blender-kiln
Claude Code plugin that turns a text brief or a photo into a production-ready 3D asset through Blender: rebuilt by script, textured from CC0 scans, graded against the real object, optimized to GLB/FBX
A collection of agent skills for Claude Code and other coding agents.
SkillsPython · ShellGitHub @shaokeyibbSelf-installOwner unconfirmed
Paste into Claude or ChatGPT for installation instructions suited to your environment.
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Installable projects can be verified without a deployment domain. Use GitHub sign-in for a personal repository, or the repository verification file above for an organization repository.
Ask about other verification options
The maker's introduction consists of the line above. Read the repository README for more details. Repository README ↗
Loading the full README.
Read the full README ↗English | 简体中文
A collection of agent skills for Claude Code and other coding agents that read the Agent Skills format. Each skill stands on its own, so install only the ones you need.
npx skills add shaokeyibb/hikarilan-skills
This lists every skill in the repository and lets you choose which ones to install. To install a single skill:
npx skills add shaokeyibb/hikarilan-skills --skill structural-fix
Add -g to install for your user rather than for the current project.
| Skill | What it does |
|---|---|
afk | Keeps an agent working while you are away. It decides small things itself, does reversible work first and parks the rest for your ruling, checks in on a schedule, and hands you one summary with every open decision when you return. |
capability-pruning | Slims a project one capability at a time. It builds a full inventory, writes an evidence card for each capability, and has the owner decide every removal. |
concurrent-worktrees | Runs several lines of work in parallel with git worktrees, then merges them back without losing anyone's changes. |
e2e-first-testing | Decides which tests to write, keep or delete. Its default is an end-to-end scenario through the production entry point, with test doubles only at external boundaries. Includes a coverage script for pruning legacy suites. |
llm-agent-surface | Sets out what an LLM sees inside an agent framework (tool schemas, prompts, rejection messages) and where the framework stops and the model decides. |
matt-skills-on-openspec | Wires Matt Pocock's engineering skills onto a repository whose work items are OpenSpec changes. |
minimal-design-gate | Checks for over-design twice: on the proposal before building, and on the delivery after. |
progress | One command makes the agent report where the work stands, as the same table every time: doing now, next, not done, done, time left and progress. Extra arguments are extra questions. |
repo-audit-loop | Audits a whole repository, or a batch of finished work, in rounds until one finds nothing. It keeps a coverage ledger and a defect ledger throughout. |
site-annotated-gates | Enforces architectural rules with static checks. Each exception is annotated at its code site, and the check fails on stale annotations too. Includes a standard-library implementation. |
structural-fix | Fixes a defect so that its whole class goes away, not just the instance that was reported. |