Skip to content

panjose/Co-Scientist / skills/skills-codex-entry/co-scientist-dashboard

co-scientist-dashboard

Verified

Resolve dashboard links for one Co-Scientist run from Codex.

FileKindSize
SKILL.mdskill md1.4 KB
---
name: co-scientist-dashboard
description: Resolve dashboard links for one Co-Scientist run from Codex.
---

# co-scientist-dashboard

Goal:

- Resolve the ready dashboard runtime for one run directory and return the current run links to the user.

Expected input:

- one run directory such as `runs/test1`

Execution steps:

1. Run:

   ```bash
   python -m tools.host.project_cli dashboard <run-dir>
   ```

2. Read the CLI JSON result.
3. Read `runs/<run_id>/dashboard/LINKS.md` and `runs/<run_id>/dashboard/LINKS.json` when present.
4. Use the CLI JSON result as the canonical ready-link resolution surface for this run.
5. Return `links.dashboard` as the primary dashboard URL, include the deep links under `links.*`, and point to `runs/<run_id>/dashboard/LINKS.md` as the human-readable dashboard receipt.
6. If `runtime.status` is still `starting`, tell the user that the dashboard is still booting, point them to `runs/<run_id>/dashboard/LINKS.md`, and include the retry command:

   ```text
   $co-scientist-dashboard <run-dir>
   ```

Rules:

- Treat `LINKS.md` as the human-readable receipt and `LINKS.json` as the machine-readable receipt.
- Do not fabricate dashboard URLs when the dashboard runtime is not available.
- This skill is the ready-link follow-up when `start`, `run`, or `resume` only returned background bootstrap status.
- This skill only resolves dashboard runtime availability and exposes run-local links; it must not perform main pipeline reasoning.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall