Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →huytieu/auto-research
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
Passed 10 of 19 test cases with the skill, and 4 of 19 without it.
and 9 more in the full report
8 fixed4 passed either way9 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
If Phase 1 question decomposition identifies a thread named 'market forces', what exact string is used as the agent name when launching that background researcher?
| Checked | Without skill | With skill |
|---|---|---|
| Names the sub-agent research-market-forces for the market forces thread. | Missed | Passed |
The instructions your model reads when the skill loads.
Inspired by Karpathy's autoresearch — but for strategic thinking instead of ML training.
Check agent_mode in 00-inbox/MY-PROFILE.md frontmatter:
agent_mode: team — use the full parallel agent execution strategy (5-7 agents). This skill benefits massively from team mode.agent_mode: solo — run 2-3 sequential research passes with WebSearch/WebFetch, produce a lighter analysis without the full multi-thread structure./auto-researchThe user provides a strategic question or topic as the command argument. Examples:
Break the user's strategic question into 5-7 research threads that together will provide a comprehensive answer. Each thread should be:
Decomposition framework:
test cases passed, vs 4 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.