Collection of 21 Claude Skills for Prompt Optimisation and Workflow Control

X postRuben HassidResource

Ruben Hassid has released a library of 21 pre-configured Claude Skills designed to counter common model quirks and inefficiencies. The slash commands address tasks ranging from clarifying vague instructions to automated fact-checking and text editing.

Key points

  1. A Claude Skill acts as a modular prompt activated via slash commands directly within chat conversations.
  2. The /grill-me command responds to vague requests by asking 10 to 15 clarifying questions to establish proper context.
  3. Other tools include /Prompt-maker for structured Claude Fable 5 prompts, /humanizer to remove AI writing tells such as em-dashes, and /fact-checker for self-auditing claims.
  4. According to Hassid, Claude reads only the three-line header of each Skill until called, keeping baseline token consumption low.
  5. Skills are installed in Claude via Settings and Capabilities by uploading the downloaded configuration files.

Why it matters

Standardised skill shortcuts reduce repetitive prompt engineering. They allow professionals to trigger structured workflows instantly, mitigating common issues such as poor input context or overly generic model answers.

Analysis

Hassid's setup illustrates how modular shortcuts turn natural language chats into structured tools. By treating prompts as reusable slash commands, users can standardise tasks like iterative questioning or editing. The /grill-me workflow specifically targets the primary failure mode of conversational models: insufficient context provided in the initial user query.

Original post

Ruben Hassid

@rubenhassid · 1 September 2026

Claude is brilliant & 'very annoying' at the same time. To fix the annoying side of Claude, I built 21 Claude Skills for free: (Very long caption → go to t.co/Q6hsKOpV25, instead. See what I did there?) > Very vague requests → /grill-me Claude will prompt you with t.co/GdSm3hvV1q t.co/sQ5vuv4n8A

152 likes8 replies305 bookmarks20.6k views

View on X
More posts in the thread (1)
  1. @ElSkib1di sent it earlier :)
Selected replies (5)
  • @ElSkib1di @rubenhassid hey, I dmed you but never got the grok code
  • @0xTreff @rubenhassid 21 skills is a lot to install Most people wont use more than a few
  • @itsthedonhashim @rubenhassid @rubenhassid haha this is genius. little tweaks like these make a huge difference! gonna give it a spin.
  • @neatpromptsai @rubenhassid I’m slowly realizing that the biggest bottleneck with LLMs is the quality of user input.
  • @bygregorr @rubenhassid the vague-request fix is real. the one that still costs me hours is claude citing a deprecated package with full confidence like it shipped yesterday. no skill on earth patches model overconfidence.

Mentioned links

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Video

    Video:Hyperautomation Labs

    How Anthropic Employees Use Claude Skills and How to Build Them

    Anthropic employees use standardized Claude Skills rather than ad-hoc prompting for recurring internal workflows. The video examines examples from Anthropic's finance and legal teams, explains the progressive disclosure loading mechanism, and details how to build a skill in Claude Code or claude.ai.

    AI & LLMs· Tutorial

  • Article:Anthropic

    Creating Custom Skills for Claude: Structure, Recording, and Best Practices

    Anthropic details how to build, structure, and test custom skills for Claude. Skills augment the assistant with specialised domain knowledge or repeatable workflows, created either manually via a skill.md file or generated from screen recordings on macOS.

    AI & LLMs· Tutorial

  • Repository:anthropics/skills

    Anthropic Skills: Reference Repository and Specification for Claude Agent Skills

    Anthropic provides a public repository containing example skills, templates, and specifications for Claude's Agent Skills standard. Skills package instructions, scripts, and resources inside folders with a central SKILL.md file to enable repeatable workflows ranging from document generation to technical testing.

    174.3kstarsPython

    AI & LLMs· Resource

  • Video

    Video:CURT

    Anthropic's Ten Updated Rules for Building Claude Skills

    Jay (RoboNuggets / CURT) breaks down ten new best-practice rules from Anthropic's updated guide for building Claude skills with modern models such as Claude 5.5, highlighting modular context structure, token efficiency, and deterministic guardrails.

    AI & LLMs· Tutorial

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.