Prompt Assay
Loading orgs…
PromptsSkillsUsageFeedback
Folders
HelpWhat's new
  1. Help
  2. Skills

Help Center · Skills

Skills

Author SKILL.md bundles, lint and critique against six dimensions, and run multi-provider Behavioral Eval. Import from Anthropic SKILL.md, OpenAI Custom GPTs, or Gemini Gems.

  • 01
    Skills overview
    What a Skill is in Prompt Assay, how it differs from a prompt, and the workbench surfaces that author + critique + evaluate one.
  • 02
    Behavioral Eval guide
    Author trigger + non-trigger probes, run them across 2-5 models in parallel, and read the activation + adherence + cross-provider consistency scores.
  • 03
    README badge
    Embed a Shields.io badge in your skill's README that links to its public Skill Report.
  • 04
    Authoring a Skill from scratch
    Frontmatter contract, body conventions, scripts/ vs references/ vs body, and the common pitfalls that trip the linter on the first save.
  • 05
    Sharing Skill Reports publicly
    What gets published, the body-publish opt-in (authorship-gated), privacy defaults, view counting, revocation, and the carve-out from PA's no-server-side-AI-cache rule.
  • 06
    Tiers, cost, and BYOK for Skills
    Per-tier caps for Behavioral Eval, what each Skill instrument bills your provider, the $5 cost-preflight gate, and how to read the per-skill cost dialog.
← Back to Help Center