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

Architecture Knowledge Curator

skill-qingye-lab-hengmu-architecture-knowledge-curator · by qingye-lab

Maintains the plugin's architecture quality models, styles, patterns, technology profiles, reference architectures, migration guides, domain guidance, decision rules, machine rule packs, and evidence-provider registry. Use when adding or refreshing architecture knowledge, checking official-source freshness, reviewing framework capability claims, resolving duplicate or contradictory entries, or pr…

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

Install

$ agentstack add skill-qingye-lab-hengmu-architecture-knowledge-curator

✓ 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-qingye-lab-hengmu-architecture-knowledge-curator)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo 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 Architecture Knowledge Curator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Curate architecture knowledge

Maintain reusable architecture knowledge without turning volatile product claims into timeless rules.

Load the contracts

Read:

  • ../../../resources/references/knowledge-contract.md;
  • ../../../resources/knowledge/manifest.yaml;
  • ../../../resources/schemas/knowledge-entry.schema.json;
  • ../../../resources/schemas/knowledge-manifest.schema.json;
  • ../../../resources/schemas/rule-pack.schema.json;
  • ../../../resources/schemas/evidence-provider.schema.json;
  • ../../../resources/schemas/evidence-provider-config.schema.json;
  • ../../../resources/schemas/evidence-run.schema.json;
  • ../../../resources/references/evidence-provider-contract.md;
  • only the Markdown entries, Rule Packs, or provider contracts affected by the

request.

Classify the change

Classify knowledge before editing:

  • stable: quality concepts, architecture styles, patterns, and tradeoffs;
  • slow-changing: framework capabilities, operating models, and lock-in;
  • fast-changing: versions, support status, compatibility, security advisories,

pricing, and product lifecycle.

Keep stable knowledge in Markdown/frontmatter entries. Record official-source URLs and a review window for slow-changing knowledge. Mark technology profiles as dynamic and verify fast-changing facts from current official sources at use time; do not freeze them into a Skill.

Curation workflow

  1. Define the decision changed by the proposed entry.
  2. Use standards, official documentation, or maintainer documentation as

sources. Use research only for claims absent from authoritative sources.

  1. Follow ../../../docs/knowledge-authoring.md and record all fourteen

required body sections plus canonical ID, version, kind, domains, triggers, qualities, relationships, sources, source policy, and freshness.

  1. Describe what a style, pattern, or technology does not solve.
  2. Keep technology and architecture style separate.
  3. Reject entries that merely repeat a product name, popularity claim, or

unbounded best practice.

  1. Deduplicate by decision semantics. Preserve different entries when

similarly named mechanisms have different ownership or failure behavior.

  1. Update associated decision rules, reference architecture, migration guide,

provider, tests, and changelog when behavior changes.

Do not change a Rule Pack solely because a tool can detect a metric. A rule must protect one invariant at an owning boundary and specify evidence requirements.

Validate

Run:

python3 ../../../resources/scripts/validate_knowledge.py
python3 ../../../scripts/validate_repository.py

Report added, changed, removed, or stale entries and their official sources. Do not audit a repository, select its target architecture, or modify product code.

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