gm3dmo/the-power/run-script
Claude Code and agent skill by gm3dmo/the-power
- community
Checking that the SKILL.md file is still in the repository.
Execute any the-power script with guided parameter input. Covers prerequisites, working directory, output interpretation, HTTP status codes, error patterns, and debugging techniques.
Install
npx vskill@latest install gm3dmo/the-power/run-scriptSKILL.md
Run Script
Execute scripts from the-power and interpret their output.
Working directory
All scripts must be run from the root of a the-power repository clone (the directory containing build-testcase, configure.py, and .gh-api-examples.conf).
Find an existing clone:
Prerequisites
- `.gh-api-examples.conf` must exist. Generate with
python3 configure.py. - Required tools:
jq,curl,python3,bash5.x. - A valid PAT configured in
.gh-api-examples.conf.
Before running
Verify the target org is accessible:
If it returns 404, either create the org first (see create-test-org) or use build-all.sh.
How to run
Orchestrated testcases
Individual scripts
Most scripts accept an optional positional argument to override the default resource name:
Understanding output
Success indicators
| HTTP status | Meaning | |
|---|---|---|
| 200 | Retrieved or updated successfully | |
| 201 | Created successfully — look for html_url in the response | |
| 204 | Deleted successfully (no content) |
Failure patterns
| HTTP status | Meaning | Common cause | |
|---|---|---|---|
| 401 | Unauthorised | Token expired, invalid, or missing | |
| 403 | Forbidden | Token lacks required scopes | |
| 404 | Not Found | Resource does not exist, or token cannot see it | |
| 422 | Validation Failed | Payload malformed or resource already exists |
Example error
Verifying results
Debugging
Inspect JSON payloads
Scripts write request bodies to tmp/ before sending:
Verbose curl
Set curl_custom_flags to -v for HTTP debugging:
Base64 encoding
Always use `python3 base64encode.py` for base64 encoding. Never use the native base64 CLI tool — it behaves inconsistently across platforms.
Error handling
- If a script fails silently, check
tmp/for the JSON payload. - If curl returns an empty response, check
curl_custom_flagsincludes
--fail-with-body.
- For SSL errors on GHES, see the
troubleshootskill.
Boundaries
- Do not run destructive scripts (
delete-*,suspend-*) without
explicit user confirmation.
- Do not display the full GITHUB_TOKEN. Show only the first 8 characters.
- Do not modify `.gh-api-examples.conf` directly unless asked.
Use python3 gh-set-value.py to change individual values.
- Always confirm the target instance before running scripts that
create or delete resources.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcopilot-plugin/skills/run-script/SKILL.md
Popularity
- Repository stars
- 216
- Repository forks
- 46
- 7-day trend score
- 27
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 28 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/gm3dmo/the-power/run-script)