shunta-sato

Use when finishing a branch or PR after verification and review, including merge, PR publication, keep, discard, cleanup, local sync, and reporting merge or PR URLs with current git state.

Use when handling received code-review feedback on a PR or diff, including requested changes, inline comments, approvals, non-blocking notes, and disputed suggestions. Separates accepted fixes, refutations, deferrals, clarification needs, and merge handoff.

Use when preparing a focused code-review request for a PR or diff after implementation evidence exists, especially to package scope, reviewer focus, PR URL, verification, known risks, and deferred work without deciding final submit readiness.

Use before every submission to decide whether required checks, artifacts, and branch evidence are complete enough to submit.

Use when work is complex, long-running, multi-step, cross-boundary, likely to span multiple PRs/sessions, or needs handoff-ready planning under plans/.

Use when adding or changing Agent-facing workflows, generated prompts, collect plans, executable handoff artifacts, CLI workflows, controller/target-local workflow chains, or validation artifacts consumed by downstream reports. Do not use for ordinary code changes without an Agent-facing workflow or generated instruction surface.

Use when fixing or investigating crashes, regressions, flakes, hangs, incorrect outputs, or incidents.

Use before feature-level implementation that adds two or more classes/modules, introduces a new layer/interface, or adds a second reason-to-change to an existing class/module. Do not use for function-only helper/API decisions or cross-boundary architecture option comparison.

Create or review structured study notes from narrative, case-based, parable, dialogue, puzzle, or problem-framing sources where the learning unit is misframing → reframing → consequence → reader application. Do not use for ordinary expository textbooks, technical pattern catalogs, or technical essay collections whose primary unit is claim → reasoning → practice/context; use the corresponding textbook or technical-essay workflow.

Create or review structured study notes from technical essay collections, engineering blogs, opinionated practice books, industry criticism, and experience-based software or engineering writing where the learning unit is claim → reasoning → anecdote/context → practice or applicability limit. Do not use for systematic textbook taxonomies or for problem-framing sources whose lesson depends on misframing → reframing → consequence.

Review textbook-style Markdown learning notes for semantic usefulness. Use for concept, method, pattern, antipattern, chapter, and review notes that should explain why an idea matters, when to use it, inputs/outputs, examples, pitfalls, relationships, and self-check prompts. Do not use for narrative problem-framing notes, technical essay notes, Markdown linting, Obsidian link checks, or final pack submission gates.

Final gate for structured study-note packs. In textbook-full-gate mode, verify textbook note-type contracts, deterministic checker results, representative semantic learning quality, tags, wikilinks, corruption scans, and publish/sync readiness. For narrative or technical-essay packs, use only explicit shared-mechanical-only mode after their workflow semantic review; do not apply textbook headings or textbook semantic checks.

Create or refresh structured textbook study notes from books, PDFs, OCR text, or existing Markdown packs. Use for expository or technical textbook sources whose durable learning units are stable concepts, methods, processes, patterns, antipatterns, or chapter-level explanations within a systematic taxonomy. Do not use as the primary workflow for narrative, case-based, parable, dialogue, puzzle, problem-framing, technical-essay, blog, industry-criticism, or argument-first sources; use the corresponding narrative or technical-essay workflow.