create-agent
create-agent is an Agent, team & workflow authoring skill for AI agents, published by aakash1999 in the claude-certified-architect repository on GitHub. Skillspace rates create-agent F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Use this skill when the user wants to scaffold a new Claude-based Python agent — single-agent loops or multi-agent coordinator systems built on the Anthropic SDK. Triggers include "create an agent", "scaffold an agent", "build me an agent that…", "I need a multi-agent system for…". Generates a runnable file that follows the course conventions (haiku-4-5 pin, four-category error schema, end_turn exit, optional coordinator + hooks). Do NOT use for editing existing agents — only for greenfield creation.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 45
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 98 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- High-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
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.