Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
Create or update an Arch Studio skill for Codex or Claude Code using the host's native skill maker when available, with Arch Studio governance and validation.
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects skill-maker --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architects.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-maker .claude/skills/skill-maker && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-maker" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-maker into .claude/skills/skill-maker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-maker", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-makerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects skill-maker --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architects.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-maker .agents/skills/skill-maker && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-maker" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-maker into .agents/skills/skill-maker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-maker", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects skill-maker --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architects.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-maker .cursor/skills/skill-maker && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-maker" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-maker into .cursor/skills/skill-maker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-maker", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AlpacaLabsLLC/skills-for-architects.git --path skills/skill-maker--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects skill-maker --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architects.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-maker .gemini/skills/skill-maker && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-maker" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-maker into .gemini/skills/skill-maker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-maker", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AlpacaLabsLLC/skills-for-architects skill-makerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architects.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-maker .github/skills/skill-maker && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-maker" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-maker into .github/skills/skill-maker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-maker", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects skill-maker --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlpacaLabsLLC/skills-for-architects.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-maker .opencode/skills/skill-maker && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-maker" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/skill-maker into .opencode/skills/skill-maker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-maker", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skill-makerCreate or update an Arch Studio skill for Codex or Claude Code using the host's native skill maker when available, with Arch Studio governance and validation.
Skill Maker is an agent skill from AlpacaLabsLLC/skills-for-architects. Create or update an Arch Studio skill for Codex or Claude Code using the host's native skill maker when available, with Arch Studio governance and validation. Use when asked to create, package, adapt or revise a reusable skill.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `README.md`, `host-contract.json` and `scripts/validate-skill.sh`).
It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: Claude Code skills for architecture, real estate, and workplace strategy. Type /skill-name and go. The licence is MIT.
Read from SKILL.md and the folder at commit 657bfd5. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrepBashFrom allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Shell and Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Skill Maker loads about 2k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 952 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, Glob, Grep, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from AlpacaLabsLLC/skills-for-architects at commit 657bfd5, republished under its MIT licence (© AlpacaLabsLLC). 952 words, ~1,958 tokens.
.claude/skills/skill-maker/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Use the active host's native skill maker when available. If none exists, write the minimum skill in that host's supported format. The host owns generic authoring technique; this skill supplies Arch Studio's target, governance and acceptance requirements. Do not require a particular host maker or install an Arch Studio runtime.
Read PATTERNS.md and follow its owning links as relevant: architecture, host contract, host adapters, workspace model, terminology, and contribution rules. Read this component's declaration (skill:skill-maker) and only its applicable modes from the shared catalog. For MCP delivery, retrieve all required resources at the advertised release digest; resource references are not assumed local paths.
Derive ordinary authoring choices from the request; do not run a routine setup interview. Ask only for missing scope, target authorization or a concrete governance conflict.
Resolve the exact target before writing. Catalog detection has highest priority: find the Git root and check whether .codex-plugin/plugin.json or .claude-plugin/plugin.json names as. A plugin cache or MCP resource is not a writable source checkout. Otherwise find the nearest STUDIO.md for a normal firm skill; do not let a nearer project silently override a resolved studio. Use the nearest project root only when the user explicitly requests a project-only skill. If no root is established, ask one target question rather than treating the current directory as a studio. A global target requires an explicit request.
| Scope | Destination |
|---|---|
| Verified catalog checkout | {project-root}/skills/{name}/ |
| Studio | {studio-root}/{host-skill-root}/{name}/ |
| Explicitly project-only | {project-root}/{host-skill-root}/{name}/ |
| Explicitly global | {host-global-skill-root}/{name}/ |
Use .agents/skills for Codex or .claude/skills for Claude Code; global roots are $HOME/.agents/skills and $HOME/.claude/skills respectively. If the host is ambiguous, ask which target host. State the selected absolute path. The installed plugin cache is never a private-skill target. Check existing contents; update a named existing skill only when the request authorizes it. Otherwise choose a distinct name or ask. Project-only discovery may be narrower when launched from a nested repository; explain that limitation without duplicating the skill.
Read the complete studio policy contract. For a relevant studio/project procedure, resolve the owning studio using the context contract, read its recorded current policy when needed to establish the procedure, and add the contract's live-reference step to the generated SKILL.md with a dependency explanation in README.md. The generated step resolves the current studio and rereads its central policy on each invocation and before resumed policy-dependent actions, handles unreadable references and conflicts explicitly, and preserves existing authorization. Embed portable instructions, not policy text or a dependency on this plugin's installed path.
Skill Maker never writes STUDIO.md or adopts a policy. No policy/decline leaves existing governance in force. Standalone/global skills do not require a studio. Public-catalog outputs use generic lookup where relevant and contain no originating policy text, private locator or studio identity in any bundle file. Existing generated skills are changed only by an explicit update request; no automatic adoption or organization-wide installation is implied.
Check existing owners before adding a capability. Give the skill one coherent outcome, a trigger description, necessary domain facts, interfaces, invariants, evidence and a done condition. Let the host choose valid methods. Include an ordered procedure only when its order is itself required and explain why. Keep firm and project facts in their owning workspace; link to governing sources rather than copying them.
Create SKILL.md and a short human-facing README.md. For a host without a native maker, adapt the bundled SKILL example and README example; use them as examples, not mandatory prose or sequence. Use a kebab-case name matching the directory. Describe both what the skill does and when to use it. Include allowed-tools only when supported and needed by the selected host. Do not embed ~/ paths. For code, zoning or life-safety analysis retain the canonical disclaimer and <!-- architecture-studio:requires-disclaimer --> marker as required by the rules.
For any files created or changed, follow the native mutation sequence for the complete affected set, including existing bytes, access, recovery, stale-write protection and fresh readback. Before any destination write, durably retain and separately reopen the complete original and prepared file/access set, including README and any requested validation report. Publish complete bytes with no-clobber or stale-write protection, then reopen and check the entire affected set. Inspect incomplete attempts before retries. Do not treat preparation as a new user approval gate. Stop before mutation when required access or recoverable publication is unavailable.
Run the host maker's checks when available. Independently apply skill_scaffold.validate semantics: the directory is kebab-case; readable README.md and UTF-8 SKILL.md exist; the latter starts with delimited YAML frontmatter whose safely parsed mapping has a matching name and nonblank description; no ~/ occurs anywhere. A missing YAML parser leaves that check unverified, never passed. Accept exactly {"directory": "<selected path>"} with a required string and no extra fields; require regular readable files and a directory matching [a-z0-9]+(?:-[a-z0-9]+)*. Frontmatter begins at the first byte with --- and LF or CRLF, closing on a separate --- line followed by newline or end of file. On success, report {"valid": true, "directory": "<actual input path>", "name": "<directory name>"} only after actual destination readback; on failure identify the failing check, fix only authorized files and rerun the complete check. The validator is read-only. This structural check does not prove discovery, policy access or usefulness. Review the whole bundle for the applicable live-reference step, README dependency, policy privacy and destination/publication constraints.
For a catalog contribution, run repository lint in the verified source checkout and relevant focused tests; check catalog membership and host contracts. A private skill need not run catalog lint. If behavior is uncertain, compare representative tasks with and without the skill; report observed value, not an assumed lift. Report the paths, invocation ($name on Codex, /{name} privately or /as:{name} in the Claude catalog), checks and any incomplete verification. Do not commit unless requested.
© AlpacaLabsLLC, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (scripts) in skills/skill-maker of AlpacaLabsLLC/skills-for-architects.
Open the folder on GitHubat commit 657bfd5
Skill Maker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Maker this skillAlpacaLabsLLC/skills-for-architects | 373 | — | ~2k | Automated safety check: Notes | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase | 10k | 11 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Claude Code Command Developmentanthropics/claude-plugins-official | 38k | 10 repos | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Plugin Structureanthropics/claude-plugins-official | 38k | 10 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 |
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
diet103/claude-code-infrastructure-showcase
A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
anthropics/claude-plugins-official
Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.
anthropics/claude-plugins-official
Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.
rohitg00/ai-engineering-from-scratch
Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.
AlpacaLabsLLC/skills-for-architects
Register received or authored project documents by confirmed coordinates, preserve their filenames and provenance, and find or verify registered documents.
AlpacaLabsLLC/skills-for-architects
Create an HTML color palette from a mood, description, or image, with swatches, color codes, pairings, and contrast checks.
AlpacaLabsLLC/skills-for-architects
Research population, income, age, housing, and employment around a site.
AlpacaLabsLLC/skills-for-architects
Research climate, sun, flood, seismic, soil, contamination, and topography for a site.
AlpacaLabsLLC/skills-for-architects
Research transit, walking, cycling, pedestrian infrastructure, and airport access for a site.
AlpacaLabsLLC/skills-for-architects
Clean a local FF&E CSV schedule by normalizing casing, dimensions, units, language, materials, and formatting.
Categories
Create or update an Arch Studio skill for Codex or Claude Code using the host's native skill maker when available, with Arch Studio governance and validation. Skill Maker is an agent skill from AlpacaLabsLLC/skills-for-architects. Create or update an Arch Studio skill for Codex or Claude Code using the host's native skill maker when available, with Arch Studio governance and validation.
Skill Maker fits situations like: asked to create; revise a reusable skill.
Run `npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a claude-code`. Or copy the skill folder (skills/skill-maker in AlpacaLabsLLC/skills-for-architects) into .claude/skills/skill-maker in your project. Claude Code loads it when a task matches its description.
Run `npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a codex`. Or copy the skill folder (skills/skill-maker in AlpacaLabsLLC/skills-for-architects) into .agents/skills/skill-maker in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlpacaLabsLLC/skills-for-architects --skill skill-maker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-maker, .gemini/skills/skill-maker, .github/skills/skill-maker and .opencode/skills/skill-maker in your project.
Going by SKILL.md and its folder, Skill Maker needs a shell and Python for the scripts in its folder. Our summary lists: Python 3; A Bash shell. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Bash.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Skill Maker is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Skill Maker: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
AlpacaLabsLLC (a GitHub organization) maintains it in AlpacaLabsLLC/skills-for-architects, which has 373 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on October 5, 2026.
Source: AlpacaLabsLLC/skills-for-architects on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.