mohamedzhioua/agentpace / skills/pace-share
pace-share
VerifiedPreviews the exact agentpace rows a user could contribute to the open dataset. Use only when the user explicitly runs /pace-share or asks to share or contribute their runs. Never start this on your own.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.0 KB |
SKILL.md
View on GitHub---
name: pace-share
description: Previews the exact agentpace rows a user could contribute to the open dataset. Use only when the user explicitly runs /pace-share or asks to share or contribute their runs. Never start this on your own.
license: MIT
compatibility: Requires Python 3.10+ and the agentpace CLI.
---
# Share runs
**Use when** the user explicitly runs `/pace-share` or `/agentpace:pace-share`, or asks to contribute their runs. Never on your own.
**Produces** a dry-run preview of the exact rows and what they reveal. A file in `data/runs` only after the user says yes. Nothing is ever sent.
Sharing is opt-in. Do nothing here unless the user asked for it.
1. Run `agentpace --version`. If it fails, show this command and stop, because installing is the user's call: `uv tool install agentpace`
2. Run `agentpace share --dry-run`. It prints the exact rows and what they reveal, and writes nothing.
3. If it refuses instead of printing rows, with one line starting `agentpace:`, pass that line on as printed and stop: do not go on to `--write`. When the refusal is about the store's idle cap (not the default, not recorded, or a record that cannot be read), rebuilding the store is the user's call: do not rename, delete or edit anything in `~/.agentpace` unless they ask.
4. If it prints `nothing new to share`, every local run is already published; say so and stop.
5. Tell the user how many rows there are, and pass on the notice in full. Offer to show the rows.
6. Stop and ask. Run `agentpace share --write` only after the user says yes to writing the file. It writes into `data/runs` under the current folder, and only inside a clone of the agentpace repo is that the real dataset: there, rows already published are left out and `agentpace validate data/runs` checks the file against every other. Run it from their clone, as CONTRIBUTING describes.
7. `--write` sends nothing. Never run the printed git commands yourself unless the user asks, because pushing publishes the rows, and they cannot be fully recalled after that.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |