Claude Skills by Julian0444

Use this skill when the user has a rough idea, wants to explore a feature, or says "let's brainstorm" or "help me design." The goal is to refine an idea into a validated design doc before any code is written.

Use this skill when fixing a bug caused by invalid data reaching deep into execution. The goal is to add validation at every layer the data passes through, making the bug structurally impossible to reproduce.

Use this skill when documentation has drifted from the codebase, needs an inventory, or should be archived.

Autonomous implementation pipeline. Reads a plan file, reviews it adversarially,

Use this skill when ending a session and you want the next session to pick up where you left off. The goal is to capture enough context for seamless session continuity.

---

Use this skill when you have analysis results, review findings, or session insights that need to be converted into an actionable implementation plan. The goal is to transform observations into prioritized, executable tasks.

Use this skill when multiple PRs target the same branch and you need to decide merge order, or when a PR has complex dependencies that affect merge safety. The goal is to classify PRs and produce a priority-ordered merge plan.

Adversarial pre-execution check on a plan file. Run this before execute_plan or manually.

Use this skill when the user has a plan or task description and needs a ticket contract template with deterministic repo detection and YAML output.

Parse a plan file and batch-create Linear tickets — one per `## Task N:` section.

Use this skill when a PR exists but is not yet merge-ready. The goal is to take an open PR through conflict resolution, review feedback, and iterative quality passes until it is clean enough to merge.

Use this skill when reviewing a pull request for merge readiness. The goal is to produce a priority-organized assessment that clearly communicates what must be fixed before merge.

Summarize the current Cursor session inline in chat.

Use this skill when the user is debugging a failure, regression, flaky behavior, traceback, or unclear root cause.

Use this skill when starting feature work that needs isolation from the current workspace, or when you need to work on multiple branches simultaneously. The goal is to create an isolated worktree with a verified clean baseline.

Use this skill when the user has a completed design doc and needs a comprehensive implementation plan with exact file paths, complete code examples, and a TDD approach.