Recently added

ODIN workflows for practical interface and visual design.

Advanced ODIN workflows for polished interfaces and design systems.

ODIN workflows for turning ideas into working artifacts.

Advanced ODIN workflows for ambitious, multi-part creative work.

Core ODIN workflows for planning, executing, and checking changes.

ODIN workflows for writing, reviewing, and maintaining code.

Advanced ODIN workflows for complex code changes and technical audits.

ODIN workflows for BigQuery data work and cost-aware queries.

ODIN workflows for software on Apple platforms.

ODIN workflows for designing and improving AI agents.

Opinionated Unity 6 + VContainer + UniTask Claude Code configuration. Hook-enforced architecture, 65 skills, 36 agents, 57 slash commands, Unity Knowledge Graph.

Spec/design-driven engineering workflow: spec -> plan -> implement -> review -> finish, with supporting standards, architecture, and debugging disciplines

Requirements tracking for Claude Code. One living spec per product: every intent is classified against everything already agreed, a contradiction stops the work instead of merging, and each release regenerates its own guide and announcement.

Replace with a short description of the skill.

Safety rules for git worktrees: verified removal, explicit handovers, one branch per worktree, shared-config hazards, and per-file ownership for parallel actors.

Background CI watcher after every push or merge, reporting pass/fail with failing-job logs.

Controls before a zero or absent reading, an alarming finding, a success claim, or stillness becomes a conclusion: evidence-bearing probes, positive and negative controls, second derivations, postconditions over logs, and a re-measure at the moment of sending.

Cross-model code review using a second agent, tool, or read-only CLI fallback.

PR bodies and issues that show the change instead of describing it, shaped to the change, with the human part short and anything written for a tool collapsed at the bottom; plain-first replies to issue reporters.

Run a session as an orchestrator: parallel worktree subagents, gated landings (direct or PR-based), fleet monitoring.

Refactor invariants out of runtime checks and into the type system: parse at boundaries, then make invalid internal states impossible to construct.

Never fix the same failure class twice. Climb every correction to the most durable response reachable: architecture and data structures first, then CI checks, then rules.

Write and edit prose that avoids the documented signs of AI writing from Wikipedia's field guide.

Create skills and memories to a quality bar, and repair them at their source when they fail.

House standards for maintainable code, applied while writing and folded into reviews.

Installable, plugin-ready skills that give coding agents disciplined workflows, from code standards and review gates to multi-agent orchestration

A local Codex plugin exposing the shared agent-skills inventory.

Synthesis engineering workflows for durable human-agent work across ChatGPT, Codex, Claude Code, and other Agent Skills runtimes.

Development handbooks for the SimpliX stack — Spring Boot backend conventions with YAML-driven code generation, simplix-react frontend conventions with OpenAPI-driven scaffolding, and a browser-driven end-to-end usability audit

SimpleCORE's curated skill set — Korean output standards with glossary tooling, SVG and ASCII diagrams, low-fidelity wireframe boards, the scenario-driven build that grows an app from one in dependency order, one chapter per agent, the parity walk that reconciles a board with a running app, and the proposal set: the content standard for a bid and the typesetting standard for the decks it is submitted as

An evidence-driven multi-agent engineering harness for Claude Code. Every conclusion carries an evidence grade; every resident rule must show a failure it prevents, or it gets deleted.

playpark LLC personal skills: blog / sns / seo / media / ops utilities (requires playpark-core)

Shared base for playpark plugins: _lib/common.sh, skill-retrospective journal telemetry, bin/journal

dev-flow: issue-to-LGTM dynamic workflows (dev-flow-run / pr-iterate / dev-improve / canary), 7 skills and 11 dev-flow agents, by playpark LLC

Use sxq to sync, preview, migrate, and release Superun projects safely

Design and review interaction behavior, state feedback, high-stakes actions, and agent-initiated UI with evidence-based checks.

Security-hardened Agent2Agent (A2A) client as an MCP server — discover cards, send and stream messages, and use confirmation-gated task control

Generate blog cover images, architecture diagrams, and process infographics as PNG files using HTML+CSS rendered via Chrome headless.

TypeScript backend development skills: database performance optimization, code review, and Prisma schema design.

Sui blockchain development skills — Move smart contracts, TypeScript SDK, frontend dApp Kit, Seal secrets, and Walrus storage.

Interact with the Solana blockchain through Claude Code. Query accounts, analyze transactions, and execute operations with built-in safety safeguards.

Write technical documentation, articles, reviews, and postmortems in a storytelling style that's direct, humble, and problem-first.

Generate humorous, absurd, and flirty Indonesian proverb (peribahasa) remixes with precise rhyme and cadence.

PreToolUse/Bash hook that blocks IaC write/destructive commands (ansible-playbook/ansible-pull without --check, ad-hoc ansible write modules, terragrunt/tofu/terraform apply-family including mise-wrapped forms), so agents never apply changes to real infrastructure.

Validate and configure token decimals for EVM-compatible blockchain deployments to prevent amount calculation errors.

Design Thinking · Design Graph · Graph Protocol — draw the call graph before writing code. Turns plans, reviews, and refactors into an annotated, stack-agnostic call graph.

Build tailored cover letters and ATS-friendly CVs by scanning a repo for background info and matching to job postings.

Autonomous sprint orchestration for BMad-driven development pipelines. Drives Claude Code through all stories without human intervention until completion or blocking condition.

Denies git commands that stage protected paths, whole-tree adds, or rewrite history.

Observability-Driven Development for CLI coding agents