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

Official agent skill

Promptkit

by microsoft in microsoft/PromptKit

PromptKit composition engine. An agent skill from microsoft/PromptKit.

OfficialMITAuto-check passedDevelopment

Install Promptkit

skills CLI
$ npx skills add microsoft/PromptKit --skill promptkit -a claude-code

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

GitHub CLI
$ gh skill install microsoft/PromptKit promptkit --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/microsoft/PromptKit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/promptkit .claude/skills/promptkit && 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
promptkit
GitHub stars
110
Token cost
~420 tokens
SKILL.md length
152 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

PromptKit composition engine. An agent skill from microsoft/PromptKit.

  • Works in 5 steps: Read bootstrap.md before doing anything… → Follow its instructions to inspect… → Gather any required parameters or… → …
  • The user wants to assemble a task-specific prompt
  • SKILL.md covers Inputs, Output and Workflow
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Promptkit is an agent skill from microsoft/PromptKit, published by the product's own GitHub organization. PromptKit composition engine. Use this skill when the user wants to assemble a task-specific prompt, write a requirements doc, investigate a bug, review code, plan an implementation, author agent instructions, create a Copilot prompt file, build an agentic workflow, or perform any engineering task that PromptKit has a template for. Also use when the user mentions PromptKit, asks about available templates or personas, or wants to compose prompts from reusable components.

Its SKILL.md is about 420 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, Prompt engineering and Agent instruction files. The repository describes itself as: Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components (personas, protocols, formats… The licence is MIT.

When your agent uses it

  • The user wants to assemble a task-specific prompt
  • Write a requirements doc
  • Investigate a bug
  • Plan an implementation

Example prompts

  • “/promptkit”

Workflow steps

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

  1. Read bootstrap.md before doing anything else.
  2. Follow its instructions to inspect manifest.yaml and identify the
  3. Gather any required parameters or clarify missing inputs from the user.
  4. Assemble the prompt in the order defined by PromptKit.
  5. Return the assembled prompt or continue the interactive workflow exactly

What it can do on your machine

Read from SKILL.md and the folder at commit 074dc8d. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Promptkit loads about 420 tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 152 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~420

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 microsoft/PromptKit at commit 074dc8d, republished under its MIT licence (© microsoft). 152 words, ~420 tokens.

Download SKILL.mdSave it as .claude/skills/promptkit/SKILL.md (or your agent's skills folder).
name
promptkit
description
PromptKit composition engine. Use this skill when the user wants to assemble a task-specific prompt, write a requirements doc, investigate a bug, review code, plan an implementation, author agent instructions, create a Copilot prompt file, build an agentic workflow, or perform any engineering task that PromptKit has a template for. Also use when the user mentions PromptKit, asks about available templates or personas, or wants to compose prompts from reusable components.
<!-- Generated by PromptKit — edit with care -->

You must read and execute bootstrap.md in the repository root. Treat it as the entry point and single source of truth for PromptKit component discovery, template selection, parameter gathering, and prompt assembly.

Inputs

  • The user's task, question, or requested artifact.
  • Any repository context needed to choose the right PromptKit template, persona, protocols, format, taxonomy, and parameters.
  • Any constraints, goals, or non-goals the user has already provided.

Output

  • A PromptKit-assembled prompt ready to use for the requested task, or
  • The result of executing the selected interactive PromptKit workflow in the current session, as directed by bootstrap.md.

Workflow

  1. Read bootstrap.md before doing anything else.
  2. Follow its instructions to inspect manifest.yaml and identify the appropriate PromptKit components.
  3. Gather any required parameters or clarify missing inputs from the user.
  4. Assemble the prompt in the order defined by PromptKit.
  5. Return the assembled prompt or continue the interactive workflow exactly as bootstrap.md directs.

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

Files

Just SKILL.md in .github/skills/promptkit of microsoft/PromptKit.

Open the folder on GitHubat commit 074dc8d

Compare with similar skills

Promptkit 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.

Promptkit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Promptkit this skillmicrosoft/PromptKit110—~420Automated safety check: PassMIT
Code Reviewimbenrabi/Financial-Modeling-Prep-MCP-Server150—~2.6kAutomated safety check: PassApache-2.0
Shipmillionco/react-doctor15k—~716Automated safety check: PassCustom licence
Megingiard Code Reviewstormpanda/megingiard154—~2.9kAutomated safety check: PassCustom licence
Ad ReviewCorridorTech/PoseCap224—~2.4kAutomated safety check: NotesApache-2.0
Review Steeringdralgorhythm/claude-agentic-framework125—~1.1kAutomated safety check: PassNone

Similar skills

  • Code Review

    imbenrabi/Financial-Modeling-Prep-MCP-Server

    Review a PR or working diff against this repo's intent layer (the AGENTS.md hierarchy), toolception pitfalls, and core invariants.

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

  • Ship

    millionco/react-doctor

    Take the current branch from done-coding to merge-ready in one pass — review the diff against AGENTS.md, deslop, commit and push, open a PR using rule-validate's PR copy, then babysit until mergeable.

    15k GitHub stars~716 tokensUpdated today
    DevelopmentAuto-check passed

  • Megingiard Code Review

    stormpanda/megingiard

    Conduct a thorough code review of the current Git branch or specific files in Megingiard.

    154 GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Ad Review

    CorridorTech/PoseCap

    Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

    224 GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • Review Steering

    dralgorhythm/claude-agentic-framework

    Compiles REVIEW.md and keeps CLAUDE.md accurate as the two sanctioned surfaces for steering Anthropic's managed Code Review service, translating this repo's rules into terse reviewer imperatives.

    125 GitHub stars~1.1k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

  • Fitness Functions

    rshankras/claude-code-apple-skills

    Write architecture fitness functions — deterministic tests that enforce a project's hard rules (module boundaries, offline guarantees, content contracts) from inside its own test target.

    783 GitHub stars~2k tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes

More from microsoft/PromptKit

  • Respond To PR Comments

    microsoft/PromptKit

    Official

    Respond to pull request review comments on GitHub or Azure DevOps Services.

    110 GitHub stars~4.2k tokensUpdated 19 days ago
    Auto-check passed

  • Ingest Cwe Taxonomies

    microsoft/PromptKit

    Official

    Ingest the official MITRE CWE database and generate per-domain security audit taxonomies for PromptKit.

    110 GitHub stars~356 tokensUpdated 19 days ago
    Auto-check passed

Categories

Questions about Promptkit

What does Promptkit do?

PromptKit composition engine. An agent skill from microsoft/PromptKit. Promptkit is an agent skill from microsoft/PromptKit, published by the product's own GitHub organization. PromptKit composition engine.

When should I use Promptkit?

Promptkit fits situations like: the user wants to assemble a task-specific prompt; write a requirements doc; investigate a bug; plan an implementation.

How do I install Promptkit in Claude Code?

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

How do I install Promptkit in Codex?

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

Can I use Promptkit 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 microsoft/PromptKit --skill promptkit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/promptkit, .gemini/skills/promptkit, .github/skills/promptkit and .opencode/skills/promptkit in your project.

What does Promptkit need to run?

SKILL.md names no scripts, command-line tools or credentials: Promptkit is instructions for the agent only.

Does Promptkit 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 Promptkit 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 Promptkit use?

Promptkit 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 Promptkit use?

About 420 tokens (SKILL.md is roughly 1.7k 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 Promptkit?

Skills that share tags, products or a category with Promptkit: Code Review (imbenrabi/Financial-Modeling-Prep-MCP-Server, 150 stars), Ship (millionco/react-doctor, 15k stars), Megingiard Code Review (stormpanda/megingiard, 154 stars) and Ad Review (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Promptkit?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/PromptKit, which has 110 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 18, 2026.

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