New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Still2rig Psd

by shinshin86 in shinshin86/still2rig-psd

Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go.

MITAuto-check passedProductivity & Automation

Install Still2rig Psd

skills CLI
$ npx skills add shinshin86/still2rig-psd --skill still2rig-psd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shinshin86/still2rig-psd still2rig-psd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shinshin86/still2rig-psd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/still2rig-psd .claude/skills/still2rig-psd && rm -rf skills-src

Use ~/.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/

Facts

Skill name
still2rig-psd
GitHub stars
130
Token cost
~1.4k tokens
SKILL.md length
704 words
Files
2
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go.

  • Works in 3 steps: Run npm run doctor. Resolve missing… → Run npm run still2rig-psd -- prepare… → Confirm the copied input hash in…
  • Still2Rig PSD conversion
  • SKILL.md covers Preflight and job creation, Colab consent boundary, Execute the generated cells and Import and finalize, plus 2 more sections
  • Calls npm

What it does

Still2rig Psd is an agent skill from shinshin86/still2rig-psd. Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go. Use for Still2Rig PSD conversion, repair, import, or QA requests; do not use for unrelated PSD editing or general browser automation.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Productivity & Automation, covering Jupyter notebooks and Browser automation. It works with Model Context Protocol and npm. The repository describes itself as: Turn one static anime character image into a structured, QA-checked PSD with Codex, a user-approved Google Colab GPU session, and a built-in motion preview. The licence is MIT.

When your agent uses it

  • Still2Rig PSD conversion
  • Do not use for unrelated PSD editing
  • General browser automation

Example prompts

  • “/still2rig-psd”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Run npm run doctor. Resolve missing local prerequisites without modifying
  2. Run npm run still2rig-psd -- prepare [--name ].
  3. Confirm the copied input hash in .still2rig-psd/jobs//job.json before any

What it can do on your machine

Read from SKILL.md and the folder at commit 29f2c08. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Still2rig Psd loads about 1.4k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated 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); files beside SKILL.md are not scanned.

SKILL.md

The full file from shinshin86/still2rig-psd at commit 29f2c08, republished under its MIT licence (© shinshin86). 704 words, ~1,361 tokens.

Download SKILL.mdSave it as .claude/skills/still2rig-psd/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
still2rig-psd
description
Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go. Use for Still2Rig PSD conversion, repair, import, or QA requests; do not use for unrelated PSD editing or general browser automation.

Still2Rig PSD

Use the project CLI as the source of truth for job state and generated Colab cells. Run commands from the repository root.

Preflight and job creation

  1. Run npm run doctor. Resolve missing local prerequisites without modifying global Codex configuration. Installing software still requires normal user approval.
  2. Run npm run still2rig-psd -- prepare <image> [--name <job>].
  3. Confirm the copied input hash in .still2rig-psd/jobs/<job>/job.json before any remote execution.

Before connecting, tell the user that the next MCP call will wait for their Colab tab. Run npm run still2rig-psd -- colab-url and give that URL to the user so they can open it in the intended signed-in Chrome profile and select an L4 GPU.

  • Use only the colab-mcp tools supplied by Colab MCP Go.
  • Do not use Chrome control, an in-app browser, Computer Use, or UI automation.
  • Do not select an account, accept terms, allocate a runtime, or change a GPU on the user's behalf.
  • Call open_colab_browser_connection only after clearly announcing it. The MCP approval prompt is the authorization gate.
  • Never call disconnect_colab_runtime or delete the runtime. Leave release of compute to the user unless they explicitly request it in the current turn.
  • Stop after three connection failures and report the exact failure; do not switch to another browser or MCP implementation silently.

Execute the generated cells

After connection, call list_colab_tools. Use the notebook tools it reports (normally add_code_cell, run_code_cell, and get_cells; names can vary). Add and run these exact generated files in order:

  1. 01-upload.py
  2. 02-setup.py
  3. 03-run.py
  4. 04-download.py

Read a cell with npm run still2rig-psd -- cell <job> <cell-file>. Do not rewrite the cell ad hoc. Wait for completion and inspect outputs after each stage. Stop on Python exceptions, input-hash mismatch, wrong GPU, revision mismatch, or a missing output PSD. The final cell starts a normal browser download; it does not transfer bytes through the MCP response.

Import and finalize

Once still2rig-psd-<job>.zip is present locally, run:

bash
npm run still2rig-psd -- import <job> /path/to/still2rig-psd-<job>.zip
npm run still2rig-psd -- finalize <job>

If the user provides full-canvas, registered expression files named mouth_open.png, mouth_close.png, or eye_close.png, pass their directory as --expressions <dir>. Use --preview-placeholders only when the user wants a non-production preview. Never describe copied or missing expressions as real lip-sync or blink art.

Choose the expression source in this order:

  1. Drawn expression files from the user: pass them with --expressions <dir>.
  2. An available image generation tool (for example, Codex image generation): generate full-canvas eye_close.png and mouth_open.png registered to the source, pass them with --expressions <dir>, and report them as generated art. Require expressionRegistration=true and expressionArtwork=true before calling them ready.
  3. Only when neither is available, as a stopgap: run npm run still2rig-psd -- derive-expressions <job> and rebuild with repair <job> --preview-expressions <dir>. The derived layers reuse the upper lash line and draw a small fixed-shape mouth, so they are less accurate than generated or drawn art. The reports list them under previewExpressions and keep productionReady=false.
Show full SKILL.md (228 more words)Show less

For mouth repair, prefer extracting the closed-mouth ink from the registered original artwork. Do not fill the component interior or carry a skin-colored rectangle into an expression layer. A derived opposite mouth state is preview art, not trustworthy production art. Render both mouth states at full-canvas scale and as a face crop, then require expressionArtwork=true and mouthWithinTolerance=true in the QA report before reporting the repair.

Motion QA

Run npm run still2rig-psd -- motion-qa <job> after the PSD is final. It records the contract captures in the built-in preview renderer and scores them. Run it again with --negative-fixture when the checks themselves changed; that run must FAIL. Only a passing motion-qa report for the current PSD SHA-256 supports a motion, seam, or hair-motion claim, and only for the built-in renderer.

Completion report

Report the job id, input SHA-256, pinned See-through revision, PSD path and SHA-256, contact sheet, structural QA result, expression readiness (including any previewExpressions), and the motion-qa result or that it was not run. A structurally valid PSD is not automatically a Live2D- or renderer-ready rig.

Tell the user that npm run preview starts the built-in local PSD preview. It lists finalized outputs and opens the newest PSD without exposing internal job details in the UI. Do not launch a browser automatically.

For failure modes and the exact trust model, read ../../../docs/codex-workflow.md and ../../../docs/security.md only when they are relevant.

© shinshin86, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/still2rig-psd of shinshin86/still2rig-psd.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 29f2c08

Compare with similar skills

Still2rig Psd 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.

Still2rig Psd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Still2rig Psd this skillshinshin86/still2rig-psd130—~1.4kAutomated safety check: PassMIT
Electron Devtools Testingankitvgupta/exo495—~2.4kAutomated safety check: PassCustom licence
Anti Detect Browserantibrow/anti-detect-browser-skills17—~9.8kAutomated safety check: WarnMIT
Project Pull Requestswimmwatch/cloakbrowser-mcp164—~1kAutomated safety check: PassMIT
Skyvern Browser AutomationSkyvern-AI/skyvern23k—~1.9kAutomated safety check: PassAGPL-3.0
Browser SearchJohell1NS/browser-search530—~2.5kAutomated safety check: PassMIT

Similar skills

  • Electron Devtools Testing

    ankitvgupta/exo

    Test the Electron app interactively using Chrome DevTools Protocol.

    495 GitHub stars~2.4k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

  • Anti Detect Browser

    antibrow/anti-detect-browser-skills

    Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone…

    17 GitHub stars~9.8k tokensUpdated 1 mo ago
    Testing & QAAuto-check: warnings

  • Project Pull Request

    swimmwatch/cloakbrowser-mcp

    Create, update, prepare, or review a cloakbrowser-mcp GitHub Pull Request only when the user explicitly requests PR work.

    164 GitHub stars~1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Skyvern Browser Automation

    Skyvern-AI/skyvern

    Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.

    23k GitHub stars~1.9k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

  • Browser Search

    Johell1NS/browser-search

    Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser).

    530 GitHub stars~2.5k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

  • Project Release

    swimmwatch/cloakbrowser-mcp

    Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work.

    164 GitHub stars~1.9k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

Works with

Categories

Questions about Still2rig Psd

What does Still2rig Psd do?

Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go. Still2rig Psd is an agent skill from shinshin86/still2rig-psd. Convert a user-provided static anime character image into a verified rig-ready PSD by coordinating the Still2Rig PSD local job CLI with a user-approved Google Colab session through Colab MCP Go.

When should I use Still2rig Psd?

Still2rig Psd fits situations like: still2Rig PSD conversion; do not use for unrelated PSD editing; general browser automation.

How do I install Still2rig Psd in Claude Code?

Run `npx skills add shinshin86/still2rig-psd --skill still2rig-psd -a claude-code`. Or copy the skill folder (.agents/skills/still2rig-psd in shinshin86/still2rig-psd) into .claude/skills/still2rig-psd in your project. Claude Code loads it when a task matches its description.

How do I install Still2rig Psd in Codex?

Run `npx skills add shinshin86/still2rig-psd --skill still2rig-psd -a codex`. Or copy the skill folder (.agents/skills/still2rig-psd in shinshin86/still2rig-psd) into .agents/skills/still2rig-psd in your project. Codex loads it when a task matches its description.

Can I use Still2rig Psd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shinshin86/still2rig-psd --skill still2rig-psd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/still2rig-psd, .gemini/skills/still2rig-psd, .github/skills/still2rig-psd and .opencode/skills/still2rig-psd in your project.

What does Still2rig Psd need to run?

Going by SKILL.md and its folder, Still2rig Psd needs the command-line tools its instructions call (npm). Our summary lists: Python 3.

Does Still2rig Psd access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Still2rig Psd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Still2rig Psd use?

Still2rig Psd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Still2rig Psd use?

About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Still2rig Psd?

Skills that share tags, products or a category with Still2rig Psd: Electron Devtools Testing (ankitvgupta/exo, 495 stars), Anti Detect Browser (antibrow/anti-detect-browser-skills, 17 stars), Project Pull Request (swimmwatch/cloakbrowser-mcp, 164 stars) and Skyvern Browser Automation (Skyvern-AI/skyvern, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Still2rig Psd?

shinshin86 (a GitHub user) maintains it in shinshin86/still2rig-psd, which has 130 GitHub stars. The repository was last updated on September 29, 2026.

Source: shinshin86/still2rig-psd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.