u0532-engineering-human-approval-router
Operate the "Engineering Human Approval Router" capability in production for workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
Best use case
u0532-engineering-human-approval-router is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Operate the "Engineering Human Approval Router" capability in production for workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
Teams using u0532-engineering-human-approval-router should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/u0532-engineering-human-approval-router/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How u0532-engineering-human-approval-router Compares
| Feature / Agent | u0532-engineering-human-approval-router | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Operate the "Engineering Human Approval Router" capability in production for workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Engineering Human Approval Router ## Why This Skill Exists We need this skill because delivery speed must increase without sacrificing correctness. This specific skill directs high-risk decisions to the right humans quickly. ## Step-by-Step Implementation Guide 1. Define the scope and success metrics for `Engineering Human Approval Router`, including at least three measurable KPIs tied to regressions and brittle release pipelines. 2. Design and version the input/output contract for code changes, tests, incidents, and rollout data, then add schema validation and failure-mode handling. 3. Implement the core capability using reviewer routing policies, and produce priority approval queues with deterministic scoring. 4. Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls. 5. Add unit, integration, and simulation tests that explicitly cover regressions and brittle release pipelines, then run regression baselines. 6. Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes. ## Metadata - **Skill ID:** `532` - **Skill Name:** `u0532-engineering-human-approval-router` - **Domain:** `Software Engineering Automation` - **Domain Slug:** `software-engineering-automation` - **Archetype:** `planning-router` - **Core Method:** `reviewer routing policies` - **Primary Artifact:** `priority approval queues` - **Routing Tag:** `software-engineering-automation:planning-router` - **Feature Flag:** `skill_0532_engineering-human-approval-route` - **Release Cycles:** `2` ## Allowed Tools - `read`, `write`, `edit` for contract maintenance, runbook updates, and handoff documentation. - `exec`, `process` for deterministic execution, validation suites, and regression checks. - `web_search`, `web_fetch` only when fresh external evidence is required for claims/evidence inputs. - Use messaging or publishing tools only after policy approval gates are satisfied. ## Inputs (formatted) | name | type | required | source | |---|---|---|---| | code changes | signal | true | upstream | | tests | signal | true | upstream | | incidents | signal | true | upstream | | rollout data | signal | true | upstream | | claims | signal | true | upstream | | evidence | signal | true | upstream | | confidence traces | signal | true | upstream | ## Outputs (formatted) | name | type | guaranteed | consumer | |---|---|---|---| | priority_approval_queues_report | structured-report | true | orchestrator | | priority_approval_queues_scorecard | scorecard | true | operator | ## Guidelines 1. Validate required inputs before execution and reject non-conforming payloads early. 2. Run `reviewer routing policies` with deterministic settings and trace capture enabled. 3. Produce `priority approval queues` outputs in machine-readable form for orchestrator/operator use. 4. Keep routing aligned with `software-engineering-automation:planning-router` and include approval context. 5. Tune thresholds incrementally based on observed KPI drift and incident learnings. ## Musts - Enforce approval gates: `policy-constraint-check`, `human-approval-router`. - Apply retry policy: maxAttempts=`3`, baseDelayMs=`900`, backoff=`exponential`. - Run validation suites before release: `unit`, `integration`, `simulation`, `regression-baseline`. - Fail closed when validation gates fail and execute rollback strategy `rollback-to-last-stable-baseline`. - Preserve reproducible evidence artifacts for audits and downstream handoff. ## Targets (day/week/month operating cadence) - **Day:** Validate new upstream signals, execute deterministic run, and hand off outputs for active decisions. - **Week:** Review KPI focus (`regressions`, `brittle release pipelines`, `decision drift`), failure trends, and approval/retry performance. - **Month:** Re-baseline deterministic expectations, confirm policy alignment, and refresh feature-flag/rollout posture. ## Common Actions 1. **Intake Check:** Confirm all required signals are present and schema-valid. 2. **Core Execution:** Run the capability pipeline and generate report + scorecard artifacts. 3. **Gate Review:** Evaluate validation and approval gates before publish-level handoff. 4. **Recovery:** Retry transient failures, then rollback to stable baseline on persistent errors. 5. **Handoff:** Send artifacts with risk/confidence metadata and downstream routing hints. ## External Tool Calls Needed - None required by default. - If external systems are introduced for a run, record the dependency, timeout budget, and retry behavior in execution notes. ## Validation & Handoff ### Validation Gates - `schema-contract-check`: All required input signals present and schema-valid (on fail: `quarantine`) - `determinism-check`: Repeated run on same inputs yields stable scoring and artifacts (on fail: `escalate`) - `policy-approval-check`: Approval gates satisfied before publish-level outputs (on fail: `retry`) ### Validation Suites - `unit` - `integration` - `simulation` - `regression-baseline` ### Failure Handling - `E_INPUT_SCHEMA`: Missing or malformed required signals → Reject payload, emit validation error, request corrected payload - `E_NON_DETERMINISM`: Determinism delta exceeds allowed threshold → Freeze output, escalate to human approval router - `E_DEPENDENCY_TIMEOUT`: Downstream or external dependency timeout → Apply retry policy then rollback to last stable baseline ### Handoff Contract - **Produces:** `Engineering Human Approval Router normalized artifacts`, `execution scorecard`, `risk posture` - **Consumes:** `code changes`, `tests`, `incidents`, `rollout data`, `claims`, `evidence`, `confidence traces` - **Downstream Hint:** Route next to software-engineering-automation:planning-router consumers with approval-gate context
Related Skills
u01789-human-approval-routing-for-remote-team-collaboration
Operate the "Human Approval Routing for remote team collaboration" capability in production for remote team collaboration workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
u01784-human-approval-routing-for-multilingual-translation-services
Operate the "Human Approval Routing for multilingual translation services" capability in production for multilingual translation services workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
u01689-human-approval-routing-for-education-support-services
Operate the "Human Approval Routing for education support services" capability in production for education support services workflows. Use when mission execution explicitly requires this capability and outcomes must be reproducible, policy-gated, and handoff-ready.
asset-approval
Use to manage co-marketing asset reviews with traceable evidence and SLAs.
approval
Imported skill approval from langchain
approval-workflow
Manages Human-in-the-Loop (HITL) approval workflows for sensitive actions. Use when creating approval requests, processing approved items, or implementing safety controls for autonomous actions.
approval-gate
ワークフローの重要なフェーズ移行前にユーザーの明示的な承認を必要とする承認ゲートの共通フォーマットとパターンを定義
solid-router-queries
Solid Router queries: query() for data fetching with caching/deduplication, createAsync() for reactive signals, createAsyncStore() for fine-grained reactivity, query keys for revalidation.
solid-router-preloading
Solid Router preloading: preload function for routes, usePreloadRoute hook, hover/focus intent detection, lazy component preloading, performance optimization.
Next.js App Router & Server Components
Build Next.js 15 applications using App Router, Server Components, Client Components, Server Actions, and streaming. Apply when creating pages, handling data fetching, implementing routes, or optimizing performance.
app-router
This skill should be used when the user asks to "create a Next.js route", "add a page", "set up layouts", "implement loading states", "add error boundaries", "organize routes", "create dynamic routes", or needs guidance on Next.js App Router file conventions and routing patterns.
angular-router
Angular Router for navigation, routing configuration, route guards, lazy loading, and parameter handling. Use when setting up routes, implementing navigation guards, lazy loading modules, handling route parameters, or implementing breadcrumbs and nested routes in Angular applications.