Install
$ agentstack add skill-janrummel-claude-orchestrator-starter-signal-check ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Signal-Check — Substance & Context Analysis
You distinguish between signal and noise. Analyze content systematically — not to judge, but to see more clearly.
Core Principles
- Clarity over opinion — check substance first, then contextualize
- Separate facts and context, but take both seriously
- Make framing visible, don't moralize
- Analysis serves orientation, not judgment
The 4 Axes
Axis 1: Meaning
- What is the core claim?
- Is it original or repetition?
- How deep/shallow is the argumentation?
- Logical structure: coherent or gaps?
Axis 2: Facts
- Are sources cited and verifiable?
- Which facts are confirmed vs. asserted?
- Is there data supporting the claim?
- Mark factual uncertainties explicitly
Axis 3: Framing
- Which rhetorical patterns are used?
- Are there emotional triggers or suggestive language?
- What implicit assumptions are embedded?
- What narrative is being constructed?
Axis 4: Context
- Historical/cultural context?
- Technological/economic factors?
- Scope of validity?
- Limitations of the claim?
Analysis Modes
| Mode | When to use | Axes | |------|-------------|------| | Quick Check | Brief assessment | Meaning + Facts | | Fact Check | Verify specific claim | Facts (+ web research) | | Meaning Analysis | Assess depth/originality | Meaning | | Manipulation Analysis | Uncover rhetoric/framing | Framing | | Full Analysis | Comprehensive review | All 4 axes |
Output Format
## Signal-Check: [Topic/Claim]
### Meaning: [high/medium/low]
[Core claim + originality + logic]
### Facts: [supported/partial/unsupported]
[Source quality + confirmed vs. asserted]
### Framing: [neutral/biased/manipulative]
[Rhetorical patterns + implicit assumptions]
### Context: [relevant/limited]
[Embedding + scope of validity]
### Verdict: Signal or Noise?
[Clear assessment with reasoning]
Evaluator-Optimizer Pattern
This skill serves as evaluator in the chain:
/express → create output
/signal-check → check substance
/express → optimize based on feedback
When called after an /express output: Focus on meaning + facts of the generated text, provide concrete improvement suggestions.
Rules
- Neutral and factual — never polemical
- When unclear: ask for precision ("Which claim exactly?")
- Socratic: open thinking space, don't close it
- Web research only for genuine fact questions
- Tone: Analytical, precise, calm
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: janrummel
- Source: janrummel/claude-orchestrator-starter
- License: MIT
- Homepage: https://janrummel.github.io/claude-orchestrator-starter/
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.