Agent skill
pull
Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.
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/pull
SKILL.md
Pull
Workflow
- Verify git status is clean or commit/stash changes before merging.
- Ensure rerere is enabled locally:
git config rerere.enabled truegit config rerere.autoupdate true
- Confirm remotes and branches:
- Ensure the
originremote exists. - Ensure the current branch is the one to receive the merge.
- Ensure the
- Fetch latest refs:
git fetch origin
- Sync the remote feature branch first:
git pull --ff-only origin $(git branch --show-current)- This pulls branch updates made remotely (for example, a GitHub auto-commit)
before merging
origin/main.
- Merge in order:
- Prefer
git -c merge.conflictstyle=zdiff3 merge origin/mainfor clearer conflict context.
- Prefer
- If conflicts appear, resolve them (see conflict guidance below), then:
git add <files>git commit(orgit merge --continueif the merge is paused)
- Verify with project checks (follow repo policy in
AGENTS.md). - Summarize the merge:
- Call out the most challenging conflicts/files and how they were resolved.
- Note any assumptions or follow-ups.
Conflict Resolution Guidance (Best Practices)
- Inspect context before editing:
- Use
git statusto list conflicted files. - Use
git difforgit diff --mergeto see conflict hunks. - Use
git diff :1:path/to/file :2:path/to/fileandgit diff :1:path/to/file :3:path/to/fileto compare base vs ours/theirs for a file-level view of intent. - With
merge.conflictstyle=zdiff3, conflict markers include:<<<<<<<ours,|||||||base,=======split,>>>>>>>theirs.- Matching lines near the start/end are trimmed out of the conflict region, so focus on the differing core.
- Summarize the intent of both changes, decide the semantically correct
outcome, then edit:
- State what each side is trying to achieve (bug fix, refactor, rename, behavior change).
- Identify the shared goal, if any, and whether one side supersedes the other.
- Decide the final behavior first; only then craft the code to match that decision.
- Prefer preserving invariants, API contracts, and user-visible behavior unless the conflict clearly indicates a deliberate change.
- Open files and understand intent on both sides before choosing a resolution.
- Use
- Prefer minimal, intention-preserving edits:
- Keep behavior consistent with the branch’s purpose.
- Avoid accidental deletions or silent behavior changes.
- Resolve one file at a time and rerun tests after each logical batch.
- Use
ours/theirsonly when you are certain one side should win entirely. - For complex conflicts, search for related files or definitions to align with the rest of the codebase.
- For generated files, resolve non-generated conflicts first, then regenerate:
- Prefer resolving source files and handwritten logic before touching generated artifacts.
- Run the CLI/tooling command that produced the generated file to recreate it cleanly, then stage the regenerated output.
- For import conflicts where intent is unclear, accept both sides first:
- Keep all candidate imports temporarily, finish the merge, then run lint/type checks to remove unused or incorrect imports safely.
- After resolving, ensure no conflict markers remain:
git diff --check
- When unsure, note assumptions and ask for confirmation before finalizing the merge.
When To Ask The User (Keep To A Minimum)
Do not ask for input unless there is no safe, reversible alternative. Prefer making a best-effort decision, documenting the rationale, and proceeding.
Ask the user only when:
- The correct resolution depends on product intent or behavior not inferable from code, tests, or nearby documentation.
- The conflict crosses a user-visible contract, API surface, or migration where choosing incorrectly could break external consumers.
- A conflict requires selecting between two mutually exclusive designs with equivalent technical merit and no clear local signal.
- The merge introduces data loss, schema changes, or irreversible side effects without an obvious safe default.
- The branch is not the intended target, or the remote/branch names do not exist and cannot be determined locally.
Otherwise, proceed with the merge, explain the decision briefly in notes, and leave a clear, reviewable commit history.
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?