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

Task Create

by jiangzhe in jiangzhe/doradb

Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task…

Apache-2.0Auto-check passedDevelopment

Install Task Create

skills CLI
$ npx skills add jiangzhe/doradb --skill task-create -a claude-code

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

GitHub CLI
$ gh skill install jiangzhe/doradb task-create --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/jiangzhe/doradb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/task-create .claude/skills/task-create && 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
task-create
GitHub stars
121
Token cost
~581 tokens
SKILL.md length
264 words
Files
3 (incl. references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task…

  • Works in 7 steps: Research relevant architecture and… → Apply the strict complexity gate and… → Run Round 1 with current-state analysis,… → …
  • Planning a feature
  • SKILL.md covers Required Flow, Proposal Quality Gate, Write Boundary and Output Quality
  • Calls cargo

What it does

Task Create is an agent skill from jiangzhe/doradb. Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task worktree creation. Use when planning a feature or bug fix into docs/tasks, including work sourced from backlog items or RFC phases.

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/workflow.md`).

It sits in Development, covering Git worktrees, Debugging and Proposals and quotes. The repository describes itself as: DoraDB - Async Rust storage engine. The licence is Apache-2.0.

When your agent uses it

  • Planning a feature
  • Bug fix into docs/tasks
  • Including work sourced from backlog items

Example prompts

  • “/task-create”

Workflow steps

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

  1. Research relevant architecture and process documents, then inspect impacted code paths.
  2. Apply the strict complexity gate and escalate program-level work to
  3. Run Round 1 with current-state analysis, evidence references, and materially different proposals.
  4. Require user feedback on the recommendation.
  5. Run Round 2 to finalize scope, interfaces, implementation details, tests, and open questions.
  6. Require explicit user approval before writing any task document or creating its worktree.
  7. After approval, allocate the task id from the dispatch root, create an isolated worktree from origin/main, and write the task document…

What it can do on your machine

Read from SKILL.md and the folder at commit 3291b68. 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:

    • cargo

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

  • Network

    No URLs in SKILL.md.

    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

Task Create loads about 581 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 86 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
~86
When it runs · the whole SKILL.md, loaded when a task matches
~581
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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 jiangzhe/doradb at commit 3291b68, republished under its Apache-2.0 licence (© jiangzhe). 264 words, ~581 tokens.

Download SKILL.mdSave it as .claude/skills/task-create/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
task-create
description
Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task worktree creation. Use when planning a feature or bug fix into docs/tasks, including work sourced from backlog items or RFC phases.

Task Create Workflow

Use this skill to design a decision-complete task document before implementation. Scripts are executable; invoke them directly (no cargo +nightly -Zscript prefix).

Read references/workflow.md completely before executing this workflow.

Required Flow

  1. Research relevant architecture and process documents, then inspect impacted code paths.
  2. Apply the strict complexity gate and escalate program-level work to $rfc-create.
  3. Run Round 1 with current-state analysis, evidence references, and materially different proposals.
  4. Require user feedback on the recommendation.
  5. Run Round 2 to finalize scope, interfaces, implementation details, tests, and open questions.
  6. Require explicit user approval before writing any task document or creating its worktree.
  7. After approval, allocate the task id from the dispatch root, create an isolated worktree from origin/main, and write the task document there.

Do not skip or reorder these gates.

Proposal Quality Gate

Include these explicit proposals in Round 1:

  • First-Principles Proposal
  • Long-Term Evolution Proposal
  • Original-Requirement-Fit Proposal

Recommend the best overall direction for correctness and project evolution. Do not default to the original request, and do not use effort tiers as substitutes for materially different strategic directions.

Write Boundary

Do not create draft task files before approval. After approval, write only under .worktrees/<task-id>/docs/tasks/; never fall back to the dispatch root when worktree creation fails.

Keep Implementation Notes blank during task design.

Output Quality

Ensure the resulting task document is:

  1. Grounded in current code and documentation.
  2. Narrow enough for one testable task.
  3. Decision-complete for direct implementation.
  4. Explicit about goals, non-goals, impacts, risks, and tests.
  5. Traceable to source backlog or RFC phase inputs when applicable.

© jiangzhe, Apache-2.0. 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 2 other files (references) in .agents/skills/task-create of jiangzhe/doradb.

  • SKILL.md
  • agents/openai.yaml
  • references/workflow.md

Open the folder on GitHubat commit 3291b68

Compare with similar skills

Task Create 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.

Task Create compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Create this skilljiangzhe/doradb121—~581Automated safety check: PassApache-2.0
Burla Parallel Dev ClustersBurla-Cloud/burla263—~1.6kAutomated safety check: PassCustom licence
Keen Pbr Symbolize Crashmaksimkurb/keen-pbr139—~1.4kAutomated safety check: PassGPL-3.0
Codex Agentmajiayu000/spellbook286—~1.9kAutomated safety check: PassMIT
Plan Loopgaasher/Agent-Loop-Skills174—~2.6kAutomated safety check: PassMIT
Contribution Architectmajiayu000/spellbook286—~1.8kAutomated safety check: NotesMIT

Similar skills

  • Burla Parallel Dev Clusters

    Burla-Cloud/burla

    Sets up an isolated Burla dev cluster per git worktree so several agents can work in parallel, and explains when to use local-dev or remote-dev.

    263 GitHub stars~1.6k tokensUpdated 16 days ago
    DevelopmentAuto-check passed

  • Keen Pbr Symbolize Crash

    maksimkurb/keen-pbr

    Diagnose Keen PBR native crashes from KPBR-CRASH v1 or legacy raw logs.

    139 GitHub stars~1.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Codex Agent

    majiayu000/spellbook

    A skill your agent uses when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals.

    286 GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Plan Loop

    gaasher/Agent-Loop-Skills

    A skill your agent uses when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the planning stage of a prompt → plan →…

    174 GitHub stars~2.6k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

  • Contribution Architect

    majiayu000/spellbook

    A skill your agent uses when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

    286 GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check: notes

  • Vibe Implement

    idiotLeoLYJ/Daliu-Awesome-Skills

    Vibe Coding 流水线的实现阶段(流水线终点,顺序 idea → interaction → architecture → design → prototype → implement)。当 interaction.md、architecture.md、design.md、prototypes/ 已就绪,用户说"开始实现""写代码""把设计落地""进入开发""implement /…

    140 GitHub stars~2.7k tokensUpdated 29 days ago
    Agent WorkflowsAuto-check passed

More from jiangzhe/doradb

All 10 skills in this repo

  • Backlog

    jiangzhe/doradb

    Manage backlog todo documents in docs/backlogs with deterministic tooling.

    121 GitHub stars~1k tokensUpdated 3 days ago
    Auto-check passed

  • Issue Rfc

    jiangzhe/doradb

    Create and list GitHub Issues for Doradb RFC documents with deterministic scripts.

    121 GitHub stars~519 tokensUpdated 3 days ago
    Auto-check passed

  • Issue Task

    jiangzhe/doradb

    Create and list GitHub Issues for Doradb task documents with deterministic scripts.

    121 GitHub stars~719 tokensUpdated 3 days ago
    Auto-check passed

  • Rfc Create

    jiangzhe/doradb

    Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals.

    121 GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed

  • Rfc Resolve

    jiangzhe/doradb

    Resolve completed or superseded Doradb RFC programs after implementation tasks, tests, review, and verification are complete.

    121 GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check passed

  • Style Audit

    jiangzhe/doradb

    Audit branch-diff Rust files, or explicitly requested file/directory Rust targets, for Doradb coding style using deterministic tooling and concise read-only review.

    121 GitHub stars~951 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Task Create

What does Task Create do?

Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task…. Task Create is an agent skill from jiangzhe/doradb. Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task worktree creation.

When should I use Task Create?

Task Create fits situations like: planning a feature; bug fix into docs/tasks; including work sourced from backlog items.

How do I install Task Create in Claude Code?

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

How do I install Task Create in Codex?

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

Can I use Task Create 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 jiangzhe/doradb --skill task-create -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-create, .gemini/skills/task-create, .github/skills/task-create and .opencode/skills/task-create in your project.

What does Task Create need to run?

Going by SKILL.md and its folder, Task Create needs the command-line tools its instructions call (cargo).

Does Task Create 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 Task Create 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 Task Create use?

Task Create is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Task Create use?

About 581 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. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Task Create?

Skills that share tags, products or a category with Task Create: Burla Parallel Dev Clusters (Burla-Cloud/burla, 263 stars), Keen Pbr Symbolize Crash (maksimkurb/keen-pbr, 139 stars), Codex Agent (majiayu000/spellbook, 286 stars) and Plan Loop (gaasher/Agent-Loop-Skills, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Create?

jiangzhe (a GitHub user) maintains it in jiangzhe/doradb, which has 121 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 5, 2026.

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