capafy-user

capafy-user is a Skill discovery & installation skill for AI agents, published by Capafy in the Capafy-skills repository on GitHub. Skillspace rates capafy-user F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Capafy platform buyer entry point. Use when the user: (1) searches for tools/Agents that perform a task (e.g., "find an Agent that analyzes TikTok data", "something that writes weekly reports"); (2) places orders, tops up Credits, renews, or manages subscriptions; (3) views orders or rates purchased services; (4) views or manages account info (balance, Profile, spending settings); (5) continues a previously purchased Agent with no local Thin Skill (fallback conversation path); (6) installs a Download Agent package (One-Time Purchase); (7) needs web-only ops like refunds, payment method changes, spending limits, or reporting (redirect only, not handled in-Agent). Skip this Skill if a matching Thin Skill (capafy-agent-*) is already installed locally — route through it instead. Does not handle Agent publishing or developer tools, but detects publish intent and guides the user to install the Publisher Skill.

Grade
F
Quality
45 / 100
Safety
Risky
GitHub stars
28

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.

Our review

Architecture
76 / 100
Maturity
Structured: ships references or scripts
Security scan
High-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • exfiltration language
  • references sensitive credential env
  • accesses sensitive system files
  • 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.