AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Advisor Review Loop Maintainer

skill-undertone0809-rudder-advisor-review-loop-maintainer · by Undertone0809

Use when Rudder development work needs first-principles advisor analysis plus independent reviewer rounds: proposals, UI/product decisions, architecture, release readiness, workflow changes, agent outcomes, explicit acceptance gates, repeated review, or “没有通过 review 返工”.

↗ Website ↗ Repository
— No reviews yet
0 installs
42 views
0.0% view→install

Install

$ agentstack add skill-undertone0809-rudder-advisor-review-loop-maintainer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-undertone0809-rudder-advisor-review-loop-maintainer)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Advisor Review Loop Maintainer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Advisor Review Loop Maintainer

Overview

Run a decision-grade advisor-to-reviewer loop for Rudder work that should not be accepted after one author pass.

When to Use

Use this skill when:

  • the user asks for Build Advisor plus reviewer agents
  • the work needs first-principles scenario, requirement, or corner-case analysis before acceptance
  • the user asks for repeated review rounds, acceptance gates, or rework until review passes
  • a proposal, skill, workflow, UI, architecture, release, or agent outcome needs independent pressure before handoff

Do not use this skill when:

  • narrow bug fixes where implementation is already clear
  • simple command execution
  • ordinary code review without advisor analysis
  • release execution without an advisor/reviewer loop

Core Pattern

evidence packet -> advisor pass -> reviewer agents -> rework list -> second review -> final handoff

Quick Reference

| Situation | Action | | --- | --- | | Fuzzy high-stakes request | Build advisor packet first | | Needs independent pressure | Spawn reviewers after the advisor artifact exists | | Reviewer finds blockers | Convert to rework list and rerun review | | User asked only for advice | Use build-advisor instead |

Implementation

  1. Build a compact evidence packet from user request, repo state, relevant docs, and named artifacts.
  2. Run the advisor pass to produce scenarios, requirements, options, risks, and recommended path.
  3. Spawn independent reviewers only after there is an artifact to judge.
  4. Merge reviewer findings into concrete rework items, revise, and run the requested next round.
  5. Hand off with advisor conclusion, reviewer verdicts, unresolved risks, and next decision.

Reference files are part of this skill contract. Before executing high-risk actions or final judgments, load references/runbook.md for the detailed legacy workflow, examples, validation cases, and command-level guidance.

Use evals/ when the route needs that detail; keep the entrypoint thin.

Common Mistakes

| Mistake | Fix | | --- | --- | | Skipping the advisor artifact and spawning reviewers immediately | Produce the scenario/requirement artifact first. | | Treating reviewer comments as optional decoration | Convert blockers into rework before handoff. | | Using this for a small obvious fix | Route to the narrow maintainer or normal implementation workflow. | | Accepting one author pass when the user asked for repeated rounds | Run the requested review loop or report why it is blocked. |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills