papermill/skills/status/SKILL.md
Display a read-only dashboard for paper project status: stage, thesis, experiments, review history, venue, and suggested next action. Reads .papermill/state.md.
npx skillsauth add queelius/claude-anvil statusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Present a concise project status dashboard for an academic paper managed by Papermill. This skill is read-only -- it does not modify any files.
Read .papermill/state.md from the repository root (Read tool).
If the file does not exist, stop and display:
No
.papermill/state.mdfound in this repository. Run/papermill:initto set up Papermill for this project.
Do not proceed further if the file is missing.
The file has YAML frontmatter (between --- delimiters) and a markdown body below it. Parse both. The frontmatter contains structured project metadata. The body contains freeform notes and activity logs.
Display a dashboard with the following sections, using the exact headers shown. For any section where data is absent or empty in the frontmatter, show the fallback text indicated.
Show the current stage value with a brief one-line description:
If no stage is set, show: "No stage set. Run /papermill:init to configure."
Show the thesis.claim and thesis.novelty fields. Format as:
Claim: [claim text] Novelty: [novelty text]
If the thesis fields are empty or not defined, show: "Not yet defined. Run /papermill:thesis to develop your central claim."
Show a summary from the prior_art fields:
key_references (e.g., "12 key references")last_survey dategaps textIf no prior art data exists, show: "No survey yet. Run /papermill:prior-art to begin."
If experiments contains entries, display a markdown table:
| Name | Type | Status | Last Run | |------|------|--------|----------| | ... | ... | ... | ... |
If the experiments list is empty, show: "None registered."
Show a summary from review_history:
If no reviews exist, show: "No reviews yet."
Show the venue.target field. If not set, show: "Not yet selected."
If venue.candidates has entries, list them as bullet points.
If related_papers contains entries, display a markdown table:
| Project | Relationship | Description | |---------|-------------|-------------| | ... | ... | ... |
Where Project is the last path component of path (e.g., masked-causes-in-series-systems), Relationship is the rel value, and Description is the label.
If the related_papers list is empty or missing, show: "None linked. Run /papermill:init with refresh to discover related projects."
Based on the current project state, suggest exactly one next skill to run. Evaluate the conditions in order and use the first match:
/papermill:thesis to define your research claim."/papermill:prior-art to survey related work."## Outline section and the stage is before outlining --> "Consider running /papermill:outline to structure the paper."drafting and there is written content --> "Consider running /papermill:review to get feedback on the current draft."/papermill:review to address open findings."/papermill:polish for final editing, or /papermill:venue to evaluate target venues."Display this under a Suggested next step heading.
Read the last 10 non-empty, non-heading lines from the markdown body of .papermill/state.md (the content below the frontmatter). These typically contain timestamped notes or activity logs.
Display them under a Recent activity heading. If the body is empty or contains no notes, show: "No activity logged yet."
.papermill/state.md or any other file. This skill is read-only.development
Force a research-agent run to conclude. Launches the researcher in synthesis mode: it reads state.md and log.md, writes .research/synthesis.md with outcome, key findings, failed approaches, open questions, and recommendations, then exits. Use when current results are good enough or the agent is stalling.
data-ai
Show the current state of an in-flight research-agent run from .research/state.md, log.md, and attempts/. Read-only summary of cycles, sub-problems, hypothesis statuses, eval trend, and current focus.
testing
Resume an interrupted research-agent run. Re-launches the researcher with instructions to read .research/state.md and log.md, reorient, and continue from the documented current focus. Use after a context compression, session restart, or explicit pause.
tools
When and how to use the repoindex plugin surface (MCP tools, agents, slash commands) for collection queries, release prep, activity summaries, and tag discipline. Use when users ask repoindex questions, mention their repo catalog, or want to know which repoindex tool fits their task.