Assemble complex, task-specific prompts using the PromptKit library and templates.

Install

mkdir -p .claude/skills/promptkit && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10526" && unzip -o skill.zip -d .claude/skills/promptkit && rm skill.zip

Installs to .claude/skills/promptkit

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

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.
474 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Write requirements documents using templates
  • Investigate bugs with structured prompts
  • Review code using predefined personas and protocols
  • Plan implementations with PromptKit templates
  • Author agent instructions and build agentic workflows

How it works

The skill reads and executes `bootstrap.md` to discover components, select templates, gather parameters, and assemble the prompt or orchestrate an interactive workflow.

Inputs & outputs

You give it
User's task, question, or requested artifact, along with repository context and constraints
You get back
A PromptKit-assembled prompt or the result of an interactive PromptKit workflow

When to use promptkit

  • Building agent workflows
  • Writing complex requirements
  • Assembling prompts for code review

About this skill

<!-- 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.

When not to use it

  • When the task does not involve PromptKit templates or components
  • When `bootstrap.md` is not available or cannot be executed
  • When the user does not want to assemble a structured prompt

Limitations

  • Requires `bootstrap.md` as the entry point and single source of truth
  • Relies on `manifest.yaml` for component discovery
  • Output is either an assembled prompt or the result of an interactive workflow

How it compares

This skill automates the structured assembly of prompts and workflows using predefined templates and components, providing consistency and efficiency compared to manually crafting prompts.

Compared to similar skills

promptkit side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
promptkit (this skill)04moNo flagsIntermediate
prompt-optimize139moNo flagsAdvanced
ai-cost-optimizer95moCautionIntermediate
self-improving-agent121moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by microsoft

View all by microsoft

You might also like

prompt-optimize

YYH211

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.

13113

ai-cost-optimizer

ScientiaCapital

Save 40-70% on AI costs with intelligent multi-LLM routing. Automatically selects the optimal model based on task complexity across 40+ models from 8 providers.

990

self-improving-agent

alirezarezvani

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

128

ccs-delegation

kaitranntt

Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p "task"` or `ccs {profile}:continue`, and reports results. Triggers on "use ccs [task]" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.

210

skill-from-notebook

GBSOSS

Extract methodologies from documents or examples to create executable skills

28

prompt-factory

alirezarezvani

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations.

45

Search skills

Search the agent skills registry