Prompt Dataset Builder
by Edric Vale
Build and curate high-quality prompt datasets for fine-tuning and eval — deduped and labeled.
Skills for writing better prompts, structuring context, and authoring SKILL.md files that agents follow reliably. Turn vague instructions into repeatable behaviour.
383 skills · page 1 of 16
by Edric Vale
Build and curate high-quality prompt datasets for fine-tuning and eval — deduped and labeled.
by Matthew King
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.
by Roy Yuen
A high-precision pre-coding gate that detects conflicting requirements and prevents agents from making wrong assumptions.
Write a portable SKILL.md in five phases, from purpose through Agensi packaging.
by WoW MCP
Enforce rigorous fact-checking, confidence scoring, and risk-based human gates to eliminate AI hallucinations.
by Shandra
Converts Custom GPT instructions, prompt systems, and agent ideas into structured, premium SKILL.md files for AI agent marketplaces.
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.
by HashLips
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.
by HashLips
A Markdown formatting and sanitization skill that cleans up structure, syntax, spacing, headings, lists, and document layout while preserving the original meaning and requirements.
by Ignasi
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.
Picks the right Claude model (Haiku, Sonnet, Opus or Fable) and effort level for each task, so you spend fewer tokens without losing quality.
Finds, organizes, and analyzes useful 3D references for modeling, texturing, and VFX work.
by Ignasi
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.
by Ignasi
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.
Prepare marketplace-ready prompt listings that pass review by enforcing variety rules and avoiding similarity declines.
by Eoghan Henn
The meta-skill that builds and improves all your skills, including itself.
by Joeri Brons
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.
Turns a one-line request into a compact and a full copy-ready prompt, or diagnoses and rewrites the prompt you paste.
by Farman J
Audits vague prompts and rewrites them into structured, constraint-heavy system instructions for consistent LLM output.
Free, instruction-only SKILL.md validator/linter. Checks frontmatter, required sections, and common pitfalls. Returns PASS/REVISE/FAIL with fixes.
by Ignasi
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.
by Ignasi
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.
by WoW MCP
Turn Code Changes into Clean, Professional Git Output. Automate Conventional Commits and structured PR descriptions from git diffs.
by Aken
Architect and security-audit production-grade Claude agents and MCP servers with enterprise guardrails.