prompt-architect
Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Basiert auf: - Nate B. Jones 4 Beginner Moves: Shape, Context, Silent Plan, Self-Check - Anthropic Claude 4.x Best Practices: Explizitheit, Contract-Style, Examples beat Adjectives - Pipelines over Prompts Philosophie Wird AUSSCHLIESSLICH per /prompt-architect aufgerufen — KEINE automatische Aktivierung. Produziert strukturierten, ausfuehrbaren Prompt mit allen Best Practices.
What this skill does
# Prompt-Architect: Best-Practice Prompt Generator
## Basiert auf Claude 4.x Best Practices (Dezember 2025)
### Quellen:
- Nate B. Jones Prompting Playbook 2025
- Anthropic Official Claude 4.x Prompting Guide
- Claude Code Best Practices
## AKTIVIERUNG
**Nur manuell.** Dieser Skill aktiviert sich NICHT automatisch — auch nicht nach
clarify-spec. Die fruehere Auto-Kette (clarify-spec -> prompt-architect) wurde
entfernt, weil sie eine Klaerungs-Schleife verstaerkt hat.
### Manuell mit Trigger
/prompt-architect [Aufgabenbeschreibung]
Falls ein clarify-spec-Lauf vorausging und ein JSON-Ergebnis vorliegt, kann
prompt-architect dieses JSON nutzen — aber nur, wenn der User /prompt-architect
explizit aufruft.
## Die 4 Beginner Moves (Nate B. Jones)
### Move 1: Define the Shape of Output
NICHT: Schreib guten Code
SONDERN: Produziere eine TypeScript-Datei mit Interface X, exportiere Funktion Y
Konkrete Artefakte definieren:
- Welche Dateien werden erstellt/geaendert?
- Welches Format hat der Output?
- Wie sieht ein Beispiel-Output aus?
### Move 2: Give Minimal but Sufficient Context
- Automatisch relevante Dateien einlesen
- CLAUDE.md/AGENTS.md Auszuege
- Nur das Noetige - kein Context-Overflow
- Token Budget beachten
### Move 3: Suggest a Silent Plan
- Claude soll INTERN planen bevor es antwortet
- Bei Claude 4.5: consider your approach first
- Vermeidung von think bei deaktiviertem Extended Thinking
### Move 4: Add a Quick Self-Check
- Evaluator-Block am Ende des Prompts
- Checkliste: Format eingehalten? Constraints erfuellt?
- Before responding, verify: [checklist]
## Claude 4.x Spezifische Patterns
### Explizitheit + Modifier
NICHT: Create dashboard
SONDERN: Create dashboard. Include as many relevant features as possible. Go beyond the basics.
### Context + Motivation (WARUM erklaert WAS)
NICHT: NEVER use ellipses
SONDERN: Your response will be read aloud by TTS, so never use ellipses since TTS cannot pronounce them.
### Examples beat Adjectives
NICHT: Schreib professionell
SONDERN: Beispiel-Output zeigen, Format demonstrieren
### XML-Tags fuer Struktur
<output_structure>, <constraints>, <verification>
### Uncertainty Permission
If unsure, state explicitly and ask clarifying question.
Reduziert Halluzinationen drastisch.
## Das Contract-Style Template
Nach Analyse des Auftrags, generiere diesen strukturierten Prompt:
---BEGIN GENERATED PROMPT---
## ROLE and GOAL
You are: [Rolle basierend auf Task-Typ, z.B. Senior TypeScript Developer]
Goal: [Konkrete Erfolgsdefinition in 1 Satz aus clarified_task.goal]
## CONTEXT
[Automatisch gesammelt:]
- Projekt: [Projektname aus CLAUDE.md]
- Relevante Dateien: [Liste mit kurzem Inhaltsuebersicht]
- Bestehende Patterns: [Aus Codebase extrahiert]
- No-Touch Zones: [Aus clarified_task.scope.no_touch]
## CONSTRAINTS
- [Constraint 1 als Bullet aus clarified_task.constraints]
- [Constraint 2 als Bullet]
- [Max 5 Constraints]
- If unsure about any aspect: State explicitly and ask for clarification
## TASK
[Klare Aufgabenbeschreibung aus clarified_task.goal + problem_statement]
### Success Criteria
- [Kriterium 1 aus clarified_task.success_criteria]
- [Kriterium 2]
- All existing tests must pass
### Examples (if examples_needed = true)
Input: [Beispiel-Input]
Expected Output: [Erwarteter Output]
## OUTPUT FORMAT
<output_structure>
[Exaktes Format basierend auf Task-Typ:]
- Fuer Code: Vollstaendige Dateien, keine Diffs, keine Platzhalter
- Fuer Docs: Markdown mit Headings
- Fuer Config: JSON/YAML mit Kommentaren
</output_structure>
## VERIFICATION (Self-Check)
Before responding, verify:
[ ] Output format followed exactly?
[ ] All constraints from CONSTRAINTS section satisfied?
[ ] All success criteria from TASK section met?
[ ] Uncertain claims marked with [UNCERTAIN]?
[ ] No changes to No-Touch Zones?
---END GENERATED PROMPT---
## Workflow
### Schritt 1: Input analysieren
Akzeptiert:
1. JSON oder Kontext aus einem vorherigen clarify-spec-Lauf, wenn der User danach
explizit /prompt-architect aufruft
2. Freie Textbeschreibung
3. Kombiniert mit aktuellem Projekt-Kontext
### Schritt 2: Kontext automatisch sammeln
- Glob fuer relevante Dateien
- Read CLAUDE.md/AGENTS.md
- Identify No-Touch Zones
- Extract existing patterns from codebase
### Schritt 3: Template ausfuellen
Fuelle das Contract-Style Template mit:
- Role basierend auf Task-Typ (Frontend, Backend, DevOps, etc.)
- Goal aus clarified_task.goal
- Context aus Projekt-Analyse
- Constraints aus clarified_task.constraints
- Task aus goal + problem_statement
- Output Format basierend auf erwarteten Artefakten
- Verification Checklist
### Schritt 4: Prompt praesentieren
Zeige den generierten Prompt dem User:
---
## Generierter Best-Practice Prompt
[Vollstaendiger Prompt hier]
---
Optionen:
- ausfuehren: Diesen Prompt jetzt ausfuehren
- anpassen: Prompt modifizieren
- kopieren: Prompt in Zwischenablage
- speichern: Als Template speichern
### Schritt 5: Ausfuehrung
Bei ausfuehren:
1. Prompt intern verwenden
2. Mit Quality Gates (wenn /supervisor aktiv)
3. Ergebnis praesentieren
## Beispiel: Vom vagen Auftrag zum Best-Practice Prompt
### Input (von clarify-spec):
{
clarified_task: {
goal: PPTX-Export fixen, damit AI-Bilder zuverlaessig erscheinen,
problem_statement: Bilder fehlen manchmal im PPTX-Download,
scope: {
files: [presentationBuilder.ts, chartVisualGenerator.ts],
no_touch: [api/analyze.ts]
},
success_criteria: [Alle Bilder erscheinen, Unter 500KB, Keine Errors],
constraints: [Keine Breaking Changes]
}
}
### Output (generierter Prompt):
## ROLE and GOAL
You are: Senior TypeScript Developer specializing in browser-based file generation
Goal: Fix PPTX export so AI-generated images reliably appear in downloaded files
## CONTEXT
- Projekt: fabrikIQ Analyzer (Manufacturing AI Platform)
- Relevante Dateien:
- presentationBuilder.ts: PptxGenJS integration, slide generation
- chartVisualGenerator.ts: Gemini image generation, base64 handling
- Bestehende Patterns: Async/await, try-catch error handling
- No-Touch Zones: api/analyze.ts (core analysis)
## CONSTRAINTS
- No breaking changes to existing PPTX export functionality
- Images must be compressed to under 500KB
- Maintain existing error handling patterns
- If unsure about any aspect: State explicitly and ask
## TASK
Fix the PPTX export to ensure AI-generated images reliably appear in downloads.
The current issue: Images sometimes fail to appear in the final PPTX file.
### Success Criteria
- All AI-generated images appear in PPTX
- Image file size under 500KB each
- No console errors during download
- Existing tests still pass
## OUTPUT FORMAT
<output_structure>
Provide complete, modified TypeScript files.
No diffs, no placeholders, no partial implementations.
Include brief comments explaining key changes.
</output_structure>
## VERIFICATION
Before responding, verify:
[ ] All images will be embedded correctly?
[ ] Compression logic handles edge cases?
[ ] No changes to api/analyze.ts?
[ ] Error handling covers network failures?
## Token-Effizienz
Der generierte Prompt ist optimiert fuer:
- Minimaler Context (nur relevante Infos)
- Maximale Klarheit (keine Ambiguitaet)
- Self-Verification (reduziert Iterationen)
## Integration
### Nach clarify-spec
clarify-spec -> User ruft /prompt-architect explizit auf -> Prompt -> Ausfuehrung
### Mit /supervisor
prompt-architect -> Prompt -> /supervisor -> Quality Gates -> Ergebnis
### Standalone
/prompt-architect [Aufgabe] -> Prompt -> Ausfuehrung
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.