push-skills
Push skills and global AGENTS.md to the private repo and verify the public mirror.
Skill by davidondrej
Chalk Labs
Need help deploying push-skills?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/davidondrej-push-skills
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: version-control
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/push-skills
What's inside
- Skill name
push-skills- Description
- Push skills and global AGENTS.md to the private repo and verify the public mirror. Use only when the user explicitly invokes /push-skills.
- License
- MIT
- Instructions
- 83 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Push Skills Canonical repo: `AGENT_REPO`. Private remote: `PRIVATE_REPO`. Pushing `main` triggers the sanitized mirror at `PUBLIC_MIRROR_REPO`; only the configured automation pushes there. Only commit or push when the user requests it. Editing this skill is not permission to publish it. For distributed skill edits, follow `distribute-skill-to-all-agents` before pushing. ## Always include global instructions The user's standing scope for an authorized `/push-skills` run includes saved changes to `GLOBAL_INSTRUCTIONS_FILE`, unless they explicitly exclude that file. Check it on every run, even when the latest message names a skill. Preserve the conversation's original publishing objective through skill edits, renames, and other follow-up requests. After fetching, compare saved `global/AGENTS.md` with `origin/main:global/AGENTS.md`. Local dirt may already be published; Git status alone cannot tell. Transfer new edits while preserving upstream changes. Verify saved global instructions are committed privately and substantive updates appear in public root `AGENTS.md`. Report this separately; successful skill publication does not complete an AGENTS.md request. ## Choose the source file - `GLOBAL_INSTRUCTIONS_FILE` should link to `AGENT_REPO/global/AGENTS.md`. Save the editor buffer and verify the link. If it differs, inspect both files before choosing; do not replace the link or overwrite either file. Public destination: root `AGENTS.md`. - `AGENT_REPO/AGENTS.md` is a separate, private repo-instruction file and stays excluded. - Updating global instructions needs no copy, skill allowlisting, or policy version bump. - Skills live under `skills/<skill-name>/`. Use `publish-skill` for newly public skills; include policy changes in the same commit. ## Prepare without disturbing other work Run Git in `AGENT_REPO` or the temporary worktree below. Check staged and unstaged changes: ```bash git status --short git diff --cached --stat git diff HEAD -- global/AGENTS.md git remote -v git fetch origin main ``` For skills, substitute the intended paths. Confirm `origin` is private. Review outgoing commits as well as files: every commit ahead of `origin/main` will push. - Clean checkout: fast-forward `main` with `git merge --ff-only origin/main`. - Only intended edits pending: commit, then rebase those commits onto `origin/main`. - Unrelated edits, staged files, or local commits: use `git worktree add --detach <temporary-path> origin/main`. Preserve the original checkout and index. Transfer approved changes as a patch against their original base, using three-way application when needed; copy approved new files separately. Preserve newer upstream edits instead of overwriting with an old copy. Resolve conflicts from both versions; ask only when intent is ambiguous. Do not stash, reset, unstage, or commit someone else's work. ## Commit and push Stage only intended paths. Plain `git commit` includes all staged files regardless of the preceding `git add`; use an explicit path list: ```bash git add -- global/AGENTS.md git commit --only -m "Update global agent instructions" -- global/AGENTS.md ``` Adapt paths and message for skills. Review `git show --stat HEAD` and `git diff origin/main..HEAD` before pushing. If nothing needs committing, check whether the intended state is already pushed, then verify it. ```bash git push origin HEAD:main source_sha=$(git rev-parse HEAD) ``` If `main` advanced, fetch, rebase the isolated intended commits, review, and retry. Never force-push. Verify the remote contains the commit instead of relying on push-output labels. Report when a temporary worktree kept the original checkout untouched. ## Verify public publication Find the workflow for the pushed commit; a private push alone does not prove publication: ```bash gh run list --repo PRIVATE_REPO --workflow MIRROR_WORKFLOW \ --commit "$source_sha" --json databaseId,headSha,status,conclusion,url gh run watch <run-id> --repo PRIVATE_REPO --exit-status ``` Wait for the matching run. If superseded, verify the newer source contains your change. The workflow may add an automated sync commit, so public `Source:` can name a descendant of your commit. For failure, cancellation without replacement, or a stall, inspect status/logs and report incomplete publication with the run link. Do not rerun indefinitely. Read the published file and confirm the intended update: ```bash gh api repos/PUBLIC_MIRROR_REPO/contents/AGENTS.md \ -H 'Accept: application/vnd.github.raw' ``` Find skill categories from the committed policy and published tree, then check `skills/<category>/<skill-name>/SKILL.md`. Private-only skills need only private push verification. The mirror may rewrite or omit content; green CI and file existence do not prove correctness. For missing or unexpected content, inspect the matching mirror-report artifact and the mirror tooling documentation. Report exclusions/failures accurately. Never bypass the sanitizer or add manual approval gates. Finish with the private commit, workflow result, and published file link.
From davidondrej/skills, MIT.
More from davidondrej/skills
- 0.819score
bb-cli
davidondrej
Use this when controlling bb.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
domain-checker
davidondrej
Check domain registration in batches using public RDAP APIs, without keys or login.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
reset-cursor-acp
davidondrej
Reset a stuck Cursor ACP thread in your chat app and reload its configuration.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
cmux
davidondrej
Control the cmux macOS terminal app: workspaces, panes, surfaces, browsers, notifications, settings, and hooks.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
kimi-review
davidondrej
Launch an independent Kimi K3.1 Pro Max code review and return it verbatim, falling back across harnesses and routes until one works.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
browser-harness
davidondrej
Direct browser control via CDP.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
cua-driver
davidondrej
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing…
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
persistent-localhost
davidondrej
Manage persistent dev servers, APIs, and other local processes on a port using macOS LaunchAgents.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
deepapi
davidondrej
Use DeepAPI for all web search, deep research, and web scraping (websites, LinkedIn, GitHub, X/Twitter, YouTube, Instagram) instead of built-in search…
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.818score
repo-sync
davidondrej
Manage automatic Git syncing on macOS with repo-sync.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.818score
anti-sleep
davidondrej
Keep a Mac awake for a set duration or while a process runs.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.816score
signal-from-expert
davidondrej
Compare the user's notes with an expert's work on a topic.
SkillAFreshness: A★ 4.2KClaude Code +9
Signals
- Stars
- 4,167
- Forks
- 612
- Open issues
- 0
- Last commit (this folder)
- Oct 18, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/davidondrej/skills
- Website
- www.cloudroom.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from davidondrej
- 0.819score
persistent-localhost
davidondrej
Manage persistent dev servers, APIs, and other local processes on a port using macOS LaunchAgents.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
cua-driver
davidondrej
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing…
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
deepapi
davidondrej
Use DeepAPI for all web search, deep research, and web scraping (websites, LinkedIn, GitHub, X/Twitter, YouTube, Instagram) instead of built-in search…
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
browser-harness
davidondrej
Direct browser control via CDP.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
domain-checker
davidondrej
Check domain registration in batches using public RDAP APIs, without keys or login.
SkillAFreshness: A★ 4.2KClaude Code +9 - 0.819score
reset-cursor-acp
davidondrej
Reset a stuck Cursor ACP thread in your chat app and reload its configuration.
SkillAFreshness: A★ 4.2KClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get push-skills running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
push-skills. Agent Mart. https://agentmart.dev/skills/davidondrej-push-skills (last updated 2026-10-24)