Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agents-bootstrap
Generate a project-specific AGENTS.md from a user goal, then confirm before overwriting.
Passed 15 of 20 test cases with the skill, and 11 of 20 without it.
and 6 more in the full report
7 fixed9 passed either way3 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm setting up a new Python and FastAPI microservice repository for AI agent assistance. Can you help bootstrap our AGENTS.md file? We use pytest for unit tests, Playwright for e2e tests, PostgreSQL for data, and we need clear repository guidance covering testing strategy, constraints, and operational loops.
| Checked | Without skill | With skill |
|---|---|---|
| Asks the user to reply CONFIRM before writing the file to disk | Missed | Passed |
| Includes a reference to the plan skill for issue and plan generation | Missed | Passed |
| Includes a reference to docs/testing-policy.md in the drafted guidelines | Missed | Passed |
The instructions your model reads when the skill loads.
Generate a concise, project-specific AGENTS.md tailored to the user's goal.
assets/agents-template.md as the base structure.AGENTS.md.AGENTS.md.bak.<timestamp>.docs/mcp-tools.md is missing or stale, instruct to use the mcp-tools-catalog skill before finalizing AGENTS.md.Collect these if not provided:
Ask at most 2 clarification questions, then proceed with stated assumptions. If the task continues across turns, re-invoke this skill to keep the rules active.
The final AGENTS.md must include (when applicable):
plan skill)docs/testing-policy.md)AGENTS.md in chat.test cases passed, vs 11 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.