render-workspace-html
Skill59 starsChanged 5 months agoApache-2.0View on GitHub
Renders the paper-workspace (outputs + lifecycle progress) into a single self-contained HTML dashboard the author can open in a browser, and refreshes it on request. Use when a researcher says "show me an HTML view", "give me a dashboard", "can I see my progress in a browser", "visualize what's been done", "make an HTML report", or "update the dashboard". Offered as an option whenever a visual overview would help (it is opt-in, not generated unprompted), and re-run after each significant change so the page stays current. The output is one local dashboard.html with inline CSS — no network, no external assets, light/dark aware — listing every generated artifact by stage with clickable links and a recent-activity timeline. Trigger words - html, dashboard, browser view, visualize progress, html report, update the html.
In this repository43 other files it gives its agents.
- docs/llms-full.txtllms.txt
- docs/llms.txtllms.txt
- add-venue-profileSkill
- anonymize-paperSkill
- assess-paperSkill
- benchmark-paperSkill
- check-originalitySkill
- draft-related-workSkill
- draft-surveySkill
- fetch-paperSkill
- find-papersSkill
- fit-page-limitSkill
- literature-reviewSkill
- make-posterSkill
- make-slidesSkill
- match-styleSkill
- orchestrate-paperSkill
- paper-profileSkill
- parse-cfpSkill
- plan-submissionSkill
- polish-proseSkill
- polish-tables-figuresSkill
- preflight-checkSkill
- prepare-artifactsSkill
- prepare-camera-readySkill
- refactor-research-codeSkill
- refactor-structureSkill
- reflect-and-improveSkill
- reflect-paperSkill
- rehearse-qaSkill
- select-venueSkill
- simulate-reviewersSkill
- study-exemplarsSkill
- tailor-to-venueSkill
- test-research-codeSkill
- triage-reviewsSkill
- verify-citationsSkill
- verify-claimsSkill
- verify-resultsSkill
- work-with-overleafSkill
- write-abstractSkill
- write-rebuttalSkill
- write-talk-scriptSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
After several skills have run and the workspace has enough in it to be worth a glance.
- Distinctive: line 20
Offer, don't impose: If the author hasn't asked, ask once: "Want an HTML dashboard of your progress?
- Distinctive: line 27
Refresh on request: If the author asked to keep it live, re-run step 2 at the end of any request that wrote new artifacts, and say you …
- Distinctive: line 47
Opt-in: Don't generate the dashboard unprompted on every turn.
- Very specific: line 53
At start: read profile.yml for the paper title/venue to label the dashboard.
- Very specific: line 55
Create .paper-memory/ on demand.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Render Workspace HTML
Turns the paper-workspace/ directory into a dashboard the author can open in a browser — lifecycle progress, every generated artifact grouped by stage with clickable links, and a recent-activity timeline. It's the visual "where am I / what's been done" view on top of the files the other skills produce.
This is opt-in: offer it when a visual overview would genuinely help (after a batch of work, or when the author asks), not on every turn. When the author wants it kept live, refresh it after each significant change so it never goes stale.
When to use
- The author asks for an HTML view / dashboard / browser-readable summary of progress.
- After several skills have run and the workspace has enough in it to be worth a glance.
- The author says "keep the HTML updated" — then regenerate it at the end of each request that changed the workspace.
Process
- Offer, don't impose. If the author hasn't asked, ask once: "Want an HTML dashboard of your progress? I can refresh it after each change." Generate only on yes.
- Generate (deterministic):
It readspython3 scripts/build_dashboard.py --workspace paper-workspacepaper-workspace/INDEX.mdand the stage folders (and.paper-memory/profile.ymlfor the title/venue if present) and writespaper-workspace/dashboard.html— one self-contained file, inline CSS, no network or external assets, light/dark aware. Exit 1 only if there is no workspace yet. - Point the author to it (
open paper-workspace/dashboard.html). Summarize what it shows. - Refresh on request. If the author asked to keep it live, re-run step 2 at the end of any request that wrote new artifacts, and say you refreshed it. Otherwise regenerate only when asked again.
Output
paper-workspace/dashboard.html — a stage-by-stage progress bar, artifact cards with links to each output, and a recent-activity timeline from INDEX.md. Opens offline in any browser.
Richer reports
This skill is built for speed and zero dependencies: one self-contained
dashboard.html that works offline and can be refreshed repeatedly. If the
author asks for a more designed or interactive report, and the current agent
runtime has a separate web artifact, frontend, or report-building skill
installed, offer to hand the workspace summary to that tool. Keep this
dashboard as the default status view; use richer builders only when the author
asks for presentation-grade HTML.
Guardrails
- Local only. The dashboard is a local file built from local artifacts; never upload it, host it, or copy it into this skills repo. No third-party paper content is rendered (only the author's own outputs).
- Self-contained, no tracking. Inline CSS only — no external scripts, fonts, images, or analytics.
- Opt-in. Don't generate the dashboard unprompted on every turn; offer it, then refresh per the author's preference.
- It only displays what other skills produced; it never edits artifacts, scores, or the paper.
Memory
Uses the shared .paper-memory/ convention (paper-memory-convention.md).
- At start: read
profile.ymlfor the paper title/venue to label the dashboard; check whether the author opted into auto-refresh. - At end: record the auto-refresh preference (
date · render-workspace-html · auto-refresh on/off) so later runs honor it without re-asking. - Create
.paper-memory/on demand; local-only, never uploaded.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

