ワンクリックで
mypac
mypac には ladislas から収集した 24 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Use `uv` for Python workflows in this repo. Use when running Python scripts, adding dependencies, or replacing pip/python/venv commands.
Create a GitHub issue in the current repository with gh. Use when the user wants to capture work as an issue from Pi or through the /ghi command.
Synthesize current context into a structured PRD draft or publishable PRD artifact using a shared template. Use when the user wants a PRD from conversation context, a GitHub issue, or a saved draft path.
Zoom out from an unfamiliar code area and map how it fits into the bigger picture. Use when the user says to zoom out, go up a layer, map an area, or asks how code fits together.
Interact with GitHub using the `gh` CLI. Use when working with GitHub issues, pull requests, workflow runs, or API queries.
Cache and refresh remote git repositories under ~/.cache/checkouts/<host>/<org>/<repo> so future references can reuse a local copy. Use this skill when the user points you to a remote git repository as reference or you encountered a remote git repo through other means.
Review upstream/reference sources against this repository and create GitHub checkpoint issues. Use when checking .pac/upstream-sources.yaml, tracking inspiration drift, or running /pac-upstream-checkpoints.
Review code changes following project review guidelines. Use when the user asks to review code, uncommitted changes, a pull request, a branch comparison, or a specific commit.
Creates a concise handoff document for another Pi session or agent. Use when ending work, switching sessions, pausing multi-step work, or preparing context for a fresh agent.
Run an optional Standards + Spec follow-up review after the default pac-review pass. Use when the user asks for a standards review, spec review, or Standards + Spec review of code changes.
Grill issue-backed work against the codebase and project language, then persist durable outcomes to GitHub issue updates, ADR comments, PRD comments, and sparing CONTEXT.md edits. Use when working from a GitHub issue/PR or when the user wants grilling plus durable notes.
Update the repository CHANGELOG.md for notable changes and release prep. Use when finishing meaningful work that should be recorded before merge or when preparing a release section.
Create, split, or plan git commits that follow this repository's commit workflow. Use when the user asks to commit changes directly, split changes into commits, or make an implementation commit along the way.
Create or refactor a Pi extension safely. Use when starting new extension work, adding helper modules to an existing extension, or colocating tests. Covers layout, modularization, tests, and CI alignment.
Explore ideas, problems, or design options without implementing. Use when the user wants open-ended discovery, codebase investigation, trade-off mapping, or to decide whether work should become a PRD, issue breakdown, grilling session, or implementation task.
Guide pragmatic test-driven implementation through small vertical slices. Use when implementing behavior-changing features or bug fixes, especially when tests, regression coverage, red-green-refactor, tracer bullets, or public-interface testing are relevant.
Break a plan, PRD, or discussion into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when the user wants to convert a plan into issues, decompose a PRD into tickets, or create a set of linked implementation issues with explicit dependencies.
Triage GitHub issues through a pac label-based state machine. Use when reviewing incoming issues, classifying bugs or enhancements, preparing pac:ready_for_agent briefs, or closing pac:wontfix/pac:out_of_scope work.
Run a disciplined diagnosis loop for hard bugs and performance regressions. Use when debugging failures, reproducing bugs, investigating flaky behavior, or diagnosing slow code.
Review a codebase for deepening opportunities using shared architecture vocabulary, then grill a chosen candidate. Use when the user wants architecture improvement ideas, refactoring candidates, or interface-deepening analysis from free text, GitHub issue/PR context, or a todo.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /pac-caveman.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree one question at a time. Use when user wants to stress-test a plan, get grilled on a design, or mentions 'grill me'.
Author, rename, or refactor a Pi skill for this repo. Use when creating a new skill under skills/, renaming one, or updating its structure and references.
Author or update a Pi prompt file for this repo. Use when creating a new slash command or editing an existing prompt in prompts/.