Agent skill
push
Push current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request.
Install this agent skill to your Project
npx add-skill https://github.com/ReinaMacCredy/maestro/tree/main/.codex/skills/maestro:symphony-setup/reference/codex-skills/push
SKILL.md
Push
Prerequisites
ghCLI is installed and available inPATH.gh auth statussucceeds for GitHub operations in this repo.
Goals
- Push current branch changes to
originsafely. - Create a PR if none exists for the branch, otherwise update the existing PR.
- Keep branch history clean when remote has moved.
Related Skills
pull: use this when push is rejected or sync is not clean (non-fast-forward, merge conflict risk, or stale branch).
Steps
-
Identify current branch and confirm remote state.
-
Run local validation (
make -C elixir all) before pushing. -
Push branch to
originwith upstream tracking if needed, using whatever remote URL is already configured. -
If push is not clean/rejected:
- If the failure is a non-fast-forward or sync problem, run the
pullskill to mergeorigin/main, resolve conflicts, and rerun validation. - Push again; use
--force-with-leaseonly when history was rewritten. - If the failure is due to auth, permissions, or workflow restrictions on the configured remote, stop and surface the exact error instead of rewriting remotes or switching protocols as a workaround.
- If the failure is a non-fast-forward or sync problem, run the
-
Ensure a PR exists for the branch:
- If no PR exists, create one.
- If a PR exists and is open, update it.
- If branch is tied to a closed/merged PR, create a new branch + PR.
- Write a proper PR title that clearly describes the change outcome
- For branch updates, explicitly reconsider whether current PR title still matches the latest scope; update it if it no longer does.
-
Write/update PR body explicitly using
.github/pull_request_template.md:- Fill every section with concrete content for this change.
- Replace all placeholder comments (
<!-- ... -->). - Keep bullets/checkboxes where template expects them.
- If PR already exists, refresh body content so it reflects the total PR scope (all intended work on the branch), not just the newest commits, including newly added work, removed work, or changed approach.
- Do not reuse stale description text from earlier iterations.
-
Validate PR body with
mix pr_body.checkand fix all reported issues. -
Reply with the PR URL from
gh pr view.
Commands
# Identify branch
branch=$(git branch --show-current)
# Minimal validation gate
make -C elixir all
# Initial push: respect the current origin remote.
git push -u origin HEAD
# If that failed because the remote moved, use the pull skill. After
# pull-skill resolution and re-validation, retry the normal push:
git push -u origin HEAD
# If the configured remote rejects the push for auth, permissions, or workflow
# restrictions, stop and surface the exact error.
# Only if history was rewritten locally:
git push --force-with-lease origin HEAD
# Ensure a PR exists (create only if missing)
pr_state=$(gh pr view --json state -q .state 2>/dev/null || true)
if [ "$pr_state" = "MERGED" ] || [ "$pr_state" = "CLOSED" ]; then
echo "Current branch is tied to a closed PR; create a new branch + PR." >&2
exit 1
fi
# Write a clear, human-friendly title that summarizes the shipped change.
pr_title="<clear PR title written for this change>"
if [ -z "$pr_state" ]; then
gh pr create --title "$pr_title"
else
# Reconsider title on every branch update; edit if scope shifted.
gh pr edit --title "$pr_title"
fi
# Write/edit PR body to match .github/pull_request_template.md before validation.
# Example workflow:
# 1) open the template and draft body content for this PR
# 2) gh pr edit --body-file /tmp/pr_body.md
# 3) for branch updates, re-check that title/body still match current diff
tmp_pr_body=$(mktemp)
gh pr view --json body -q .body > "$tmp_pr_body"
(cd elixir && mix pr_body.check --file "$tmp_pr_body")
rm -f "$tmp_pr_body"
# Show PR URL for the reply
gh pr view --json url -q .url
Notes
- Do not use
--force; only use--force-with-leaseas the last resort. - Distinguish sync problems from remote auth/permission problems:
- Use the
pullskill for non-fast-forward or stale-branch issues. - Surface auth, permissions, or workflow restrictions directly instead of changing remotes or protocols.
- Use the
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
maestro-skill-author
Create, update, or debug maestro built-in skills. Covers SKILL.md frontmatter, reference directory structure, step-file architecture, build-time embedding, naming conventions, alias management, and registry validation. Use when creating a new maestro built-in skill, modifying an existing SKILL.md, adding reference files, debugging skill loading failures, updating the skills registry, or working on the skills full port. Also use when frontmatter validation fails, skills don't appear in skill-list, or reference files fail to load.
maestro:brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
maestro:plan-review-loop
Deep-review any plan (maestro, Codex, Claude Code plan mode, or plain markdown) using iterative subagent review loops with BMAD-inspired adversarial edge-case discovery. Spawns reviewer subagents that find issues using pre-mortem, inversion, and red-team techniques, auto-fixes them with structured fix strategies, and re-reviews until the plan passes with zero actionable issues. Use when the user says 'review the plan', 'deep review', 'check the plan thoroughly', 'review loop', 'validate before approving', or wants rigorous plan validation before execution. Also use proactively before plan-approve when the plan is complex or high-risk.
maestro:research
Structured research workflow for maestro features. Guides tool selection across three tiers (codebase exploration, Context7 for library docs, NotebookLM for deep analysis), defines research patterns, finding organization via memory_write, and completion criteria. Use during the research pipeline stage after feature_create and before plan_write. Also use when investigating a problem space, comparing technical approaches, gathering context on unfamiliar code, or needing to understand external library APIs before making architectural decisions.
cli-for-agents
Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.
Didn't find tool you were looking for?