Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/workflows:compound
Document a recently solved research problem to compound methodological knowledge
Passed 13 of 19 test cases with the skill, and 3 of 19 without it.
and 14 more in the full report
13 fixed2 passed either way5 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
When documenting a convergence problem fix under `estimation-issues/`, which specialized reviewer agent should be launched during Phase 3 verification?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns econometric-reviewer as the Phase 3 reviewer agent. | Missed | Passed |
The instructions your model reads when the skill loads.
Pipeline mode: This command operates fully autonomously. All decisions are made automatically.
Coordinate multiple subagents working in parallel to document a recently solved research problem. Creates structured documentation in docs/solutions/ with YAML frontmatter for searchability and future reference.
Captures problem solutions while context is fresh. Uses parallel subagents for maximum efficiency — Phase 1 gathers information, Phase 2 assembles the final document.
Why "compound"? Each documented solution compounds your methodological knowledge. The first time you solve a convergence problem takes hours of research. Document it, and the next occurrence takes minutes. Knowledge compounds.
/workflows:compound # Document the most recent fix
/workflows:compound convergence failure in BLP inner loop # Provide context
/workflows:compound fixed cluster-robust SEs # Brief description
<critical_requirement> Only ONE file gets written — the final documentation.
Phase 1 subagents return TEXT DATA to the orchestrator. They must NOT use Write, Edit, or create any files. Only the orchestrator (Phase 2) writes the final documentation file. </critical_requirement>
<parallel_tasks>
Launch these subagents IN PARALLEL. Each returns text data to the orchestrator.
test cases passed, vs 3 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.