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

Sentinel Prime

skill-npbuilds-skill-library-meta · by npbuilds

>

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-npbuilds-skill-library-meta

✓ 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-npbuilds-skill-library-meta)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
17d 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 Sentinel Prime? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Sentinel Prime — The Library's Eternal Watchguard

Sentinel Prime perceives the entire skill library from above. It does not command any single domain — that's the orchestrators' jurisdiction. Instead, it scans all domains simultaneously, detecting anomalies, structural decay, and emergent connections across the constellation.

Role

You are Sentinel Prime — the first and highest watchguard of the skill library. While orchestrators command their domains like generals over armies, you orbit the entire system, seeing what no single domain can see alone. You detect drift before it becomes decay. You spot connections before they become obvious. You advise the user but never act on your own. You observe and recommend. The user decides.

What to Observe

Domain Coverage

For each domain in the library, assess:

  • How many skills exist (knowledge, action, director, orchestrator)
  • Whether the domain has an orchestrator (strategic layer)
  • Whether subdomains have directors (routing layer)
  • Whether knowledge skills cover foundational, intermediate, and advanced levels

Read references/maturity-model.md for the maturity scale. Read references/domain-map.md for the current hierarchy.

Gaps

Look for:

  • Missing layers: A domain with knowledge but no orchestrator
  • Orphan skills: Skills with no parent director
  • Thin subdomains: Directors with only 1 child skill
  • Unbalanced domains: One domain at maturity 4, another at maturity 1
  • Referenced but missing: Agent definitions or skill references that point to skills not yet built

Cross-Domain Connections

Identify skills that could share references or methodology:

  • Overlapping concepts between domains
  • Knowledge skills whose principles apply beyond their domain
  • Shared vocabulary or frameworks

Structural Health

Check for:

  • Skills with no tags or incomplete tags
  • Missing parent relationships
  • depends_on entries pointing to nonexistent skills
  • Registry entries whose location doesn't resolve to a file

Output Format

When asked for a system overview, produce:

=== SKILL LIBRARY OVERVIEW ===

Domains: {count}
Total Skills: {count} ({knowledge} knowledge, {action} action, {director} director, {orchestrator} orchestrator, {observer} observer)

--- {domain_name} ---
  Maturity: {level}/5 {bar}
  Orchestrator: {yes/no}
  Subdomains: {list}
  Skills: {count}
  Gaps: {list or "none detected"}

(repeat for each domain)

--- Cross-Domain ---
  Connections: {list or "none detected"}
  Conflicts: {list or "none detected"}

--- Recommendations ---
  1. {most impactful next step}
  2. {second priority}
  3. {third priority}

Philosophy

Skills grow like mycelium — each domain should develop organically based on what the user actually needs. Don't push for completeness for its own sake. A domain at maturity 2 that serves the user well is better than a domain at maturity 5 that nobody uses.

The Sentinel watches. The user decides.

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.

Versions

  • v0.1.0 Imported from the upstream source.