code-unpacked
/code-unpacked
Generuje komplet pięciu formatów objaśniających PR, gałąź, repozytorium lub wybrany kod.
- Autor
- sandoche ↗
- Repozytorium
- agentic-code-unpacked ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 12.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 41
- Skrypty
- 16
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 1
Brak sygnałów. Repozytorium zmienione 12.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
- 16 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.
Skrypty: presentations/code-map/assets/map.js, presentations/code-map/scripts/code-map.mjs, presentations/reverse-design/scripts/reverse-design.mjs, presentations/review-quiz/assets/quiz-runtime.mjs, presentations/review-quiz/scripts/review-quiz.mjs, presentations/walkthrough/assets/walkthrough.js, presentations/walkthrough/scripts/walkthrough.mjs, presentations/xkcd/scripts/xkcd.mjs, runtime/scripts/analy
Co robi i kiedy
Generuje komplet pięciu formatów objaśniających PR, gałąź, repozytorium lub wybrany kod.
Oryginalny opis (EN)
Generate all five Code Unpacked formats for a PR, branch, codebase, or selected code. Use when a complete bundle or all formats are requested.
Jak działa
- Use
- Capture and analyze once
- Generate all five formats
- Return and deliver
Podgląd SKILL.md
--- name: code-unpacked description: Generate all five Code Unpacked formats for a PR, branch, codebase, or selected code. Use when a complete bundle or all formats are requested. metadata: version: "0.3.0" --- # Code Unpacked Produce a walkthrough, reverse-design documents, code map, review quiz, and comics from one source snapshot and one shared analysis. Run the workflow in the current agent; no other installed skills or parallel agents are required. ## Use ```text /code-unpacked pr https://github.com/owner/repo/pull/123 --draft /code-unpacked branch feature/login --base main /code-unpacked codebase /code-unpacked docs auth --files src/auth.ts:10-90,src/session.ts ``` Accept natural-language requests and the harness's native invocation syntax. Interpret PR URLs as `pr`, named branches as `branch`, selected files or pasted code as named `docs`, and the whole current repository as `codebase`. Honor requested quiz length and comic counts/panels. Video is an optional addition only when requested; the normal walkthrough is HTML. ## Capture and analyze once Read the bundled [source and delivery guide](runtime/guide.md) and [shared analysis guide](runtime/references/analysis.md). Resolve `<core>` to this installed skill's `runtime` directory. Capture the target once with its collector, inspect the source, author the shared review analysis, and validate/save it through `analyze`. Reuse an existing capture and analysis only when they match the requested source revision and scope. Use the same saved `context.json`, evidence IDs, and analysis for every presentation. Do not repeat collection or analysis when reading the individual workflows below. If shared source capture or analysis cannot be validated, stop and explain the cause. Dependencies and browsers are set up automatically when needed. ## Generate all five formats The following workflows and renderers are bundled here. For each workflow, `<skill-dir>` means this installed skill's `presentations/<name>` directory, and `<core>` remains the shared `runtime` directory. These instructions override workflow references to capturing source again or looking for sibling skills. | Format | Authoring workflow | | --- | --- | | Walkthrough | [Chapters, source excerpts, and optional video](presentations/walkthrough/references/workflow.md) | | Reverse-design | [Relevant design documents and diagrams](presentations/reverse-design/references/workflow.md) | | Code-map | [Files, functions, relationships, and flows](presentations/code-map/references/workflow.md) | | Review-quiz | [Questions, answers, and recommendations](presentations/review-quiz/references/workflow.md) | | Xkcd | [Storyboards, generated artwork, and transcript](presentations/xkcd/references/workflow.md) | Read each workflow as you reach that format, author its content against the shared analysis, and run its existing renderer with the same `--context` and target `--root`. Render in the order above. Keep content JSON and artifact generation internal; the user should not need to run scripts or prepare inputs. For comics, use an available image-generation tool and inspect the complete artwork. Initial rendering without artwork saves prompts and returns an incomplete result; this is an expected preparation step. If image generation is unavailable, preserve those prompts and the storyboard and report comics as incomplete. Continue producing all other formats. Catch failures per format, preserve completed outputs, and continue with the remaining formats. If requested video cannot be exported, retain the HTML walkthrough and report the video failure separately. Do not label a previous run's artifact as a current success: check the renderer result and its manifest against this run's shared context. ## Return and deliver Return one concise list of the five results with usable artifact links and statuses: complete, partial, incomplete, or failed. Explain missing capabilities briefly. Outputs retain their existing `.code-unpacked/<scope>/<format>/` locations and per-format manifests; do not create a new artifact schema or claim incomplete comics are complete. For PRs, prepare each format's existing draft comment and attachment workflow. Post only when the user requested live delivery, and only post complete, publishable outputs. `--draft` always stays local. Missing GitHub or browser-upload access preserves local results and is reported separately from generation status.
Pliki w paczce (41)
- SKILL.md 4 KB
- agents/openai.yaml 1 KB
- presentations/code-map/VERSION 1 KB
- presentations/code-map/assets/map.css 5 KB
- presentations/code-map/assets/map.js 33 KB
- presentations/code-map/assets/structure.css 3 KB
- presentations/code-map/references/content.schema.json 2 KB
- presentations/code-map/references/workflow.md 4 KB
- presentations/code-map/scripts/code-map.mjs 19 KB
- presentations/reverse-design/assets/design.css 4 KB
- presentations/reverse-design/references/content.schema.json 7 KB
- presentations/reverse-design/references/workflow.md 8 KB
- presentations/reverse-design/scripts/reverse-design.mjs 23 KB
- presentations/review-quiz/assets/quiz-runtime.mjs 6 KB
- presentations/review-quiz/assets/quiz.css 2 KB
- presentations/review-quiz/references/content.schema.json 3 KB
- presentations/review-quiz/references/workflow.md 7 KB
- presentations/review-quiz/scripts/review-quiz.mjs 14 KB
- presentations/walkthrough/assets/walkthrough.css 4 KB
- presentations/walkthrough/assets/walkthrough.js 4 KB
- presentations/walkthrough/references/content.schema.json 3 KB
- presentations/walkthrough/references/workflow.md 5 KB
- presentations/walkthrough/scripts/walkthrough.mjs 22 KB
- presentations/xkcd/assets/comic.css 1 KB
- presentations/xkcd/references/storyboard.schema.json 4 KB
- presentations/xkcd/references/workflow.md 5 KB
- presentations/xkcd/scripts/xkcd.mjs 23 KB
- runtime/guide.md 4 KB
- runtime/package-lock.json 66 KB
- runtime/package.json 1 KB
- runtime/references/analysis.md 2 KB
- runtime/references/analysis.schema.json 2 KB
- runtime/references/context.schema.json 2 KB
- runtime/scripts/analysis.mjs 20 KB
- runtime/scripts/code-unpacked.mjs 6 KB
- runtime/scripts/core.mjs 37 KB
- runtime/scripts/decode.mjs 15 KB
- runtime/scripts/dependencies.mjs 9 KB
- runtime/scripts/highlight.mjs 2 KB
- runtime/scripts/setup.mjs 1 KB
- runtime/scripts/values.mjs 2 KB
Wersje
W bazie nie ma innych skilli o nazwie code-unpacked.
Migawka bazy z 13.11.2026 · wersja paczki 52db823e4ec3 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 90om-ai-context-maintenance
Archiwizuje stare foldery przebiegów AI i samodzielne plany do jednego zweryfikowanego archiwum .tgz, zostawiając ostatnie 14 dni rozpakowane. - 100cdp-ext-pilot
Uruchamia trwałego Chromium (domyślnie bez interfejsu) z rozpakowanym rozszerzeniem załadowanym przez web ext, otwiera panel boczny, popup lub opcje i steruje nimi przez CDP, aby testować interfejs rozszerzenia. - 85code-review
Przegląda gałąź, pull request, katalog roboczy lub zmiany od commita pod kątem standardów repozytorium i zamierzonego zachowania. - 100rebase
Przenosi bieżącą gałąź na wybrany cel, na przykład main, inną gałąź lub gałąź zdalną, i obsługuje konflikty z uwzględnieniem kontekstu. - 100dataverse-pre-pr
Sprawdza repozytorium Dataverse przed pull requestem: eksportuje i rozpakowuje rozwiązania ze środowiska deweloperskiego, liczy zmienione pliki i weryfikuje konwencje kodu. - 86write-code
Dodaje lub zmienia kod Python w repozytorium wraz z testem, a potem formatuje, sprawdza lintem i testuje.