New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Commit

by benoror in benoror/obsidianos_work

Stage and commit with flexible intent parsing. An agent skill from benoror/obsidianos_work.

MITAuto-check: notesDevelopment

Install Commit

skills CLI
$ npx skills add benoror/obsidianos_work --skill commit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install benoror/obsidianos_work commit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/benoror/obsidianos_work.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/commit .claude/skills/commit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
commit
GitHub stars
165
Token cost
~1.4k tokens
SKILL.md length
731 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

Stage and commit with flexible intent parsing. An agent skill from benoror/obsidianos_work.

  • Works in 6 steps: Gather state → Determine file set → Stage files → …
  • Development work in your project
  • SKILL.md covers Usage, Argument Parsing, Workflow and Amend Safety, plus 2 more sections
  • Calls git

What it does

Commit is an agent skill from benoror/obsidianos_work. Stage and commit with flexible intent parsing. Accepts file/folder scope, free-text description, amend, or any combination.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. It works with Git. The repository describes itself as: ObsidianOS - Work Vault. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/commit”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather state
  2. Determine file set
  3. Stage files
  4. Craft the commit message
  5. Present and confirm
  6. Commit

What it can do on your machine

Read from SKILL.md and the folder at commit 3c7923e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Commit loads about 1.4k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 731 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:127
    mmit files that likely contain secrets (`.env`, credentials, tokens).

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from benoror/obsidianos_work at commit 3c7923e, republished under its MIT licence (© benoror). 731 words, ~1,374 tokens.

Download SKILL.mdSave it as .claude/skills/commit/SKILL.md (or your agent's skills folder).
name
commit
description
Stage and commit with flexible intent parsing. Accepts file/folder scope, free-text description, amend, or any combination.
license
MIT

Commit

Usage

CommandWhat it does
/commitCommit staged files; if none staged, infer related changes
/commit <file>Scope to a specific file's changes
/commit <folder>/Scope to a folder's changes
/commit <description>Infer scope from free-text intent
/commit <scope> <description>Scope + explicit intent
/commit amendAmend the last commit (re-use message)
/commit amend <scope/description>Amend with additional scope or new message
(sequence mode)Deferred — sub-skills skip, caller commits once at the end

Argument Parsing

Parse the raw argument string into scope, intent, and flags:

  1. Amend flag: If the first word is amend, set amend mode and strip it. The remainder is parsed normally.
  2. Scope (file or folder): Any token that matches a real path in the repo (file or directory) — whether provided via @-reference or plain text. Multiple scopes are allowed.
  3. Intent (free-text description): Whatever remains after extracting scopes. Used to guide the commit message.
  4. Nothing: No arguments at all — default mode.

Examples:

InputScopeIntentAmend
(empty)——no
Meetings/Engineering/Meetings/Engineering/—no
.gitignore.gitignore—no
my awesome refactor—my awesome refactorno
Meetings/ wrap up notesMeetings/wrap up notesno
amend——yes
amend .obsidian/.obsidian/—yes
amend fixed typo—fixed typoyes

Workflow

1. Gather state

Run in parallel:

  • git diff --staged --stat — staged changes
  • git diff --stat — unstaged changes
  • git status --short — untracked files
  • git log --oneline -5 — recent commits (for style and amend safety)
2. Determine file set

Resolve which files will be committed, based on parsed arguments:

ScenarioFile set
Scope providedOnly changed/untracked files under the given path(s). Ignore everything else.
Intent provided, no scopeAnalyze all changed files; select only those whose diffs relate to the described intent. Present the selection for confirmation.
No args + staged files existUse exactly what's staged. Do NOT add unstaged files — the user intentionally staged those.
No args + nothing stagedAnalyze all changed/untracked files. Group related changes and propose a sensible set. Ask for confirmation.

If nothing matches (no changes in scope, or no related files for intent), tell the user and stop.

3. Stage files
  • If the file set is already fully staged, skip.
  • If unrelated files are staged, unstage them first (git restore --staged <path>).
  • Stage the resolved file set with explicit paths — never broad patterns.
4. Craft the commit message

Analyze the staged diff (git diff --staged) and write:

  • Title: ≤72 chars, conventional format — type: summary.
    • Common types: add (new files), update (modify existing), fix (corrections), chore (config/tooling), feat (new capability), refactor, docs, rename.
  • Body (optional): 1–3 lines explaining "why" if not obvious. Omit for trivial changes.
  • If the user provided intent, use it to guide the message but still ground it in the actual diff.
Show full SKILL.md (285 more words)Show less
5. Present and confirm

Show:

  • The list of files that will be committed (or amended).
  • The proposed commit message.

Wait for user confirmation before proceeding.

6. Commit
  • Normal mode: git commit with the confirmed message.
  • Amend mode: git commit --amend (see safety rules below). If the user provided new intent, replace the message; otherwise keep the existing message (--no-edit).

Do not push.

Amend Safety

Before amending, verify ALL of these conditions:

  1. HEAD was created by you in this conversation — check git log -1.
  2. HEAD has not been pushed — git status should show "Your branch is ahead" or the commit should not exist on the remote.
  3. The user explicitly said amend.

If any condition fails, refuse and explain why. Suggest creating a new commit instead.

Sequence Mode

When called as part of a sequenced workflow (e.g. /meeting wrap), the caller owns the commit. Individual sub-skills skip their commit step.

How to detect: the calling workflow explicitly states it is running sub-skills in sequence. Do not offer to commit — just proceed. The sequence owner commits once at the end with a combined message.

Sub-skill commit format

When committing on behalf of a sequence:

  • Message: update: /{workflow-name} {argument} (e.g. update: /meeting wrap Meetings/Engineering/Some Meeting.md).
  • Stage only files modified by the current skill invocation (or full sequence). Use explicit paths.
  • Present and confirm before committing.

Important Notes

  • This workspace may not be a git repo. If git status fails, skip entirely without error.
  • Always use explicit file paths for staging — never broad patterns.
  • If no files were actually modified, skip the commit offer.
  • Never commit files that likely contain secrets (.env, credentials, tokens).
  • When the scope is a folder, include all changed files recursively under it.

© benoror, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/commit of benoror/obsidianos_work.

Open the folder on GitHubat commit 3c7923e

Compare with similar skills

Commit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Commit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Commit this skillbenoror/obsidianos_work165—~1.4kAutomated safety check: NotesMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything86k1 repos~1.2kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Codebase Knowledge Graph Q&A

    Egonex-AI/Understand-Anything

    Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.

    86k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed

  • Code Design Rationale Investigator

    cursor/plugins

    Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Understand Explain

    Egonex-AI/Understand-Anything

    Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.

    86k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

More from benoror/obsidianos_work

All 18 skills in this repo

  • Qmd

    benoror/obsidianos_work

    Search vault notes by keyword or meaning. An agent skill from benoror/obsidianos_work.

    165 GitHub stars~858 tokensUpdated 3 mo ago
    Auto-check passed

  • Cache Notes

    benoror/obsidianos_work

    Fetch & embed AI transcripts as Obsidian callouts. An agent skill from benoror/obsidianos_work.

    165 GitHub stars~2.7k tokensUpdated 3 mo ago
    Auto-check passed

  • Fill Participants

    benoror/obsidianos_work

    Resolve and fill Participants frontmatter + link unlinked names in body.

    165 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed

  • Followup Todos

    benoror/obsidianos_work

    Extract action items as plain markdown bullets (with confirmation).

    165 GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed

  • Last 1on1

    benoror/obsidianos_work

    Show when you last had a 1:1 with each direct report / peer, sorted by recency.

    165 GitHub stars~732 tokensUpdated 3 mo ago
    Auto-check passed

  • Mail Transcripts

    benoror/obsidianos_work

    Gmail AI transcript notifications → meeting Notes: URLs + mark read.

    165 GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about Commit

What does Commit do?

Stage and commit with flexible intent parsing. An agent skill from benoror/obsidianos_work. Commit is an agent skill from benoror/obsidianos_work. Stage and commit with flexible intent parsing.

When should I use Commit?

Commit fits situations like: development work in your project.

How do I install Commit in Claude Code?

Run `npx skills add benoror/obsidianos_work --skill commit -a claude-code`. Or copy the skill folder (.agents/skills/commit in benoror/obsidianos_work) into .claude/skills/commit in your project. Claude Code loads it when a task matches its description.

How do I install Commit in Codex?

Run `npx skills add benoror/obsidianos_work --skill commit -a codex`. Or copy the skill folder (.agents/skills/commit in benoror/obsidianos_work) into .agents/skills/commit in your project. Codex loads it when a task matches its description.

Can I use Commit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add benoror/obsidianos_work --skill commit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/commit, .gemini/skills/commit, .github/skills/commit and .opencode/skills/commit in your project.

What does Commit need to run?

Going by SKILL.md and its folder, Commit needs the command-line tools its instructions call (git).

Does Commit access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Commit safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Commit use?

Commit is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Commit use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Commit?

Skills that share tags, products or a category with Commit: Finishing a Development Branch (obra/superpowers, 296k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 86k stars) and Code Design Rationale Investigator (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Commit?

benoror (a GitHub user) maintains it in benoror/obsidianos_work, which has 165 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on June 11, 2026.

Source: benoror/obsidianos_work on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.