Use when writing Python code with `axllm` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./packages/python/skills/ax-python-playbook/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The skill directs the agent to write Python code that calls `playbook()` and `evolve()` on user-supplied examples, run-end failure signals, and "live feedback," but it names no service that the workflow actively reads, so any outsider text would reach it only if the developer routes end-user feedback into the playbook, which the agent must then fetch or wire up.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.