JetXu-LLMJetXu-LLM/DocMason/skills/optional/public-sample-workspace/SKILL.md

public-sample-workspace

Skill152 starsChanged 4 months agoApache-2.0View on GitHub

Materialize the tracked ICO + GCS public sample corpus into live original_doc/ for contributor testing inside the canonical source repo.

In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adapter-syncSkill
- askSkill
- grounded-answerSkill
- grounded-compositionSkill
- knowledge-base-syncSkill
- knowledge-constructionSkill
- provenance-traceSkill
- retrieval-workflowSkill
- runtime-log-reviewSkill
- validation-repairSkill
- workspace-bootstrapSkill
- workspace-doctorSkill
- workspace-statusSkill
- operator-evalSkill

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Use this skill only when the user explicitly wants a local demo workspace built from the tracked public sample corpus in the canonical …
line 8
Distinctive:
If the current environment cannot inspect or modify the local workspace, stop and explain the blocker.
line 25
Very specific:
If original_doc/ is non-empty and the user did not explicitly ask to replace it:
line 32
Distinctive:
ask for explicit confirmation before overwriting them
line 35
Very specific:
If original_doc/ is empty, or the user explicitly asked to replace it, run:
line 36
Very specific:
Add --force only when the user explicitly asked to replace existing live corpus files.
line 38
Very specific:
Add --prepare only when the user explicitly asked to bootstrap the workspace immediately after materialization.
line 39
Very specific:
Add --sync only when the user explicitly asked to build or refresh the knowledge base immediately after materialization.
line 40
Very specific:
After success, summarize that the tracked public sample corpus was copied into live original_doc/ and note whether bootstrap or sync also …
line 41
Very specific:
Do not overwrite a non-empty original_doc/ silently.
line 45
Distinctive:
Do not run bootstrap or sync as a side effect unless the user asked for it.
line 46
Distinctive:
If the tracked preset is missing, stop and report that this checkout does not expose the public sample workspace helper.
line 47

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Public Sample Workspace

Use this skill only when the user explicitly wants a local demo workspace built from the tracked public sample corpus in the canonical source repository.

This is contributor-oriented setup help. It should not replace the clean or demo release-bundle onboarding paths.

Activation

This optional skill is intended to be exposed only when the canonical source repo contains the tracked ICO + GCS sample preset.

Required Capabilities

local file access
shell or command execution
ability to inspect whether original_doc/ already contains user files

If the current environment cannot inspect or modify the local workspace, stop and explain the blocker.

Procedure

Confirm that the current repository contains the tracked public sample preset.
Inspect original_doc/ for visible user files before copying anything.
If original_doc/ is non-empty and the user did not explicitly ask to replace it:
- stop
- explain that live corpus files already exist
- ask for explicit confirmation before overwriting them
If original_doc/ is empty, or the user explicitly asked to replace it, run:
- python3 scripts/use-sample-corpus.py --preset ico-gcs
Add --force only when the user explicitly asked to replace existing live corpus files.
Add --prepare only when the user explicitly asked to bootstrap the workspace immediately after materialization.
Add --sync only when the user explicitly asked to build or refresh the knowledge base immediately after materialization.
After success, summarize that the tracked public sample corpus was copied into live original_doc/ and note whether bootstrap or sync also ran.

Escalation Rules

Do not overwrite a non-empty original_doc/ silently.
Do not run bootstrap or sync as a side effect unless the user asked for it.
If the tracked preset is missing, stop and report that this checkout does not expose the public sample workspace helper.

Completion Signal

The workflow is complete when the public sample corpus has been copied into live original_doc/, or when a clear overwrite/missing-preset blocker has been surfaced.

Notes

The tracked sample corpus is a contributor and demo fixture, not the normal writable user corpus boundary.
The direct non-agent equivalent is python3 scripts/use-sample-corpus.py --preset ico-gcs.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free