Open, inspect or configure an Arch Studio workspace and register projects.
$ npx skills add AlpacaLabsLLC/skills-for-architects --skill studio -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects studio --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/studio .claude/skills/studio && 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 "studio" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio into .claude/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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/studioType 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 studio -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects studio --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/studio .agents/skills/studio && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "studio" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio into .agents/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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 studio -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects studio --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/studio .cursor/skills/studio && 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 "studio" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio into .cursor/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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/studio--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 studio -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AlpacaLabsLLC/skills-for-architects studio --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/studio .gemini/skills/studio && 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 "studio" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio into .gemini/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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 studioInstalls 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 studio -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/studio .github/skills/studio && 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 "studio" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio into .github/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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 studio -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 studio --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/studio .opencode/skills/studio && 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 "studio" agent skill from https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/studio into .opencode/skills/studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "studio", 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.
studioOpen, inspect or configure an Arch Studio workspace and register projects.
Studio is an agent skill from AlpacaLabsLLC/skills-for-architects. Open, inspect or configure an Arch Studio workspace and register projects. Use for studio administration; direct domain skills and tools-only use remain available.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `README.md`, `host-contract.json` and `scripts/update_preference.py`).
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:
ReadWriteEditGlobGrepBashAskUserQuestionFrom allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (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.
Studio loads about 2.2k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 1,064 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, Bash, AskUserQuestionAutomated 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). 1,064 words, ~2,219 tokens.
.claude/skills/studio/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Before acting, read the host contract, this component's declaration (skill:studio), and applicable workspace semantics. Load only the required modes from the shared catalog.
<!-- architecture-studio:harness-compatibility -->Use the host adapter for native invocation. Apply the native workspace operations with the host’s own tools and ordinary task-specific code. Operation names identify semantic scope, not function calls or a dispatcher. No Arch Studio runner, executable download or reconstructed helper is required. Resolve canonical context before existing-workspace edits; fresh setup validates its explicit target and ancestor boundary instead. Existing exact authorization persists; ask only for material missing information or missing permission.
Own STUDIO.md, project registration, synchronized registered Status and the studio-only connector boundary. Read moments for state-aware welcome and no-folder behavior. Do not repeat a declined setup nudge. A supplied task proceeds directly; no welcome/menu replay. Tools-only and valid standalone project use require no studio scaffolding.
Before persistent changes, follow the native mutation sequence: Inspect → Prepare → Verify preparation → Apply → Verify result → Complete. Inspect pending work first. Finish and verify preparation before the first canonical write: separately reread every saved original and prepared file, check its complete actual bytes, establish durable saving, and inspect actual permissions, ownership and ACLs. Merely writing recovery files does not finish verification. Apply only that verified set. Mark complete only after fresh readback validates the entire affected result and its relationships. Read-only requests and inline drafts need no publication sequence.
Fresh setup prepares the whole declared studio tree and identities. Project-mode registration changes STUDIO.md while guarding the existing project's identity; portfolio registration also includes any permitted removal of a header-only local TASKS.csv and the project task-pointer update in the same prepared set. Status/archive changes prepare both STUDIO.md and PROJECT.md before either publisher runs. Task-mode changes include every affected register and ownership reference. Single-setting edits remain bounded to their declared file/field; optional preference/connector edits retain their separate exact authorization.
Read the studio policy contract for fresh setup or an explicitly requested policy configuration. Ask once whether the user has an AI-use policy or wants the offered default, show the default before adoption, and allow decline. Existing references stay in place; a default is created only at the resolved Standards root's governance/ai-policy.md. Record the reference and adoption choice in STUDIO.md's Data governance section. Include that exact file set in the existing setup preview and readback. Preserve already-configured choices on unrelated edits; Skill Maker only consumes them. No policy is silently adopted or migrated.
Use studio.init for a confirmed exact fresh target. Gather only missing studio name, working units, jurisdiction (No default is valid), naming policy (as, firm, none), folder taxonomy/managed roots, document path template and firm stage vocabulary keyed by project Kind. Naming and taxonomy are separate advisory choices. Preserve confirmed human names/casing. The shipped building/software/initiative stages are Arch Studio-owned defaults, not an asserted external standard.
Show the exact target, files, managed roots and data boundary: records stay in the user workspace; content supplied to a configured model follows that provider's terms; setup creates no ALPA account/cloud storage/Git repository. One concrete setup gate covers those choices. Format version stays 3; Document model 1 identifies the fresh record shape. No existing workspace conversion or backward-compatibility setup is provided.
Finish setup preferences with: “Would you like this assistant to use Arch Studio by default for architecture and project work?” Follow the preference protocol. When the exact scoped preference edit has been previewed, the same setup approval can cover it; a general yes never approves an unseen file edit. Otherwise retain session guidance and obtain only missing concrete authorization. Do not persist a global preference implicitly.
MCP instruction delivery does not install lifecycle hooks. Background update preference is an installed-package feature outside this MCP workflow; report it unavailable here without inspecting or creating package state. Do not infer enablement from connection or general setup approval.
Apply the reviewed studio.init preparation with native tools. Reopen STUDIO.md, identity, connector manifest (mcpServers empty), managed roots and host skill roots. Installation/connection checks do not prove workspace creation.
studio.status lists valid and invalid registrations, identity drift and task mode read-only. Unknown or archived status does not hide a project. No authentication/network checks are implied.project.init then studio.register; each uses the same already-approved identity/target. A partially completed project is reported and registration resumed without recreating it.studio.register requires an existing new-model descendant with immutable unique Project ID and Folder ID. Paths are relative cached locations; do not infer identity from a human folder name.studio.set-status and studio.archive change only the selected registry Status cell and the matching PROJECT.md Status Value cell. Preserve its existing Source and Date cells exactly unless the user separately authorized those specific provenance changes; do not replace Source with the operation name. Before publication and on actual readback, compare the field-level diff across both files and reject any other changed cell. Activity never establishes completion or acceptance.studio.set-naming changes the advisory policy/convention without renaming existing IDs or folders.studio.task-mode switches only empty current-model task registers between project and studio portfolio ownership, preserving the one-writer topology. Populated registers require a separately specified current-data operation, not an automatic merge/split or historical converter.Only studio owns .mcp.json, at studio root. Setup leaves it empty; connector configuration/authentication requires separately available capabilities and scope. Projects never receive this manifest. Firm extensions stay in the relevant host's studio skill root.
General domain work may hand off once to Norma with scope, completed outputs and existing authorization; an explicit studio administration task stays here. Main-harness agent creation follows approved roles/assignments and real capabilities. Do not claim that instructions or a welcome executed a workflow.
Use studio.preference only for the optional default-assistant choice, applying the preference protocol with the verified native instruction mechanism and concrete authorized diff. No persistence claim follows from connection or a saved file alone. MCP background lifecycle update checks remain unavailable; do not invoke installed-package update operations through this workflow.
studio.connectors owns the studio .mcp.json boundary. Fresh setup creates exactly an empty mcpServers object. A later explicitly requested configuration must use verified connector/host documentation and a reviewed exact change, preserving other entries. Configure only the known authorized server; authentication, external messages and account provisioning require their actual separate capabilities and authorization. No arbitrary connector endpoint or secret is inferred from workspace setup.
After administration, use the shared completion reporting contract. Report actual changes and readbacks; a connection or welcome is not workspace creation.
© 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 3 other files (scripts) in skills/studio of AlpacaLabsLLC/skills-for-architects.
Open the folder on GitHubat commit 657bfd5
Studio 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 |
|---|---|---|---|---|---|---|
| Studio this skillAlpacaLabsLLC/skills-for-architects | 373 | — | ~2.2k | Automated safety check: Notes | MIT | |
| Performing Ssl Tls Inspection Configurationmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.9k | Automated safety check: Notes | Apache-2.0 | |
| Studioremotion-dev/remotion | 62k | — | ~376 | Automated safety check: Pass | Custom licence | |
| Configure Channelopenclaw/openclaw | 392k | — | ~946 | Automated safety check: Pass | MIT | |
| Node Inspect Debuggeropenclaw/openclaw | 392k | 1 repos | ~894 | Automated safety check: Pass | MIT | |
| Studio Queriessupabase/supabase | 111k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 |
mukul975/Anthropic-Cybersecurity-Skills
Configure SSL/TLS break-and-inspect on next-generation firewalls and forward proxies to decrypt, inspect, and re-encrypt HTTPS traffic for malware and exfiltration detection, including deploying…
remotion-dev/remotion
Start Remotion Studio from packages/example and open it in the Codex browser.
openclaw/openclaw
Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.
openclaw/openclaw
Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.
supabase/supabase
React Query conventions for data fetching in Supabase Studio.
supabase/supabase
Testing strategy for Supabase Studio. An agent skill from supabase/supabase.
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.
Open, inspect or configure an Arch Studio workspace and register projects. Studio is an agent skill from AlpacaLabsLLC/skills-for-architects. Open, inspect or configure an Arch Studio workspace and register projects.
Studio fits situations like: studio administration; direct domain skills and tools-only use remain available.
Run `npx skills add AlpacaLabsLLC/skills-for-architects --skill studio -a claude-code`. Or copy the skill folder (skills/studio in AlpacaLabsLLC/skills-for-architects) into .claude/skills/studio in your project. Claude Code loads it when a task matches its description.
Run `npx skills add AlpacaLabsLLC/skills-for-architects --skill studio -a codex`. Or copy the skill folder (skills/studio in AlpacaLabsLLC/skills-for-architects) into .agents/skills/studio 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 studio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/studio, .gemini/skills/studio, .github/skills/studio and .opencode/skills/studio in your project.
Going by SKILL.md and its folder, Studio needs Python for the scripts in its folder. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Bash, AskUserQuestion.
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.
Studio is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k 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 Studio: Performing Ssl Tls Inspection Configuration (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Studio (remotion-dev/remotion, 62k stars), Configure Channel (openclaw/openclaw, 392k stars) and Node Inspect Debugger (openclaw/openclaw, 392k 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.
