analyst
claudeResearch and business intelligence agents — web research with source attribution, and company/market analysis from public sources
15 skills · 3 agents
Shared coding conventions for TypeScript, .NET, Python, PHP, plus git workflow, testing, architecture, and AI steering rules
Plugin coding-standards from marketplace turtlestack in hpsgd/turtlestack. Commands read from the repo's manifest — 1 month ago.
bootstrapBootstrap the coding standards documentation for a project. Creates docs/tooling-register.md and appends coding conventions to root CLAUDE.md. Idempotent — merges missing sections into existing files without overwriting. Rule installation is handled separately by the thinking plugin's SessionStart h
review-dotnetReview .NET / C# code against team conventions — messaging architecture, API design, testing, dependency management, and analyser compliance. Auto-invoked when reviewing .cs files.
review-gitReview git conventions — commit messages, PR titles, branch model, and content date integrity. Auto-invoked during PR and commit workflows.
review-goReview Go code against team conventions — error handling patterns, interface design, goroutine safety, and table-driven tests. Auto-invoked when reviewing .go files.
review-phpReview PHP code against team conventions — type safety, immutability, testing, linting, error handling, and code structure. Auto-invoked when reviewing .php files.
review-pythonReview Python code against team conventions — type safety, data modelling, testing, linting, configuration, and code structure. Auto-invoked when reviewing .py files.
review-standardsReview code changes against general quality and writing style standards — cross-cutting concerns that apply to every language and file type. Auto-invoked during code review.
review-typescriptReview TypeScript and Next.js code against team conventions — type safety, component patterns, API routes, testing, and bundle hygiene. Auto-invoked when reviewing .ts/.tsx files.
Research and business intelligence agents — web research with source attribution, and company/market analysis from public sources
15 skills · 3 agents
Structured thinking and reasoning skills — first principles, ISC, algorithm, council, red team, and more
16 skills · hooks
Agile coach — Scrum and Kanban coaching, ceremony facilitation, retrospective design, team health, flow management, and working agreements. Ongoing per-team presence for engineering, product, discovery, and design teams
13 skills · 1 agent
Product manager — owns the why and the what for a product slice: problem validation, continuous discovery, JTBD, roadmap, PRDs, RICE prioritisation, and strategy input to the CPO
13 skills · 1 agent
Delivery manager — RAID logs, dependency tracking, weekly status reporting, release-readiness coordination, organisational impediment removal, multi-team coordination, and GDS service-assessment readiness
11 skills · 1 agent
Go-to-market specialist — positioning, launch strategy, content marketing, competitive analysis
11 skills · 1 agent
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
7 skills · 1 command · 3 agents
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Statically analyze a local JS/Electron app you're authorized to study, with file+line evidence, and build an original reimplementation of what you find. Experimental. Phase 1: JS/Electron static analysis. Phase 2: native ELF/PE/Mach-O container inspection. Phase 3: .NET assembly metadata. Phase 4: EVM bytecode inventory. Phase 5: CUDA fatbin, cubin and PTX inventory. Parses, never executes. Dynamic analysis is a future phase, not yet implemented.
1 skill · 1 command · 1 agent
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.