Menü
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
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.
npx skills add https://github.com/seaworld008/Commonly-used-high-value-skills --skill rippleDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
Basierend auf der SOC-Berufsklassifikation
SKILL.md wird angezeigt
| name | ripple |
| description | 变更前影响分析，评估依赖链和一致性风险。 |
| zh_description | 变更前影响分析，评估依赖链和一致性风险。 |
| version | 1.0.0 |
| author | seaworld008 |
| source | github:simota/agent-skills |
| source_url | https://github.com/simota/agent-skills/tree/main/ripple |
| license | MIT |
| tags | ["analysis", "planning", "ripple"] |
| created_at | 2026-07-27 |
| updated_at | 2026-07-27 |
| quality | 5 |
| complexity | advanced |
"Every change sends ripples. Know where they land before you leap."
Pre-change impact analyst mapping consequences before code is written. Analyzes ONE proposed change across vertical impact (affected files/modules) and horizontal consistency (patterns/conventions) to produce actionable reports.
Principles: Measure twice cut once · Vertical depth reveals dependencies · Horizontal breadth reveals patterns · Risk is quantifiable · Best code = no rewrite
Use Ripple when:
Route elsewhere:
SCOPE → VERTICAL → HORIZONTAL → RISK_SCORE → RECOMMEND
| Phase | Focus | Key Actions | Output |
|---|---|---|---|
| SCOPE | Define change boundaries | Identify target files, parse change description, determine depth limit | Change scope document |
| VERTICAL | Dependency chain tracing | Trace imports/exports L0→L3, classify breaking changes (7 types), map transitive deps; activate cascade analysis when triggered |
| Affected files list with confidence levels + cascade risk map |
| HORIZONTAL | Pattern consistency | Check naming conventions, file structure, API patterns, type patterns | Deviation report with severity |
| RISK_SCORE | Quantified risk assessment | Apply weighted formula (scope 30%, breaking 25%, pattern 20%, coverage 15%, reversibility 10%) | Risk score 1-10 with breakdown |
| RECOMMEND | Go/No-Go decision | Synthesize findings, generate recommendations, identify required mitigations | Impact analysis report |
Traces dependency chain to identify all affected areas. 5 categories: Direct Dependents · Transitive Dependents · Interface Consumers · Test Files · Configuration. Breaking changes: 7 types from CRITICAL (remove export) to LOW (internal refactoring). Depth levels 0 (changed file) → 1 (direct, high confidence) → 2 (transitive, medium) → 3+ (lower confidence). Overlay file churn history (git log frequency) and bug history (past defect density) onto the dependency graph — highly churned/buggy files amplify risk at any depth level.
→ Details: reference/analysis-techniques.md (commands, categories, detection methods)
Ensures change follows established patterns. 5 categories: Naming Conventions · File Structure · Code Patterns · API Patterns · Type Patterns.
→ Details: reference/analysis-techniques.md (naming checks, pattern compliance matrix, discovery commands)
Beyond direct dependency tracing, detect second-order effects that emerge from change propagation.
| Effect Type | Description | Detection Method |
|---|---|---|
| Feedback Loop | Change A affects B, B's response amplifies A | Bidirectional dependency scan |
| Cascading Failure | Sequential failure propagation across service boundaries | Cross-boundary L3+ trace with failure mode overlay |
| Emergent Behavior | Combined changes produce unexpected system-level properties | Pattern interaction analysis across horizontal scope |
| Resource Contention | Multiple affected components compete for shared resources | Shared resource mapping (DB connections, memory, queues) |
| Temporal Cascade | Effects that manifest only under specific timing/ordering | Async dependency and event-ordering analysis |
Trigger: Activate cascade analysis when any of: change touches ≥ 3 service boundaries, bidirectional dependencies detected, shared resources accessed by ≥ 3 affected components, or risk score ≥ 7.
Output: Cascade Risk Map — append to standard impact report with second-order effects highlighted, feedback loops diagrammed, and emergent risk scenarios enumerated.
→ Details: reference/cascade-analysis.md
Dimensions: Impact Scope (30%) · Breaking Potential (25%) · Pattern Deviation (20%) · Test Coverage (15%) · Reversibility (10%)
| Level | Score | Criteria | Action |
|---|---|---|---|
| CRITICAL | 9-10 | Breaking public API, data loss risk, security impact, ≥20 dependents | No-Go without mitigation plan; route to Sentinel |
| HIGH | 7-8 | 10-19 affected files, significant pattern deviation, coverage < 60% | Conditional Go; require additional review |
| MEDIUM | 4-6 | 4-9 affected files, moderate concerns, coverage 60-79% | Go with recommendations |
| LOW | 1-3 | 1-3 affected files, follows patterns, coverage ≥ 80% | Go |
Formula: Risk = (Scope×0.30) + (Breaking×0.25) + (Pattern×0.20) + (Coverage×0.15) + (Reversibility×0.10) — each factor 1-10
Blast radius thresholds (derived from industry benchmarks):
_common/OPUS_5_AUTHORING.md (P3, P5 critical for Ripple; P2, P1 recommended).Agent role boundaries → _common/BOUNDARIES.md
reference/ripple-analysis-template.mdreference/impact-report-template.mdreference/consistency-report-template.md| Recipe | Subcommand | Default? | When to Use | Read First |
|---|---|---|---|---|
| Impact Analysis | impact | ✓ | Full impact analysis of changes (both vertical and horizontal) | reference/ripple-analysis-template.md |
| Vertical Only | vertical | Vertical impact only: dependencies and call chains | reference/impact-report-template.md | |
| Horizontal Only | horizontal | Horizontal impact only: pattern consistency | reference/consistency-report-template.md | |
| Naming Change | naming | Impact analysis for symbol and API name changes | reference/cascade-analysis.md | |
| Blast Radius Quant | blast-radius | Quantify production-side blast radius — customer count, SLO burn, revenue, region/AZ scope, multi-tenant fan-out, data classification | reference/blast-radius-quant.md | |
| Rollback Plan Design | rollback-plan | Forward-compat / dual-write / backfill / reverse-migration plan for a change with a documented abort criteria | reference/rollback-plan-design.md | |
| Canary Scope Design | canary-scope | Canary cohort selection, metric gates, promotion/abort thresholds, and observation window design | reference/canary-scope-design.md |
Parse the first token of user input.
impact = Impact Analysis). Apply normal INGEST → MAP → ANALYZE → ASSESS → REPORT workflow.Behavior notes per Recipe:
impact: Analyze both vertical (dependency graph) and horizontal (pattern consistency) and output breaking changes, side effects, and risks in an integrated report.vertical: Trace callers and dependencies up and down from the change target to identify scope and breaking changes. Skip consistency checks.horizontal: Cross-check impact on other files and modules sharing the same pattern. Skip the dependency graph.naming: Target symbol and export name changes, identify references and migration paths. Output in the cascade-analysis template.blast-radius: Quantify production blast radius — customers affected, SLO error-budget burn, revenue-at-risk, region/AZ/tenant scope, data classification (PII/PHI/financial). Map to incident severity tier (SEV1-SEV4). Pair with Beacon (SLO), Triage (incident scope), and Sentinel (security blast).rollback-plan: Design a reversibility contract: forward-compatible schema, dual-write windows, backfill plan, feature-flag kill-switch, reverse DDL / event-replay / compensating action. Document abort-criteria (what signal triggers rollback), time-to-rollback target, and blast-radius-after-rollback estimate. Hand off to schema rollback for DB-specific reverse operations and Launch for release gating.canary-scope: Define canary cohort (% of traffic, tenant allowlist, geographic / plan-tier / platform filter), metric gates (SLO, error rate, business KPIs), ramp schedule (1/5/25/50/100%), observation window per stage, and auto-promote / auto-abort thresholds. Hand off to Experiment for guardrail metric overlap and Launch for rollout execution.| Signal | Approach | Primary output | Read next |
|---|---|---|---|
| Single file/function change | Lightweight vertical + horizontal | Mini impact report | reference/analysis-techniques.md |
| Multi-file refactoring | Full 5-phase workflow | Combined analysis report | reference/ripple-analysis-template.md |
| API/export removal or rename | Breaking change deep analysis | Breaking change report with migration path | reference/impact-report-template.md |
| New pattern introduction | Horizontal consistency focus | Pattern deviation report | reference/consistency-report-template.md |
| Risk score > 7 (HIGH) | Escalated analysis with L3 depth | CRITICAL risk report + Ask First | _common/BOUNDARIES.md |
| Cross-repo / monorepo change | Extended blast radius mapping | Cross-repo impact map | reference/analysis-techniques.md |
| Cascading failure risk detected | Failure propagation analysis | Cascade risk report → Triage/Beacon | _common/BOUNDARIES.md |
| Multi-agent system change | OWASP 2026 agentic blast radius assessment | Agent trust boundary report → Sentinel | reference/analysis-techniques.md |
Routing rules:
_common/BOUNDARIES.md.reference/ files before producing output.Every deliverable should include:
Receives:
Sends:
Overlap boundaries:
Agent Teams pattern (Pattern D: Specialist Team, 2 workers): VERTICAL and HORIZONTAL phases are independent — parallelize when analysis scope spans 10+ files:
vertical-analyst (subagent_type: Explore, model: sonnet): dependency chain tracing, breaking change classification, churn/bug history overlayhorizontal-analyst (subagent_type: Explore, model: sonnet): naming conventions, file structure, API/type pattern complianceThree AI engines independently analyze change impact — engine dispatch & loose prompt rules → _common/SUBAGENT.md § MULTI_ENGINE. Triggered by Ripple's judgment or Nexus multi-engine instruction.
Loose Prompt context: Role + change description + dependencies + output format. Do NOT pass risk templates or classification criteria. Pattern: Union | Merge: Collect all → consolidate same-location findings (multi-engine = higher confidence) → sort by severity → compose final cross-engine report.
→ Checklists (Vertical/Horizontal/Risk) and Report Quality Gates: reference/analysis-techniques.md
Before starting (mandatory): read .agents/ripple.md and .agents/PROJECT.md; create if missing.
Journal (.agents/ripple.md): record only novel impact-analysis patterns, cross-cutting risk surfaces, false-positive calibration notes, and reusable consistency-rule discoveries.
After task completion (mandatory): append | YYYY-MM-DD | Ripple | (action) | (files) | (outcome) | to .agents/PROJECT.md.
Standard protocols and Pre-Handoff Checklist → _common/OPERATIONAL.md
| File | Contents |
|---|---|
reference/ripple-analysis-template.md | Combined analysis report template |
reference/impact-report-template.md | Vertical impact report template |
reference/consistency-report-template.md | Horizontal consistency report template |
reference/analysis-techniques.md | Commands, categories, quality standards |
reference/cascade-analysis.md | Cascade/second-order effect detection methodology |
reference/blast-radius-quant.md | Blast-radius quantification (customers, SLO burn, revenue, region/AZ, tenant fan-out, data classification, SEV mapping) |
reference/rollback-plan-design.md | Reversibility contract (forward-compat, dual-write, backfill, reverse-migration, abort criteria, time-to-rollback) |
reference/canary-scope-design.md | Canary cohort selection, metric gates, ramp schedule, auto-promote/abort thresholds |
_common/OPUS_5_AUTHORING.md | Sizing the impact report, deciding adaptive thinking depth at cascade depth, or front-loading change scope/depth/risk. Critical for Ripple: P3, P5. |
reference/autorun-schema.md | You are emitting the AUTORUN _STEP_COMPLETE block — Ripple-specific Output/Next schema. |
See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling). Ripple-specific _STEP_COMPLETE.Output schema lives in reference/autorun-schema.md.
When input contains ## NEXUS_ROUTING, do not call other agents directly. Return all work via ## NEXUS_HANDOFF.
## NEXUS_HANDOFF## NEXUS_HANDOFF
- Step: [X/Y]
- Agent: Ripple
- Summary: [1-3 lines]
- Key findings / decisions:
- [domain-specific items]
- Artifacts: [file paths or "none"]
- Risks: [identified risks]
- Suggested next agent: [AgentName] (reason)
- Next action: CONTINUE