Install the "start-task" agent skill from https://github.com/yuriolive/PortPS5/tree/main/.agents/skills/start-task into .claude/skills/start-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start-task", 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.
Type 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.
skills CLI
$ npx skills add yuriolive/PortPS5 --skill start-task -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "start-task" agent skill from https://github.com/yuriolive/PortPS5/tree/main/.agents/skills/start-task into .agents/skills/start-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start-task", 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.
skills CLI
$ npx skills add yuriolive/PortPS5 --skill start-task -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "start-task" agent skill from https://github.com/yuriolive/PortPS5/tree/main/.agents/skills/start-task into .cursor/skills/start-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start-task", 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.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add yuriolive/PortPS5 --skill start-task -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "start-task" agent skill from https://github.com/yuriolive/PortPS5/tree/main/.agents/skills/start-task into .gemini/skills/start-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start-task", 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.
GitHub CLI
$ gh skill install yuriolive/PortPS5 start-task
Installs 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).
skills CLI
$ npx skills add yuriolive/PortPS5 --skill start-task -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "start-task" agent skill from https://github.com/yuriolive/PortPS5/tree/main/.agents/skills/start-task into .github/skills/start-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start-task", 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.
skills CLI
$ npx skills add yuriolive/PortPS5 --skill start-task -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "start-task" agent skill from https://github.com/yuriolive/PortPS5/tree/main/.agents/skills/start-task into .opencode/skills/start-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "start-task", 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.
Facts
Skill name
start-task
GitHub stars
123
Token cost
~629 tokens
SKILL.md length
264 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
GPL-2.0
At a glance
Standard procedure to start a new task in PortPS5. An agent skill from yuriolive/PortPS5.
SKILL.md covers 1. Upstream & Remote Sync, 2. Check Roadmap & Subsystem…, 3. Create Worktree & Branch and 4. Structure the Task Plan, plus 1 more section
Calls git; reaches github.com
What it does
Start Task is an agent skill from yuriolive/PortPS5. Standard procedure to start a new task in PortPS5. Checks upstream AnyPS5 for reference code, creates an isolated git worktree, sets up the structured task plan, and establishes test baselines.
Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Git worktrees. It works with Git. The repository describes itself as: Converts decrypted PS5 game dumps into native Windows executables via binary relinking, replacement system libraries, and Vulkan. No CPU emulation. The licence is GPL-2.0.
When your agent uses it
Tasks that involve Git worktrees
Example prompts
“/start-task”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit aa7d6da. 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:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
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
Start Task loads about 629 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 264 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~51
When it runs· the whole SKILL.md, loaded when a task matches
~629
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.
Download SKILL.mdSave it as .claude/skills/start-task/SKILL.md (or your agent's skills folder).
name
start-task
description
Standard procedure to start a new task in PortPS5. Checks upstream AnyPS5 for reference code, creates an isolated git worktree, sets up the structured task plan, and establishes test baselines.
Start a Task
When starting any new task, bugfix, or roadmap deliverable on PortPS5, execute this workflow in order:
Note useful patterns, data structures, or bug fixes to adapt.
Never copy verbatim without adaptation: PortPS5 strictly requires APS5_VABI on guest exports, no host exceptions crossing ABI boundaries (noexcept / SCE error codes), GTest suites (portps5_add_gtest), no title-specific hacks, and comprehensive code comments explaining "why, not what".
2. Check Roadmap & Subsystem Spec
Consult docs/ROADMAP.md to confirm the milestone scope and exit criteria.
Read the subsystem spec in docs/spec/<subsystem>.md (Target design, Decisions, Interfaces, Failure modes).
Run beans list (or beans list --json --ready) to find an existing bean for this work; create one with beans create if none exists (see AGENTS.md "Task tracking (beans)").
3. Create Worktree & Branch
Ensure the base is up to date with origin/main:bash
Start Task 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.
Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.
Creates or reuses an isolated AgentsMesh Git worktree from a verified base branch, preserves existing changes, and optionally starts the worktree-scoped development environment.
Standard procedure to start a new task in PortPS5. An agent skill from yuriolive/PortPS5. Start Task is an agent skill from yuriolive/PortPS5. Standard procedure to start a new task in PortPS5.
When should I use Start Task?
Start Task fits situations like: tasks that involve Git worktrees.
How do I install Start Task in Claude Code?
Run `npx skills add yuriolive/PortPS5 --skill start-task -a claude-code`. Or copy the skill folder (.agents/skills/start-task in yuriolive/PortPS5) into .claude/skills/start-task in your project. Claude Code loads it when a task matches its description.
How do I install Start Task in Codex?
Run `npx skills add yuriolive/PortPS5 --skill start-task -a codex`. Or copy the skill folder (.agents/skills/start-task in yuriolive/PortPS5) into .agents/skills/start-task in your project. Codex loads it when a task matches its description.
Can I use Start Task 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 yuriolive/PortPS5 --skill start-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/start-task, .gemini/skills/start-task, .github/skills/start-task and .opencode/skills/start-task in your project.
What does Start Task need to run?
Going by SKILL.md and its folder, Start Task needs the command-line tools its instructions call (git).
Does Start Task access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Start Task 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 Start Task use?
Start Task is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Start Task use?
About 629 tokens (SKILL.md is roughly 2.5k 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 Start Task?
Skills that share tags, products or a category with Start Task: Git Worktree Isolation (jnMetaCode/superpowers-zh, 8.3k stars), Worktree (AgentsMesh/AgentsMesh, 2.4k stars), Cursor Composer Task Delegate (Chachamaru127/claude-code-harness, 3.2k stars) and Git Worktree Setup (k8zdev/k8z, 155 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Start Task?
yuriolive (a GitHub user) maintains it in yuriolive/PortPS5, which has 123 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 1, 2026.
Source: yuriolive/PortPS5 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
