Przejdź do treści
Biblioteka skilli
Programowanie · Budowanie i kod

superpowers

/superpowers

Prowadzi dyscyplinowaną implementację oprogramowania: planowanie, TDD, debugowanie przyczyn, przegląd kodu i dowody ukończenia.

Repozytorium
devflow-kit ↗
Licencja
MIT
Ostatnia zmiana repozytorium
11.11.2026

Ocena i bezpieczeństwo

81/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść16 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
85
Skrypty
7
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 11.11.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co sprawdzić przed instalacją
  • 7 skryptów w paczce. Przejrzyj je przed instalacją, bo Claude może je uruchomić.

Skrypty: upstream/skills/brainstorming/scripts/helper.js, upstream/skills/brainstorming/scripts/server.cjs, upstream/skills/brainstorming/scripts/start-server.sh, upstream/skills/brainstorming/scripts/stop-server.sh, upstream/skills/systematic-debugging/condition-based-waiting-example.ts, upstream/skills/systematic-debugging/find-polluter.sh, upstream/skills/writing-skills/render-graphs.js

Co robi i kiedy

Prowadzi dyscyplinowaną implementację oprogramowania: planowanie, TDD, debugowanie przyczyn, przegląd kodu i dowody ukończenia.

Oryginalny opis (EN)

Use for disciplined software implementation with planning, TDD, root-cause debugging, code review and evidence-based completion, or when the user requests the bundled Superpowers workflows. Includes sequential and supported subagent execution; reuse accepted requirements and existing UI design.

Jak działa

SKILL.md bez nagłówków drugiego poziomu · 31 linii, 475 słów

Podgląd SKILL.md
---
name: superpowers
description: Use for disciplined software implementation with planning, TDD, root-cause debugging, code review and evidence-based completion, or when the user requests the bundled Superpowers workflows. Includes sequential and supported subagent execution; reuse accepted requirements and existing UI design.
license: MIT; see LICENSE.
---

# Superpowers — bundled development workflows

This is an adapted, pinned Superpowers 7.0.2 suite, not the upstream auto-bootstrap plugin. Read [compatibility and scope](references/compatibility.md), then only the relevant profile below. There are 15 profiles behind this one discoverable entry. Profiles are `GUIDE.md` files so hosts do not auto-load an additional global `using-superpowers` entry. The upstream body, supporting references, prompts and helpers are retained with documented adaptations.

For review scope and security findings, use [DevFlow review coordination](../devflow/references/review-security.md). The relevant profile supplies engineering discipline; Open Code Review and Security Audit supply specialist review without repeating accepted work.

For an approved task, continue from the unresolved work. For a bug, investigate the cause and reproduce it, fix it, and verify. For an accepted plan, execute it directly; choose sequential execution if the host lacks subagents. For new product decisions, use brainstorming, then a plan sized to the task. [The lifecycle router](../devflow/SKILL.md) owns reference discovery, specifications, mock/reverse and acceptance; Superpowers supplies the engineering steps within that lifecycle. [Ponytail](../ponytail/SKILL.md) keeps the implementation focused, and the [shared UI policy](../devflow/references/ui-task-policy.md) keeps UI scope and brand intact.

| Profile | When to load |
|---|---|
| [using-superpowers](upstream/skills/using-superpowers/GUIDE.md) | How the suite selects relevant workflows; use the bundle capability rules below. |
| [brainstorming](upstream/skills/brainstorming/GUIDE.md) | Clarify unresolved product/design decisions; reuse accepted requirements. |
| [writing-plans](upstream/skills/writing-plans/GUIDE.md) | Break an accepted design into verifiable implementation tasks. |
| [executing-plans](upstream/skills/executing-plans/GUIDE.md) | Execute an accepted plan sequentially; also the no-subagent fallback. |
| [subagent-driven-development](upstream/skills/subagent-driven-development/GUIDE.md) | Delegate implementation/review when supported and appropriate. |
| [dispatching-parallel-agents](upstream/skills/dispatching-parallel-agents/GUIDE.md) | Independent investigations with no shared mutable work. |
| [test-driven-development](upstream/skills/test-driven-development/GUIDE.md) | Reproduce meaningful behavior/bugs, then verify the correction. |
| [systematic-debugging](upstream/skills/systematic-debugging/GUIDE.md) | Find the root cause before changing code. |
| [requesting-code-review](upstream/skills/requesting-code-review/GUIDE.md) | Review a concrete change with sufficient code and evidence. |
| [receiving-code-review](upstream/skills/receiving-code-review/GUIDE.md) | Check feedback against requirements and reproduce findings. |
| [verification-before-completion](upstream/skills/verification-before-completion/GUIDE.md) | Run relevant checks before claiming success. |
| [using-git-worktrees](upstream/skills/using-git-worktrees/GUIDE.md) | Isolate work when needed, preserving current user work. |
| [finishing-a-development-branch](upstream/skills/finishing-a-development-branch/GUIDE.md) | Prepare tested changes for the authorized delivery action. |
| [writing-skills](upstream/skills/writing-skills/GUIDE.md) | Create or refine skill instructions using realistic scenarios. |
| [diagnosing-superpowers](upstream/skills/diagnosing-superpowers/GUIDE.md) | Requested session diagnosis using scoped evidence; no automatic transcript export. |

Resolve `superpowers:<profile>` mentions by this table even if the host has no Skill tool. Read the linked file directly. Never substitute an older personal copy just because its name matches. Explicit use: ask the installed `superpowers` entry to apply `systematic-debugging`, or ask the outer `devflow` router to use Superpowers for the accepted task. Actual skill names/prefixes depend on discovery.

Helper prerequisites are optional for reading: Bash + Git/POSIX tools for plan helpers, Node for the visual companion, Graphviz for diagram rendering. See [execution boundaries and portable commands](references/compatibility.md). Installation starts no server, injects no hook and edits no account configuration. Missing capabilities must be reported, never simulated as a successful run.
Pliki w paczce (85)
  • LICENSE 1 KB
  • SKILL.md 5 KB
  • profiles.json 1 KB
  • references/compatibility.md 6 KB
  • upstream/VERSION.json 1 KB
  • upstream/skills/brainstorming/GUIDE.md 15 KB
  • upstream/skills/brainstorming/builder-check-prompt.md 1 KB
  • upstream/skills/brainstorming/visual-companion.md 13 KB
  • upstream/skills/brainstorming/scripts/frame-template.html 8 KB
  • upstream/skills/brainstorming/scripts/helper.js 5 KB
  • upstream/skills/brainstorming/scripts/server.cjs 25 KB
  • upstream/skills/brainstorming/scripts/start-server.sh 7 KB
  • upstream/skills/brainstorming/scripts/stop-server.sh 3 KB
  • upstream/skills/diagnosing-superpowers/GUIDE.md 7 KB
  • upstream/skills/diagnosing-superpowers/prompts/analyst-common.md 2 KB
  • upstream/skills/diagnosing-superpowers/prompts/cost-and-time.md 2 KB
  • upstream/skills/diagnosing-superpowers/prompts/plan-adherence.md 2 KB
  • upstream/skills/diagnosing-superpowers/prompts/quality-evidence.md 1 KB
  • upstream/skills/diagnosing-superpowers/prompts/repeated-work.md 1 KB
  • upstream/skills/diagnosing-superpowers/prompts/request-conflicts.md 1 KB
  • upstream/skills/diagnosing-superpowers/prompts/scrub-audit.md 1 KB
  • upstream/skills/diagnosing-superpowers/prompts/scrub.md 1 KB
  • upstream/skills/diagnosing-superpowers/prompts/similar-session.md 2 KB
  • upstream/skills/diagnosing-superpowers/prompts/skill-timeline.md 2 KB
  • upstream/skills/diagnosing-superpowers/prompts/stumbles.md 1 KB
  • upstream/skills/diagnosing-superpowers/references/context-safety.md 1 KB
  • upstream/skills/diagnosing-superpowers/references/github-issues.md 2 KB
  • upstream/skills/diagnosing-superpowers/references/redaction-policy.md 2 KB
  • upstream/skills/diagnosing-superpowers/references/session-discovery.md 2 KB
  • upstream/skills/diagnosing-superpowers/templates/bundle-README.md 4 KB
  • upstream/skills/diagnosing-superpowers/templates/case.md 3 KB
  • upstream/skills/diagnosing-superpowers/templates/issue.md 3 KB
  • upstream/skills/diagnosing-superpowers/templates/report.md 2 KB
  • upstream/skills/dispatching-parallel-agents/GUIDE.md 7 KB
  • upstream/skills/executing-plans/GUIDE.md 19 KB
  • upstream/skills/executing-plans/scripts/task-done 2 KB
  • upstream/skills/executing-plans/scripts/task-start 1 KB
  • upstream/skills/finishing-a-development-branch/GUIDE.md 8 KB
  • upstream/skills/receiving-code-review/GUIDE.md 7 KB
  • upstream/skills/requesting-code-review/GUIDE.md 3 KB
  • upstream/skills/requesting-code-review/code-reviewer.md 6 KB
  • upstream/skills/subagent-driven-development/GUIDE.md 20 KB
  • upstream/skills/subagent-driven-development/implementer-prompt.md 6 KB
  • upstream/skills/subagent-driven-development/re-review-prompt.md 5 KB
  • upstream/skills/subagent-driven-development/task-reviewer-prompt.md 9 KB
  • upstream/skills/subagent-driven-development/references/batching.md 1 KB
  • upstream/skills/subagent-driven-development/references/cannot-verify.md 1 KB
  • upstream/skills/subagent-driven-development/references/final-review.md 3 KB
  • upstream/skills/subagent-driven-development/references/fix-loop.md 4 KB
  • upstream/skills/subagent-driven-development/references/handling-reports.md 1 KB
  • upstream/skills/subagent-driven-development/references/preflight.md 1 KB
  • upstream/skills/subagent-driven-development/references/resuming.md 1 KB
  • upstream/skills/subagent-driven-development/scripts/review-package 2 KB
  • upstream/skills/subagent-driven-development/scripts/sdd-repo 2 KB
  • upstream/skills/subagent-driven-development/scripts/sdd-workspace 5 KB
  • upstream/skills/subagent-driven-development/scripts/task-brief 5 KB
  • upstream/skills/systematic-debugging/GUIDE.md 10 KB
  • upstream/skills/systematic-debugging/condition-based-waiting-example.ts 5 KB
  • upstream/skills/systematic-debugging/condition-based-waiting.md 3 KB
  • upstream/skills/systematic-debugging/defense-in-depth.md 4 KB
  • upstream/skills/systematic-debugging/find-polluter.sh 3 KB
  • upstream/skills/systematic-debugging/root-cause-tracing.md 5 KB
  • upstream/skills/test-driven-development/GUIDE.md 10 KB
  • upstream/skills/test-driven-development/writing-good-tests.md 8 KB
  • upstream/skills/using-git-worktrees/GUIDE.md 7 KB
  • upstream/skills/using-superpowers/GUIDE.md 4 KB
  • upstream/skills/using-superpowers/references/antigravity-tools.md 1 KB
  • upstream/skills/using-superpowers/references/claude-code-tools.md 1 KB
  • upstream/skills/using-superpowers/references/codex-tools.md 5 KB
  • upstream/skills/using-superpowers/references/gemini-tools.md 4 KB
  • upstream/skills/using-superpowers/references/hermes-tools.md 2 KB
  • upstream/skills/using-superpowers/references/muse-tools.md 2 KB
  • upstream/skills/using-superpowers/references/pi-tools.md 1 KB
  • upstream/skills/verification-before-completion/GUIDE.md 4 KB
  • upstream/skills/writing-plans/GUIDE.md 11 KB
  • upstream/skills/writing-skills/GUIDE.md 17 KB
  • upstream/skills/writing-skills/render-graphs.js 5 KB
  • upstream/skills/writing-skills/references/CLAUDE_MD_TESTING.md 5 KB
  • upstream/skills/writing-skills/references/anthropic-best-practices.md 45 KB
  • upstream/skills/writing-skills/references/bulletproofing.md 3 KB
  • upstream/skills/writing-skills/references/discovery.md 7 KB
  • upstream/skills/writing-skills/references/flowcharts.md 1 KB
  • upstream/skills/writing-skills/references/graphviz-conventions.dot 6 KB
  • upstream/skills/writing-skills/references/persuasion-principles.md 6 KB
  • upstream/skills/writing-skills/references/testing-skills-with-subagents.md 12 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · chinhkrb113/devflow-kit81MIT
alebgl77/claude-inc100MIT
HK-hub/AgentSkills100MIT

Migawka bazy z 13.11.2026 · wersja paczki 273f333310b3 (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

  • 100superpowers-zh
    Prowadzi pracę AI nad kodem według metodyki: TDD, systematyczne debugowanie, przegląd kodu i weryfikację wyników.
  • 100test-driven-development
    Prowadzi TDD dla każdej funkcji i poprawki przed implementacją, na podstawie dystrybucji Superpowers 6.2.0 na licencji MIT.
  • 100using-superpowers
    Wybiera skille workflow Superpowers, gdy użytkownik prosi o ten przepływ albo konkretne zadanie deweloperskie skorzysta z jego procesu.
  • 100sdd-to-tdd-with-ddd
    Koordynuje planowanie specyfikacji, modelowanie domeny, przykłady BDD i programowanie sterowane testami w OpenSpec i Superpowers. Przydaje się, gdy zespół chce połączyć te podejścia.
  • 100planning
    Wspiera planowanie rozwoju: funkcje, TDD i przegląd architektury, z wynikiem w postaci strategii technicznej.
  • 100obra-superpowers
    Dodaje agentowi kodującemu metodę tworzenia oprogramowania jako plugin skilli: burza mózgów, pisane plany, implementacja test-first, wykonanie przez subagentów i przegląd kodu, z instalacją i diagnozą wyzwalania.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.