Agent skills
Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
visual-novel
9,705Game Development
Builds visual novels and choice-driven stories in Ren'Py or any engine: routes, endings, saves, backlog and skip, with reachability checks.
Code Improver
8,320Code Review And Quality
Runs an autonomous review-and-fix loop over any code target with a reviewer you name, a findings ledger, escalation and a scope guard.
Differential Security Review
8,320Code Review And Quality · Security Auditing
Reviews PRs, commits and diffs for security risk using git history, blast radius by caller count and test coverage checks, and writes a markdown report.
goal-prompt
8,320Agent Workflows
Drafts one-line /goal commands for Claude Code and Codex that have a checkable end state, a stated check, invariants and a stop bound.
implement-patch
8,320Code Review And Quality
The patcher stage of patching-bugs: find the broken invariant, write a regression test that fails first, fix it, and leave one local commit.
mutation-testing
8,320Code Review And Quality
Configures mewt and muton mutation testing campaigns, analyzes surviving mutants and uses them to find bugs in weakly tested code.
patching-bugs
8,320Code Review And Quality
The orchestrator for fixing one known bug: reproduce it, validate it, patch it, prove the patch, hunt regressions, and render reports for review.
PR Improver
8,320Code Review And Quality
Runs a review-and-fix loop over the current branch's changes until a PR review reports no critical or major findings, scoped to the touched directories.
property-based-testing
8,320Code Review And Quality
Write, review and debug property-based tests across Hypothesis, fast-check, proptest and Echidna, with a catalog of properties and failure triage.
prove-patch
8,320Code Review And Quality
The prover stage of patching-bugs: run scoped cases on baseline and patched trees, then confirm the bug returns when the patch is reverted.
reproduce-bug
8,320Code Review And Quality
The reproduction stage of patching-bugs: build the baseline, exercise the named bug with a PoC or compiler run, and save the raw receipts.
review-walkthrough
8,320Code Review And Quality
Turns the current branch into a self-contained HTML walkthrough: the diff split into ordered steps, each with an explanation and review findings anchored to lines.
second-opinion
8,320Code Review And Quality
Runs an external CLI review (Codex, Antigravity or Gemini) on your uncommitted changes, a branch diff or a commit, and reports the findings with severity and file lines.
Skill Improver
8,320Agent Workflows
Loops the plugin-dev skill-reviewer agent and a fixer over a Claude Code skill until its review comes back clean, with a ledger and scope guard.
validate-bug
8,320Code Review And Quality
The validation stage of patching-bugs: a fresh agent reruns the unchanged PoC and decides whether the claim and its invariant hold.
Dual Axis Skill Reviewer
7,471Agent Workflows
Scores agent skills on two axes, deterministic code checks and an LLM review, then merges them into a weighted score with improvement items.
skill-designer
7,471Agent Workflows
Builds a prompt from a JSON skill idea that tells Claude CLI to create a full skill folder with SKILL.md, references, scripts and tests.
Asset Gen
7,374Game Development
Generate images, sprites, textured 3D models, rigged characters, sound effects and voice lines for games and videos, free on a local GPU or through paid APIs.
Engine Guide
7,374Game Development
Choose and use Godot, Bevy, Babylon.js, three.js or HTML for games, videos and interactive 3D, with install steps, build commands and headless capture.
n8n Agents
6,689Developer Tools
A guide for designing n8n AI agents: which AI node to use, how to name tools, wire memory, force structured output and gate risky actions behind human review.
n8n Binary and Data
6,689Developer Tools
A guide to files in n8n: where bytes live, how to read and write them, how to stop transforms from dropping them, and how to pass files to agent tools and chat apps.
n8n Code JavaScript
6,689Developer Tools
A guide to writing JavaScript in n8n Code nodes: a gate that checks native nodes first, data access, return format, webhook body, sandbox limits and loop pitfalls.
n8n Code Python
6,689Developer Tools
A guide to native Python in n8n 2.x Code nodes: the two input variables, blocked imports, denied builtins, accepted return shapes and how errors interact with onError.
n8n Code Tool
6,689Developer Tools
A guide to the n8n Custom Code Tool that AI agents call: string in and string out, the query variable, input schemas, sandbox limits and the three signature errors.