wandb/senpai / plugins/senpai/skills/maintain-research-state
maintain-research-state
VerifiedMaintain and publish the advisor-owned current research state, durable research-ideas syntheses, and dataset analysis. Use when evidence or human guidance changes the research focus or direction, durable research ideas should be recorded, or dataset understanding changes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.0 KB |
SKILL.md
View on GitHub---
# SPDX-FileCopyrightText: 2026 CoreWeave, Inc.
# SPDX-License-Identifier: Apache-2.0
# SPDX-PackageName: senpai
name: maintain-research-state
description: >
Maintain and publish the advisor-owned current research state, durable
research-ideas syntheses, and dataset analysis. Use when evidence or human
guidance changes the research focus or direction, durable research ideas
should be recorded, or dataset understanding changes.
---
# Maintain research state
Use the immutable `program.md` snapshot embedded in your system prompt. It defines
target-specific objectives, metrics, constraints, protected files, and any
baseline or research-log format.
Maintain these advisor-owned artifacts:
- Keep `research/CURRENT_RESEARCH_STATE.md` as a living, pruned view of the
current high-level focus, themes, hypotheses, experiments, and potential next
directions. Do not use it as an archive or experiment-by-experiment log. Use
this schema:
```markdown
# SENPAI Research State
- <current date and time>
- <most recent research direction from human researcher team>
- <current research focus and themes>
- <list of potential next research directions and themes>
```
- Optionally record durable research or round-planning synthesis in
`research/RESEARCH_IDEAS_<YYYY-MM-DD_HH:MM>.md`.
- Save rigorous dataset analysis and durable future dataset insights in
`research/DATASET_ANALYSIS.md`.
Commit only advisor-owned changes. The advisor branch moves whenever an
experiment merges, and those merges happen through the GitHub API rather than
through this checkout, so call `sync_advisor_branch` first. It fetches the
branch, returns its current remote head and leaves your work in place; rebase
local research commits onto `refs/remotes/origin/<advisor branch>` when it has
moved.
Then read the current remote advisor-branch SHA and the local commit SHA, and
call `publish_advisor_branch`:
```json
{
"remote_branch_sha_before_push": "REMOTE_SHA_BEFORE_PUSH",
"local_commit_sha": "LOCAL_COMMIT_SHA"
}
```
Do not publish the advisor branch with `git push`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |