agentleFS
ldaumeldaume/agentic-engineering-harness/skills/infrastructure/gitea-tea/SKILL.md

gitea-tea

Skill3 starsChanged 3 months agoMITView on GitHub

Uses the tea CLI to inspect and operate Gitea repositories, issues, pull requests, releases, branches, labels, and workflow-adjacent metadata from the terminal. Use when the user mentions tea, gitea cli, terminal-based Gitea operations, PR inspection, issue triage, release checks, or repository automation against Gitea.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    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. Very specific:

    Use this when Gitea state should be inspected or changed through the tea CLI instead of the browser.

    line 8
  2. Very specific:

    Check whether tea is installed and which login/profile is active.

    line 15
  3. Distinctive:

    Read repo remotes and local branch state before inferring owner/repo.

    line 16
  4. Distinctive:

    Prefer read-only commands first.

    line 19
  5. Distinctive:

    Do not print tokens or login config.

    line 21
  6. Very specific:

    Use tea --help and subcommand help for the installed version.

    line 35
  7. Distinctive:

    Always identify the target remote, owner, repo, branch, issue, or PR.

    line 39
  8. Distinctive:

    When multiple remotes exist, ask or use the one documented by the repo.

    line 40
  9. Very specific:

    Prefer tea pulls view plus local git diff/git log before reviewing a PR.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Gitea Tea

Use this when Gitea state should be inspected or changed through the tea CLI instead of the browser.

Project Fit Check

Before running commands:

  1. Check whether tea is installed and which login/profile is active.
  2. Read repo remotes and local branch state before inferring owner/repo.
  3. Confirm destructive actions: close issues, delete branches, edit releases, merge PRs, or change labels.
  4. Prefer read-only commands first; show the target repo and object id before mutating anything.
  5. Do not print tokens or login config.

Common Read Commands

tea repos ls
tea issues ls
tea issues view <id>
tea pulls ls
tea pulls view <id>
tea releases ls
tea labels ls

Use tea --help and subcommand help for the installed version; flags vary.

Operating Rules

  • Always identify the target remote, owner, repo, branch, issue, or PR.
  • When multiple remotes exist, ask or use the one documented by the repo.
  • Prefer tea pulls view plus local git diff/git log before reviewing a PR.
  • For labels and milestones, preserve existing naming conventions.
  • For releases, verify tag existence and changelog source before publishing.
  • For automation, wrap tea in small scripts only when the command is repeated.

Review And Triage Flow

  1. List the relevant issues or PRs.
  2. Open the target item with full metadata.
  3. Cross-check local branch, CI status, and linked issues.
  4. Perform the smallest needed action.
  5. Report the command result and any follow-up state.

Red Flags

  • command would mutate a repo inferred only from the current directory
  • ambiguous login/profile
  • closing or merging without showing target id
  • release creation without checking tag and artifacts
  • automation that assumes one Gitea host across all projects

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.