Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Understanding critical path for a release or milestone
Analyzing impact of changing a shared module or entity
When NOT to Use
Single-service code changes with no cross-boundary impact -- just implement directly
Performance analysis -- use performance instead
Security dependency auditing -- use security-review instead
Package/npm dependency upgrades -- use package-upgrade instead
Prerequisites
Read the feature/PBI/plan files to understand scope
Access to docs/project-reference/project-structure-reference.md for service boundary reference
Understand the project's microservice boundaries (read the project's structure reference / docs/project-config.json for the service-root location, then list the services under it)
Workflow
Step 1: Identify Scope
Determine what to map:
Single feature: Find all files, services, and entities it touches
Module/service: Map all inbound and outbound dependencies
Release/milestone: Map all features and their inter-dependencies
Step 2: Classify Dependencies
For each dependency found, classify by type:
Type
Direction
Description
Example
Data
Entity A requires Entity B
Foreign key, navigation property, shared ID
Order requires Customer
Service
Service A calls Service B
Message bus, API call, event consumer
Service A consumes entity events from Service B
UI
Component A embeds Component B
Shared component, library dependency
Feature form uses shared component library select
Infrastructure
Feature needs infra change
Database migration, config, new queue
New feature needs Redis cache key
Step 3: Build Dependency Graph
Use Mermaid syntax for visualization:
graph TD
A[Feature A] -->|data| B[Feature B]
A -->|service| C[Feature C]
B -->|blocks| D[Feature D]
C -->|blocks| D
style D fill:#f96,stroke:#333
Step 4: Identify Critical Path
Find the longest chain of blocking dependencies
Mark items with no blockers as "ready to start"
Flag circular dependencies as errors
Step 5: Deliver Report
Output structured dependency report (see Output Format).
Output Format
## Dependency Map: [Feature/Module Name]### Summary- Total items: N
- Ready to start: N (no blockers)
- Blocked: N
- Critical path length: N steps
### Dependency Graph
[Mermaid diagram]
### Critical Path1. [Item A] -- no blockers, estimated: Xd
2. [Item B] -- blocked by: A, estimated: Xd
3. [Item C] -- blocked by: B, estimated: Xd
### Dependency Details
| Item | Type | Depends On | Blocks | Status |
| ---- | --------------------- | ---------- | ------ | ------------- |
| ... | data/service/UI/infra | ... | ... | ready/blocked |
### Risks- [Circular dependency / tight coupling / single point of failure]
Examples
Example 1: Backend Cross-Service Feature
Input: "Map dependencies for adding a new Shipment feature in {ServiceA}"
Analysis:
graph TD
E[Order Entity - ServiceA] -->|data| C[Shipment Entity]
U[User Entity - AuthService] -->|service| C
C -->|service| N[Notification - ServiceB]
C -->|UI| CF[Shipment Form Component]
CF -->|UI| BC[shared-components select]
Critical path: Order Entity -> Shipment Entity -> Shipment API -> Shipment Form
Ready to start: Order Entity already exists, shared component select exists
Blocked: Shipment Entity creation, then API, then UI
Example 2: Frontend Module Dependency
Input: "What blocks the new Dashboard widget in {AnalyticsService}?"
Analysis:
graph TD
GA[Source API - ServiceA] -->|service| GE[Event Bus Message]
GE -->|service| GC[Consumer - AnalyticsService]
GC -->|data| GS[Summary Entity]
GS -->|UI| GW[Dashboard Widget]
GW -->|UI| DC[Dashboard Container]
Blockers identified:
Event Bus Message producer must exist in ServiceA (exists: yes)
Consumer must be created in AnalyticsService (exists: no -- BLOCKER)
Summary Entity for aggregated data (exists: no -- BLOCKER)
Related Skills
project-manager -- for sprint planning and status tracking
workflow-feature -- for implementing features after dependency analysis
package-upgrade -- for npm/NuGet package dependency upgrades
[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
Prerequisites:MUST ATTENTION READ before executing:
AI Mistake Prevention — Failure modes to avoid on every task:
Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting.
Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing.
Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first.
Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done.
Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect.
Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history.
Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk.
Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code.
Search 3+ similar patterns (grep/glob) — cite file:line evidence
Read existing files in target area — understand structure, base classes, conventions
Run python .claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists
Map dependencies via connections or callers_of — know what depends on your target
Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files)
Re-read analysis file before implementing — never work from memory alone. — why: long context drifts from the file; the file is ground truth
NEVER invent new patterns when existing ones work — match exactly or document deviation. — why: divergent patterns fragment the codebase and slow every future reader
MANDATORY IMPORTANT MUST ATTENTION search 3+ existing patterns and read code BEFORE any modification. Run graph trace when graph.db exists.
MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim. Confidence >80% to act, <60% = do NOT recommend.
MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.
MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.
Closing Reminders
Protocols in force (concise digest of the SYNC/shared blocks this skill carries):
AI Mistakes: holistic-first debug, fix at responsible layer, surgical diff, verify all outputs.
Critical Thinking: traced proof per claim, confidence >80% to act, NEVER guess.
Understand Code: read code and grep 3+ patterns before any modification.
MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.
