Best Prompt & Skill Engineering Skills for Claude Code

    Skills for writing better prompts, structuring context, and authoring SKILL.md files that agents follow reliably. Turn vague instructions into repeatable behaviour.

    New in Prompt & Skill Engineering

    383 skills · page 1 of 16

    Prompt Dataset Builder

    by Edric Vale

    $9.9

    Build and curate high-quality prompt datasets for fine-tuning and eval — deduped and labeled.

    11
    1621.0(1)

    skill auditor

    by Matthew King

    $5

    Audit, score, and improve your AI agent skills for higher quality, lower token costs, better reliability, and marketplace success. Get actionable recommendations for prompts, instructions, tool usage, error handling, and user experience.

    2
    0

    code context engineering

    by Roy Yuen

    $7

    A high-precision pre-coding gate that detects conflicting requirements and prevents agents from making wrong assumptions.

    2
    0

    Agensi Skill Authoring

    by Markus Isaksson

    Free

    Write a portable SKILL.md in five phases, from purpose through Agensi packaging.

    2
    604.8(4)

    Output Verifier ➡ Make Your AI Agent More Reliable

    by WoW MCP

    $9.47

    Enforce rigorous fact-checking, confidence scoring, and risk-based human gates to eliminate AI hallucinations.

    2
    25.0(1)

    Custom GPT to Agent Skill Converter

    by Shandra

    $5

    Converts Custom GPT instructions, prompt systems, and agent ideas into structured, premium SKILL.md files for AI agent marketplaces.

    2
    0

    Agent Harness Architect

    by PubsProToolkit

    $14

    Model quality is table stakes — the harness is where agents win or fail. This designs yours: it writes a structured, testable system prompt (role, tools, boundaries, method, output contract, failure handling) and maps every concern to the right layer — prompt, tool, guardrail, or evaluation — so the pieces reinforce each other instead of fighting.

    1
    3

    Agent Skill Creator

    by HashLips

    Free

    A skill for creating and structuring reusable Agent Skills with a focused SKILL.md, supporting reference files, clear triggers, and a maintainable architecture. It works best alongside the MD Design System.

    7
    325.0(6)

    MD Design System

    by HashLips

    Free

    A Markdown formatting and sanitization skill that cleans up structure, syntax, spacing, headings, lists, and document layout while preserving the original meaning and requirements.

    6
    194.9(7)

    Skill Creator Pro: Build Skills That Trigger & Work

    by Ignasi

    Free

    Turns any workflow, chat or prompt into a high-quality SKILL.md skill: trigger-optimized description, clear steps, scripts and references, trigger tests and a ready-to-upload ZIP plus marketplace listing copy. Works for Claude Code, Codex, Cursor and more.

    3
    115.0(1)
    NewFree

    Picks the right Claude model (Haiku, Sonnet, Opus or Fable) and effort level for each task, so you spend fewer tokens without losing quality.

    2
    15.0(2)

    3D Reference Researcher

    by Atharva Patil

    Free

    Finds, organizes, and analyzes useful 3D references for modeling, texturing, and VFX work.

    1
    21

    Prompt Engineer: Reliable Prompts & System Prompts

    by Ignasi

    Free

    Writes, diagnoses and tests production-grade prompts and system prompts for LLM apps and agents: clear structure, output schemas, examples, edge cases and injection safety, validated on a small eval set so results stay consistent and cheaper.

    2
    105.0(1)

    Terse Mode: Shorter Answers, Fewer Tokens

    by Ignasi

    Free

    Makes your agent answer in a compact, high-signal style that cuts output tokens 30-75% without losing correctness: no preamble, no recaps, no filler; code, commands and numbers kept verbatim. Three levels (lite, short, ultra) and automatic full detail for risks, explanations and deliverables.

    2
    105.0(1)

    Prompt Marketplace Listing Builder

    by Trumpify Prints

    Free

    Prepare marketplace-ready prompt listings that pass review by enforcing variety rules and avoiding similarity declines.

    1
    85.0(1)

    Task Observer: One Skill to Rule Them All

    by Eoghan Henn

    Free

    The meta-skill that builds and improves all your skills, including itself.

    1
    11

    Agensi Listing Card

    by Joeri Brons

    Free

    Turns any agensi.io skill listing (URL or SKILL.md) into a 1920×1080 explanatory card in Agensi branding: skill name, one-line explainer, numbered how-it-works steps, Agensi footer. Exports a PNG for the listing page.

    1
    45.0(1)

    Prompt Generator & Optimizer (PT BR + EN)

    by Vinícius Yuki

    Free

    Turns a one-line request into a compact and a full copy-ready prompt, or diagnoses and rewrites the prompt you paste.

    3
    25.0(1)

    Prompt Quality Reviewer

    by Farman J

    Free

    Audits vague prompts and rewrites them into structured, constraint-heavy system instructions for consistent LLM output.

    1
    65.0(1)

    SKILL.md Validator / Linter

    by Rachid Houmayni

    Free

    Free, instruction-only SKILL.md validator/linter. Checks frontmatter, required sections, and common pitfalls. Returns PASS/REVISE/FAIL with fixes.

    1
    55.0(1)

    Self Improving Agent

    by Ignasi

    Free

    Your agent learns from every correction and failed command: verified one-line rules in LEARNINGS.md, applied at session start, pruned and promoted to CLAUDE.md/AGENTS.md. Never repeats the same mistake twice.

    1
    75.0(1)

    Skill Finder: Find & Install the Right Skill

    by Ignasi

    Free

    Finds the best existing skill for any task: checks installed skills, searches directories and GitHub, ranks by fit, quality, maintenance and safety, then installs it in the right folder for Claude Code, Codex, Cursor or Gemini CLI.

    1
    75.0(1)

    💻 Git Commit & PR Writer

    by WoW MCP

    Free

    Turn Code Changes into Clean, Professional Git Output. Automate Conventional Commits and structured PR descriptions from git diffs.

    1
    35.0(1)

    forgeagent architect

    by Aken

    Free

    Architect and security-audit production-grade Claude agents and MCP servers with enterprise guardrails.

    1
    53.0(1)