations with agents doing all work. Main context stays clean.
typescript-review
by metabase/metabase
Source details, install context, and public review data are available on the full page.