skills/pr-merge-temporal/SKILL.md
Merge multiple PRs into a temporal integration branch before merging to base, with ordered conflict resolution. Use when you want to validate a set of PRs together on a staging branch before advancing the base branch.
npx skillsauth add outlinedriven/odin-codex-plugin pr-merge-temporalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Merge multiple PRs into a temporal integration branch for validation before merging to base.
Detect base branch: Identify the default branch via git remote show origin or repo conventions.
Enumerate PRs: List all PRs to merge. For each, fetch the latest HEAD.
Create temporal branch: Fetch latest and branch from the remote base tip.
git fetch origin
git checkout -b temporal/<timestamp> origin/<base>
Determine merge order:
Sequential merge with conflict handling — for each PR in order:
a. Attempt git merge --no-ff <pr-branch> into the temporal branch.
b. If merge succeeds cleanly, continue to next PR.
c. If conflicts occur:
difft and codebase context.git merge --abort), stop, and report the conflict with both sides and a recommended resolution.
d. After each successful merge, run available build/test commands to catch regressions early.Validate temporal branch: Once all PRs are merged, run full build/test suite if available.
Report results: Present the validated temporal branch to the user. Do NOT merge into base automatically — only advance base if the user explicitly requests it.
Abort conditions — stop the queue and report if:
git checkout <base> — base remains untouched.Report for each PR: merged successfully, conflicts resolved (with details), or blocked (with reason). Include the temporal branch name for user review.
testing
ODIN's compress-operations dispatcher under the Compressor/Extender role. Invoke on "tidy", "clean up", "tidy this file/memory/workspace/git/docs", or when active context (current file, diff, stack, memory directory) has structural rot to resolve before touching behavior. Detects target domain from context and routes to the sibling skill. Requires explicit target or clear active-context signal — do not invoke speculatively.
development
Cross-domain taste skill — apply distinctive judgment to any artifact (prose, code, design, decisions) instead of converging to AI defaults. Two modes — `audit` (judge work against the two-sided charter and portable anchors) and `anchor` (load register before producing). Auto-detects by phrasing; override via `/taste audit | anchor`. Trigger on "is this slop?", "overkill?", "elegant?", "taste-test this".
tools
One-shot bootstrap of strict-mode tooling per ecosystem plus per-task GOALS.md scaffolding so an agentic loop can self-verify. Writes typechecker/linter/schema-validator config for TS (strict + noUncheckedIndexedAccess + exactOptionalPropertyTypes), Python (Pyright strict, Ruff strict), Rust (Clippy deny-correctness), Go (golangci-lint with staticcheck), OCaml (dune --release); establishes `.agent-tasks/<id>/GOALS.md` per-task convention distinct from project-stable AGENTS.md. C++/Java/Kotlin and framework specifics (Spring Boot, Nest, React-strict) are out of scope. Trigger on new project bootstrap, agentic-task setup, "make this self-verifying", "set the loop's goal", "scaffold goals for this issue". Pairs with `llm-self-loop` runtime.
tools
Install git pre-commit hooks via the project's hook tool — Husky+lint-staged (JS), pre-commit (Python/OCaml), lefthook (Go), cargo-husky (Rust). Use when the user wants commit-time formatting, linting, type-checking, or test gates. Detects ecosystem first.