act-as-fable
act-as-fable is an Agent behaviour & coding discipline skill for AI agents, published by ShaftHQ in the SHAFT_ENGINE repository on GitHub. Skillspace rates act-as-fable D (62/100) and it passed the safety scan; the rating is based on static analysis only.
Binding SHAFT methodology: evidence over inference, risk-first planning, small verified increments, empirical verification, outcome-first reporting, full-loop ownership (pr/green/merge), plus enforced skill routing (graphify, test-driven-development, ponytail, shaft-mastery) and Haiku-first delegation tiers. Load at the start of ANY nontrivial task — debugging, features, investigations, reviews — and on "act as fable", "ultracode", "maximum effort", "be comprehensive". If in doubt whether a task qualifies, it does.
- Grade
- D
- Quality
- 62 / 100
- Safety
- Passed
- GitHub stars
- 395
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.
Our review
- Architecture
- 84 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
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
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.