By kustomzone
Freenet development skills - dApp builder, PR creation guidelines, and systematic debugging
Reviews PRs for alignment with stated goals, detects "CI chasing" anti-patterns, and ensures AI agent/skill instructions stay up to date with code changes. Critical for catching removed tests/fixes and stale automation rules.
Reviews PR code changes independently before reading the description to catch discrepancies between implementation and stated intent. Use as part of parallel review process.
Simplifies code, cleans up changes, and ensures documentation is accurate before review. Use after completing a PR but before running review agents to ensure reviewers see the cleanest version of the code with up-to-date docs.
Performs parallel readonly investigation of a codebase to gather evidence for debugging. Searches for patterns, checks git history, reads related files. Use when debugging to parallelize evidence gathering.
Performs adversarial review of PR changes, actively looking for bugs, edge cases, race conditions, and failure modes. Assumes bugs exist until proven otherwise.
Executes a risk-tiered, multi-perspective PR review — triages the change, runs specialist subagents in parallel (code-first, testing, skeptical, big-picture) plus an external model pass scaled to risk, then posts a consolidated review to the PR.
Build decentralized applications on Freenet using river as a template. Guides through designing contracts (shared state), delegates (private state), and UI. Use when user wants to create a new Freenet dApp, design contract state, implement delegates, or build a Freenet-connected UI.
Run integration tests that require Linux (full loopback range 127.x.x.x) via Docker. Use when a test fails on macOS with "Can't assign requested address" or when the user says "/linux-test".
Set up and manage local Freenet development environments and interact with a running node. Use when the user wants to test contract changes locally, debug UI issues, run a local node, query connections/diagnostics, inspect the dashboard, use the WebSocket API, or iterate on a Freenet application without deploying to the live network.
Guidelines for creating high-quality Freenet pull requests. This skill should be used when creating PRs for freenet-core, freenet-stdlib, or related repositories. Emphasizes quality over speed, thorough testing, and proper review process.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI coding agent skills for building applications on Freenet. Compatible with Claude Code and OpenCode.
Build decentralized applications on Freenet. Guides through:
Based on River, a decentralized chat application.
Guidelines for creating high-quality Freenet pull requests. Includes:
Methodology for debugging non-trivial problems:
The hooks/ directory contains two types of hooks for Freenet development:
File: hooks/hooks.json
Automatically runs cargo fmt and cargo clippy before Claude runs git commits. Included with the plugin - no setup required.
File: hooks/pre-commit
Runs cargo fmt and cargo clippy before git commits. Must be installed manually:
# From freenet-core repository
curl -fsSL https://raw.githubusercontent.com/freenet/freenet-agent-skills/main/hooks/pre-commit > .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit
See hooks/README.md for full details and comparison.
Add the marketplace:
/plugin marketplace add freenet/freenet-agent-skills
Then install the plugin:
/plugin install freenet@freenet-agent-skills
This installs all bundled skills (dapp-builder, pr-creation, pr-review, release, systematic-debugging, linux-test, local-dev). Browse via /plugin → Discover tab to confirm.
Option 1: Copy individual skills
git clone https://github.com/freenet/freenet-agent-skills.git
cp -r freenet-agent-skills/skills/dapp-builder ~/.claude/skills/
Option 2: Symlink (easier to update)
git clone https://github.com/freenet/freenet-agent-skills.git ~/freenet-agent-skills
ln -s ~/freenet-agent-skills/skills/dapp-builder ~/.claude/skills/
OpenCode automatically discovers skills from Claude-compatible paths:
git clone https://github.com/freenet/freenet-agent-skills.git ~/freenet-agent-skills
ln -s ~/freenet-agent-skills/skills/dapp-builder ~/.claude/skills/
ln -s ~/freenet-agent-skills/skills/pr-creation ~/.claude/skills/
ln -s ~/freenet-agent-skills/skills/systematic-debugging ~/.claude/skills/
To include a skill in a specific project (shared with team):
mkdir -p .claude/skills
cp -r freenet-agent-skills/skills/dapp-builder .claude/skills/
git add .claude/skills
Verify installation: Ask your AI agent: "What skills are available?" - it should list the installed skills.
freenet-agent-skills/
├── .claude-plugin/
│ └── marketplace.json # Claude Code marketplace manifest
├── skills/
│ ├── dapp-builder/
│ │ ├── SKILL.md # Main skill definition
│ │ ├── README.md # Skill documentation
│ │ └── references/ # Detailed documentation
│ ├── pr-creation/
│ │ └── SKILL.md
│ └── systematic-debugging/
│ └── SKILL.md
├── hooks/
│ ├── hooks.json # Claude Code hooks (run before git commit)
│ ├── pre-commit # Git pre-commit hook for cargo fmt/clippy
│ └── README.md
├── agents/ # Subagent definitions (reviewers, etc.)
├── README.md
└── LICENSE
See CLAUDE.md for the current version and version history. When making changes:
.claude-plugin/marketplace.json → metadata.versionCLAUDE.md with version number and changelog entrySkills follow the structure:
skill-name/
├── SKILL.md # Main instructions (required, with YAML frontmatter)
└── references/ # Detailed documentation loaded on-demand (optional)
SKILL.md files require YAML frontmatter:
---
name: skill-name # Must match directory name
description: Brief description of what the skill does
license: LGPL-3.0 # Optional
---
LGPL-3.0
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
Build reusable scripts for Hugging Face Hub and API workflows. Useful for chaining API calls, enriching Hub metadata, or automating repeated tasks.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Explore, query, and extract data from any Hugging Face dataset using the Dataset Viewer REST API and npx tooling. Zero Python dependencies — covers split/config discovery, row pagination, text search, filtering, SQL via parquetlens, and dataset upload via CLI.
Scrape, search, crawl, and map the web with a single command.
npx claudepluginhub kustomzone/freenet-agent-skillsConsult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.