prompting-fable

prompting-fable is a Prompt design & optimisation skill for AI agents, published by amanaiproduct in the amans-skills repository on GitHub. Skillspace rates prompting-fable D (59/100) and it passed the safety scan; the rating is based on static analysis only.

How to prompt Fable (and other next-generation frontier agentic models) to get outsized results — distilled from Matt Shumer's "How I Prompt Fable." Use when handing a big build/creative/engineering task to a top-tier model, when the user asks "help me write a prompt for X", mentions Fable, /loop, or ultracode, or says "I can't get results like the demos." Shifts prompting from step-by-step instructions to goal + house rules + a hard self-checkable bar + looping.

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
76

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubamanaiproduct/amans-skills

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Prompt design & optimisation

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.