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

Mdtask Do

by syabro in syabro/mdtask

Work one project task end to end — pick, plan, review, execute, review code, update the spec, commit

Custom licenceAuto-check passedDevelopment

Install Mdtask Do

skills CLI
$ npx skills add syabro/mdtask --skill mdtask-do -a claude-code

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

GitHub CLI
$ gh skill install syabro/mdtask mdtask-do --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/syabro/mdtask.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mdtask-do .claude/skills/mdtask-do && 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
mdtask-do
GitHub stars
246
Token cost
~2.7k tokens
SKILL.md length
1,694 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Custom licence

At a glance

Work one project task end to end — pick, plan, review, execute, review code, update the spec, commit

  • Works in 8 steps: Pick a task → Plan → Review the plan → …
  • Tasks that involve Code review
  • SKILL.md covers Flow, When you can't decide — park it and Working a list of tasks
  • Calls pnpm

What it does

Mdtask Do is an agent skill from syabro/mdtask. Work one project task end to end — pick, plan, review, execute, review code, update the spec, commit

Its SKILL.md is about 2.7k 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 Code review. The repository describes itself as: The spec-driven development system where specs and tasks live in your repo and never drift from the code.

When your agent uses it

  • Tasks that involve Code review

Example prompts

  • “/mdtask-do”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Pick a task
  2. Plan
  3. Review the plan
  4. Execute with risk-based validation and behavior check
  5. Review the code
  6. Final validation
  7. Record what was done
  8. Commit

What it can do on your machine

Read from SKILL.md and the folder at commit fe28740. 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

Mdtask Do loads about 2.7k tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 1,694 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,694 words (~2,680 tokens).

“Gate — do this before reading any further. Your first action is to materialize the steps below as a live, checkable list and tick items off as you go (you'll confirm against it before the commit in Step 8). The…”

— opening of SKILL.md by syabro, Custom licence
name
mdtask-do
disable-model-invocation
false

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/mdtask-do of syabro/mdtask.

Open the folder on GitHubat commit fe28740

Compare with similar skills

Mdtask Do 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.

Mdtask Do compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mdtask Do this skillsyabro/mdtask246—~2.7kAutomated safety check: PassCustom licence
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow156k—~3.5kAutomated safety check: NotesMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    156k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Mole Bug Patterns

    tw93/Mole

    A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

More from syabro/mdtask

  • Mdtask

    syabro/mdtask

    A skill your agent uses for the task format and the spec-driven development reference — the spec→build→document cycle and spec file structure — and for inspecting or editing existing tasks in .md…

    246 GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed

  • Mdtask Add

    syabro/mdtask

    ALWAYS invoke this skill when user asks to add, create, or track a task — including indirect requests like "make a task for X", "add a task for this", "we need a task to...".

    246 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Mdtask Do

What does Mdtask Do do?

Work one project task end to end — pick, plan, review, execute, review code, update the spec, commit. Mdtask Do is an agent skill from syabro/mdtask.

When should I use Mdtask Do?

Mdtask Do fits situations like: tasks that involve Code review.

How do I install Mdtask Do in Claude Code?

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

How do I install Mdtask Do in Codex?

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

Can I use Mdtask Do 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 syabro/mdtask --skill mdtask-do -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mdtask-do, .gemini/skills/mdtask-do, .github/skills/mdtask-do and .opencode/skills/mdtask-do in your project.

What does Mdtask Do need to run?

Going by SKILL.md and its folder, Mdtask Do needs the command-line tools its instructions call (pnpm).

Does Mdtask Do 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 Mdtask Do 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 Mdtask Do use?

Mdtask Do has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Mdtask Do use?

About 2.7k tokens (SKILL.md is roughly 11k 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 Mdtask Do?

Skills that share tags, products or a category with Mdtask Do: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 156k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mdtask Do?

syabro (a GitHub user) maintains it in syabro/mdtask, which has 246 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 6, 2026.

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