Install any skill in seconds. Free to start, no credit card required.
Get Started Free →human-agent-society/deep-research
Research the problem domain before coding. Web search for techniques, save raw sources, write structured findings, update the index.
Passed 10 of 16 test cases with the skill, and 6 of 16 without it.
and 9 more in the full report
9 fixed5 passed either way5 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
We just authored a new research note titled `kernel-fusion.md` in `notes/research/`. Which script and parameter should be run so that existing notes automatically pick up cross-references to this new file?
| Checked | Without skill | With skill |
|---|---|---|
| Runs resolve_links.py with the --new flag. | Missed | Passed |
The instructions your model reads when the skill loads.
Research the problem thoroughly before writing code. Understand what's known, what's been tried, and what approaches exist.
notes/
├── index.md ← table of contents for research/ and experiments/
├── raw/ ← saved web pages, paper excerpts (immutable, never edit)
├── research/ ← your synthesized findings (link back to raw/)
│ └── _coverage.md ← the research coverage ledger (dimensions × covered/partial/missing)
└── experiments/ ← eval reflections and results (written by reflect heartbeat)
Read the task description and key files. Identify what's being optimized, what the constraints are, and what makes it hard. Check coral log and {shared_dir}/notes/ for prior work.
Then decompose the problem into 4–8 research dimensions — the distinct things a team would need to understand to win this task. Derive them from the task, don't pull them from a fixed list. Useful starting prompts (not a required set): prior art / SOTA methods, mechanism or theory, implementation / libraries, the evaluation & grader surface, failure modes, adjacent fields. Drop the ones that don't apply; add task-specific ones that do.
Record them in the coverage ledger at {shared_dir}/notes/research/_coverage.md — the team's map of what's been researched and what hasn't. If it doesn't exist, create it with every dimension missing; if it does, read it first and target the gaps rather than re-covering what's done:
# Research Coverage — <task name>
<!-- Owned by the research team. Update on every research pass. Dimensions are
derived from THIS task, not a fixed list. Status: covered | partial | missing -->
| Dimension (what to understand) | Status | Note | Last touched |
|---------------------------------|---------|-------------------------------------|--------------|
| Prior art / SOTA methods | missing | — | — |
test cases passed, vs 6 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.