agentleFS
Sign inStart free
Sanix-DarkerSanix-Darker/git-ci-skills/skills/git-ci/SKILL.md

git-ci

Skill0 starsChanged 3 months agoMITView on GitHub

Install, connect, inspect, run, and diagnose private GCI CI/CD controllers over MCP. Use when a user mentions GCI, git-ci, VPS pipelines, workflow runs, job logs, deployment approvals, retries, or rollbacks.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. dmythro/agent-skills★ 7same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 8 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use GCI through its typed MCP tools.

    line 13
  2. Distinctive:

    Ask for the VPS hostname or IP when it is not already known.

    line 18
  3. Very specific:

    Ask for an SSH target such as root@host only if that connection fails.

    line 20
  4. Distinctive:

    Never ask for a private key, passphrase, or service token.

    line 21
  5. Very specific:

    Run scripts/setup.sh --host <host> for a read-only preflight.

    line 22
  6. Very specific:

    Use scripts/verify.sh --ssh-target <target> after setup.

    line 25
  7. Distinctive:

    Read workflow admission and graph before starting a run.

    line 33
  8. Distinctive:

    Ask for missing workflow inputs.

    line 34
  9. Distinctive:

    Use a fresh idempotency key for each intended write operation.

    line 35
  10. Distinctive:

    Follow run state through bounded log pages.

    line 36
  11. Distinctive:

    Never request or reveal secret values.

    line 39
  12. Very specific:

    Read references/mcp-tools.md for the tool contract and references/security.md before granting write scopes.

    line 41

≈ “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

GCI

Use GCI through its typed MCP tools. Never replace a GCI tool with an arbitrary SSH shell command when the tool exists.

Connect

  1. Ask for the VPS hostname or IP when it is not already known.
  2. Try the current SSH user and SSH config first.
  3. Ask for an SSH target such as root@host only if that connection fails.
  4. Never ask for a private key, passphrase, or service token.
  5. Run scripts/setup.sh --host <host> for a read-only preflight.
  6. Show the planned host and client changes before rerunning with --apply.
  7. Let setup configure Codex through codex mcp add; use the generic JSON for other clients.
  8. Use scripts/verify.sh --ssh-target <target> after setup.

Setup is read-only by default. Use --allow-write only after the user asks to run, retry, cancel, approve, or roll back through the agent.

Operate

  1. List projects before selecting one. Do not guess a project ID.
  2. Read workflow admission and graph before starting a run.
  3. Ask for missing workflow inputs.
  4. Use a fresh idempotency key for each intended write operation.
  5. Follow run state through bounded log pages; do not request unbounded logs.
  6. Explain failed admission, approval, runner, or capacity states directly.
  7. Require clear user approval before a deployment rollback or automation change.
  8. Never request or reveal secret values.

Read references/mcp-tools.md for the tool contract and references/security.md before granting write scopes.

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