Install
$ agentstack add skill-shaishavmaisuria-research-paper-lifecycle-skills-render-workspace-html ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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):
`` python3 scripts/build_dashboard.py --workspace paper-workspace ` It reads paper-workspace/INDEX.md and the stage folders (and .paper-memory/profile.yml for the title/venue if present) and writes paper-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](../paper-profile/references/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.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ShaishavMaisuria
- Source: ShaishavMaisuria/research-paper-lifecycle-skills
- License: Apache-2.0
- Homepage: https://shaishavmaisuria.github.io/research-paper-lifecycle-skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.