Speq Git Operations logo

Speq Git Operations

Community
marconae
speq-git-operations

The git/gh operation-to-command mapping and return formats — invoked directly by /speq-plan-pr and /speq-implement-pr.

Overview

Publishermarconae
Repositoryspeq-skill
Skill namespeq-git-operations
Stars
54
Forks
10
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by marconae on GitHub. Read the source before you install it.

Installation

Install the Speq Git Operations AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/marconae/speq-skill/tree/main/.claude/skills/speq-git-operations
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/marconae/speq-skill.git /tmp/speq-skill
mkdir -p .claude/skills
cp -r /tmp/speq-skill/.claude/skills/speq-git-operations .claude/skills/speq-git-operations
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Speq Git Operations in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Speq Git Operations on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Speq Git Operations is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Git Operations

This skill documents the git/gh write commands available to speq-plan-pr and speq-implement-pr.

Rules

  • Run one operation at a time. The fixed composite sequences below are the exception.
  • Compose commit messages, PR and issue titles and bodies, and comment text as your own workflow step, before you run an operation.
  • Write commit messages as Conventional Commits. The type spec marks spec changes.
  • Never stage secrets or sensitive information (API keys, passwords, credentials, tokens).
  • Stage only the paths you name. Touch only the refs, PRs, or issues you name.
  • Report a no-op plainly (nothing to commit, PR already exists, already ready). It is not an error.
  • Report ambiguity or a not-found target. Do not guess.
  • Never merge a PR. Never force-push. Never rewrite history (rebase, amend, reset --hard, filter-branch).

create-branch

Params: branch (exact name), base (optional; default: repository default branch). git fetch, then create branch off base and check it out. Returns:

Branch: <branch> (created off <base>)

checkout

Params: target (a branch name, a PR number, #N, or a PR URL). Resolve and check out: PR number/URL → gh pr checkout <target>; a branch that exists locally or remotely → check it out (git fetch first if remote-only). If target matches nothing, report not-found. Create nothing. Returns:

Branch: <branch> (checked out)
PR: <none | #N (draft|ready) — <url>>

commit

Params: paths (files/globs to stage), message (exact commit message). git add <paths>, git commit -m "<message>". Nothing staged or nothing changed is a no-op, not an error. Returns:

Committed: <sha> "<subject>"

or

Nothing to commit

push

Params: none. Pushes the current branch (-u origin <branch> on first push). Returns:

Pushed: <branch>

create-pr

Params: title, body, draft (bool), base (optional; default: default branch), head (optional; default: current branch). If a PR already exists for head, do not recreate it. Return it unchanged. Otherwise gh pr create with the given title and body, adding --draft when draft is true. Returns:

PR: #N (draft|ready) — <url> (created | already existed)

ready-pr

Params: pr (optional; default: PR for current branch). gh pr ready <pr> when it is a draft; no-op if already ready. Returns:

PR: #N (ready) — <url>

comment-pr

Params: pr (optional; default: PR for current branch), body (exact comment text). gh pr comment <pr> --body "<body>". Returns:

Comment: <url>

create-issue

Params: title, body, labels (optional). gh issue create with the given fields. Returns:

Issue: #N — <url>

comment-issue

Params: issue (number or URL), body (exact comment text). gh issue comment <issue> --body "<body>". Returns:

Comment: <url>

read-comments

Params: target (PR or issue number/URL; default: PR for current branch), since (optional ISO timestamp: return only comments and reviews posted at or after it). For a PR, collect all three comment kinds: conversation comments and review summaries (gh pr view --json comments,reviews), and inline review comments on files (gh api repos/{owner}/{repo}/pulls/<n>/comments, which carry path and line). For an issue, gh issue view --json comments. Concatenate each body as plain text with author, timestamp, and for inline comments the file and line. An empty result is valid. Returns:

Comments found: N
<author> @ <timestamp> [<path>:<line> for inline comments]:
<body>
...

or

Comments found: 0

Composite operations

Each composite is one operation with a sequence fixed by this skill. The caller supplies parameters, never the sequence. "Nothing to commit" at the commit step is a no-op: continue with the remaining steps. Stop at the first failing step. Report which steps completed and which step failed.

ship-draft

Params: paths (files/globs to stage), message (exact commit message), title, body. Sequence: commit(paths, message) → push → create-pr(draft: true, title, body). Returns:

Committed: <sha|no-op> / Pushed: <ref> / PR: #<n> (draft) — <url>

ship-ready

Params: paths (files/globs to stage), message (exact commit message), title, body. Sequence: commit(paths, message) → push → create-pr(draft: true, title, body) → ready-pr. Returns:

Committed: <sha|no-op> / Pushed: <ref> / PR: #<n> (draft) — <url> / Ready: true

Frequently asked questions

What does the Speq Git Operations AI skill do?

The git/gh operation-to-command mapping and return formats — invoked directly by /speq-plan-pr and /speq-implement-pr.

Why use Speq Git Operations on TypingMind?

Because you install it once and use it with any model. Speq Git Operations is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Speq Git Operations in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/marconae/speq-skill/tree/main/.claude/skills/speq-git-operations. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Speq Git Operations?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Speq Git Operations?

As many as you like. As long as a model supports skills, you can use Speq Git Operations with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Speq Git Operations AI skill free?

Yes. It is published on GitHub by marconae under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇