Skip to main content
Back to registry

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

156

Post-hoc analysis tool for validating Claude Code session behavior against SKILL.md specifications.

Research and Audits

optimizing-attention-flash

by davila7/claude-code-templates

155

Flash Attention provides 2-4x speedup and 10-20x memory reduction for transformer attention through IO-aware tiling and recomputation.

Research and AuditsFirst seen Jan 20, 2026

symfony:controller-cleanup

by makfly/superpowers-symfony

155

Source details, install context, and public review data are available on the full page.

Research and AuditsFirst seen Jan 22, 2026

fastapi-code-review

by existential-birds/beagle

154

Source details, install context, and public review data are available on the full page.

Research and AuditsFirst seen Jan 19, 2026

quality-manager-qmr

by alirezarezvani/claude-skills

154

Quality system accountability, management review leadership, and regulatory compliance oversight per ISO 13485 Clause 5.5.2 requirements.

Research and AuditsFirst seen Jan 19, 2026

transformer-lens-interpretability

by davila7/claude-code-templates

154

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.

Research and AuditsFirst seen Jan 20, 2026

botchan

by bankrbot/openclaw-skills

153

The onchain agent messaging layer on the Base blockchain.

Research and AuditsFirst seen Feb 1, 2026

qms-audit-expert

by alirezarezvani/claude-skills

153

ISO 13485 internal audit methodology for medical device quality management systems.

Research and AuditsFirst seen Jan 19, 2026

opc-architecture

by parcadei/continuous-claude-v3

152

OPC (Orchestrated Parallel Claude) extends Claude Code - it does NOT replace it.

Research and AuditsFirst seen Jan 21, 2026

startup-business-analyst-business-case

by sickn33/antigravity-awesome-skills

152

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.

Research and AuditsFirst seen Jan 27, 2026

seo-content-optimizer

by onewave-ai/claude-skills

151

Comprehensive SEO analysis and optimization for content creators and marketers.

Research and AuditsFirst seen Jan 23, 2026

expo

by pproenca/dot-skills

150

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.

Research and AuditsFirst seen Jan 19, 2026

kotlin-concurrency-expert

by new-silvermoon/awesome-android-agent-skills

150

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.

Research and AuditsFirst seen Jan 26, 2026

mcp-management

by mrgoonie/claudekit-skills

150

Skill for managing and interacting with Model Context Protocol (MCP) servers.

Research and AuditsFirst seen Jan 21, 2026

migrate

by parcadei/continuous-claude-v3

150

Safe migrations for frameworks, languages, and infrastructure.

Research and AuditsFirst seen Jan 21, 2026

tldr-deep

by parcadei/continuous-claude-v3

150

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Research and AuditsFirst seen Jan 23, 2026

tldr-router

by parcadei/continuous-claude-v3

150

Maps questions to the optimal tldr command. Use this to pick the right layer.

Research and AuditsFirst seen Jan 23, 2026

validate-agent

by parcadei/continuous-claude-v3

149

Note: The current year is 2025. When validating tech choices, check against 2024-2025 best practices.

Research and AuditsFirst seen Jan 21, 2026

agentica-server

by parcadei/continuous-claude-v3

148

Complete reference for running Agentica SDK with a local Claude proxy. This enables Python agents to use Claude CLI as their inference backend.

Research and AuditsFirst seen Jan 21, 2026

clip

by davila7/claude-code-templates

148

OpenAI's model that understands images from natural language.

Research and AuditsFirst seen Jan 20, 2026

codable-patterns

by dpearson2699/swift-ios-skills

148

Encode and decode Swift types using Codable ( Encodable & Decodable ) with JSONEncoder , JSONDecoder , and related APIs. Targets Swift 6.2 / iOS 26+.

Research and Audits

sparse-autoencoder-training

by davila7/claude-code-templates

148

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.

Research and AuditsFirst seen Jan 20, 2026

tdd-migrate

by parcadei/continuous-claude-v3

148

Orchestrate TDD migrations with agents doing all work. Main context stays clean.

Research and AuditsFirst seen Jan 21, 2026

typescript-review

by metabase/metabase

148

Source details, install context, and public review data are available on the full page.

Research and AuditsFirst seen Jan 19, 2026
Page 23 of 36