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

Start Task

by maotoumao in maotoumao/Cebian

Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.

AGPL-3.0Auto-check passedAgent Workflows

Install Start Task

skills CLI
$ npx skills add maotoumao/Cebian --skill start-task -a claude-code

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

GitHub CLI
$ gh skill install maotoumao/Cebian start-task --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/maotoumao/Cebian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/start-task .claude/skills/start-task && 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
start-task
GitHub stars
163
Token cost
~580 tokens
SKILL.md length
320 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.

  • Works in 7 steps: Locate the plan → Find the next subtask → Sync the TODO list → …
  • Tasks that involve Task breakdown
  • Calls pnpm
  • Tasks that involve Agent instruction files

What it does

Start Task is an agent skill from maotoumao/Cebian. Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.

Its SKILL.md is about 580 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 Agent Workflows, covering Task breakdown and Agent instruction files. It works with Chrome Extensions. The repository describes itself as: An AI assistant that lives in your browser side panel. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Task breakdown
  • Tasks that involve Agent instruction files

Example prompts

  • “/start-task”

Workflow steps

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

  1. Locate the plan
  2. Find the next subtask
  3. Sync the TODO list
  4. Execute exactly that one subtask
  5. Code review
  6. Hand off to the user
  7. Wait for explicit approval

What it can do on your machine

Read from SKILL.md and the folder at commit d566708. 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:

    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, 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

Start Task loads about 580 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 320 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~580

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 maotoumao/Cebian at commit d566708, republished under its AGPL-3.0 licence (© maotoumao). 320 words, ~580 tokens.

Download SKILL.mdSave it as .claude/skills/start-task/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
start-task
description
Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md.

Resume work on an in-progress plan. Follow the Task Execution Workflow defined in AGENTS.md strictly — one subtask, code review, test instructions, then stop.

Steps

  1. Locate the plan

    • If the user provided a path, use that file.
    • Otherwise list docs/plans/ and pick the most recently modified *.md plan that is not marked PROPOSAL. Confirm the choice with the user in one short line before proceeding.

  2. Find the next subtask

    • Read the plan and locate the first ## Task N: section that still contains unchecked - [ ] steps.
    • If every task is fully checked, report "All tasks complete" and stop. Do not invent new work.

  3. Sync the TODO list

    • Use your harness's todo/task list to mirror the plan's tasks. Mark already-completed tasks as completed, the located next task as in-progress, and remaining tasks as not-started.

  4. Execute exactly that one subtask

    • Implement only the steps inside that single ## Task N: section.
    • Do not touch files belonging to later tasks. Do not look ahead.
    • When the implementation is done, update the plan file to check off (- [x]) the steps you completed.

  5. Code review

    • Run the repository's code-review workflow in the current harness's dedicated read-only reviewer. Pass it the files changed in this task and the plan section as context, then address any actionable issues before continuing.

  6. Hand off to the user

    • Provide concrete manual testing instructions: what to run (pnpm dev is usually already running in the dev terminal), what to open, what to click, expected console output, expected UI state.
    • Then stop. Do not start the next task. Do not mark the TODO completed yet.

  7. Wait for explicit approval

    • Only after the user replies with explicit approval (e.g., "approved", "next", "looks good", "passed") should the TODO be marked completed. Acknowledgements and silence are not approval.

If the plan turns out to be wrong or incomplete during step 4, stop and trigger the Plan-First re-approval flow instead of pushing forward.

© maotoumao, AGPL-3.0. 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/start-task of maotoumao/Cebian.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit d566708

Compare with similar skills

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.

Start Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Start Task this skillmaotoumao/Cebian163—~580Automated safety check: PassAGPL-3.0
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k19 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed

  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 19 repos~2.7k tokens
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from maotoumao/Cebian

  • Code Review

    maotoumao/Cebian

    A skill your agent uses when completing a coding task to perform senior-level code review.

    163 GitHub stars~3.6k tokensUpdated today
    Auto-check passed

  • I18n Naming

    maotoumao/Cebian

    Cebian project i18n key naming, placeholder, pluralization, file layout, and glossary conventions.

    163 GitHub stars~3.7k tokensUpdated today
    Auto-check passed

  • Skill Creator

    maotoumao/Cebian

    Create new Cebian skills, edit or improve existing ones, scaffold multi-file skill packages, and validate them against the agentskills.io specification.

    163 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Cl

    maotoumao/Cebian

    审计自上次发版以来的提交，把遗漏的「用户可见变更」补进 CHANGELOG.md 的 [Unreleased]；可选地把 [Unreleased] 收口成正式版本节

    163 GitHub stars~428 tokensUpdated today
    Auto-check passed

  • Upgrade Packages

    maotoumao/Cebian

    调研 package.json 所有依赖的最新版本，交叉验证版本差异，给出可升级到最新版的结论. An agent skill from maotoumao/Cebian.

    163 GitHub stars~505 tokensUpdated today
    Auto-check passed

  • Upgrade Pi

    maotoumao/Cebian

    升级pi-agent-core和pi-ai到最新版本

    163 GitHub stars~894 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Start Task

What does Start Task do?

Resume execution of an approved plan from the next unchecked subtask, following the gated Task Execution Workflow in AGENTS.md. Start Task is an agent skill from maotoumao/Cebian.md.

When should I use Start Task?

Start Task fits situations like: tasks that involve Task breakdown; tasks that involve Agent instruction files.

How do I install Start Task in Claude Code?

Run `npx skills add maotoumao/Cebian --skill start-task -a claude-code`. Or copy the skill folder (.agents/skills/start-task in maotoumao/Cebian) 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 maotoumao/Cebian --skill start-task -a codex`. Or copy the skill folder (.agents/skills/start-task in maotoumao/Cebian) 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 maotoumao/Cebian --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 (pnpm).

Does Start Task access the network?

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.

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 AGPL-3.0 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 580 tokens (SKILL.md is roughly 2.3k 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: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Start Task?

maotoumao (a GitHub user) maintains it in maotoumao/Cebian, which has 163 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 2026.

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