Detect Fix Probe
by Shippers
verify honest detection
- Verify strict adherence to zero-output constraints
- Test model honesty during draft generation phases
- Audit agent behavior for hidden instruction leakage
Free
See it in action
You say
Run a probe on the draft detection logic to ensure it returns no output as specified.
Your agent does
None.
Free
Included in download
- Downloadable skill package
- Instant install
See it in action
You say
Run a probe on the draft detection logic to ensure it returns no output as specified.
Your agent does
None.
About This Skill
The problem
Manual testing for "hallucination" or non-compliance in draft detection prompts is tedious and inconsistent. Developers need a reliable way to verify if their agents are following strict output constraints during the drafting phase.
What it does
- Identifies honest draft detection anomalies in agent responses.
- Probes for hidden prompt leakage during the output generation cycle.
- Verifies that "None" output constraints are strictly followed when conditions are met.
Why this beats prompting it yourself
This skill handles the edge cases of silence and negative constraints that standard prompts often fail to maintain. It ensures the agent stays within the defined probe boundaries without producing extraneous conversational filler.
Use cases
- Unit testing agent compliance for negative constraints.
- Verifying draft security protocols in automated pipelines.
- Stress testing model honesty when instructed to produce zero output.
Use Cases
- Verify strict adherence to zero-output constraints
- Test model honesty during draft generation phases
- Audit agent behavior for hidden instruction leakage
Known Limitations
- Effectiveness varies by model base training.
- Not designed for complex data extraction.
- May requires manual oversight for nuanced constraint violations.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/detect-fix-probe -o /tmp/detect-fix-probe.zip && unzip -o /tmp/detect-fix-probe.zip -d ~/.claude/skills && rm /tmp/detect-fix-probe.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Compatible with SKILL.md-compatible agents
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
diagnosing-rag-failure-modes
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
cinematic-sites
Turn any basic business URL into a high-end cinematic landing page with AI-generated 4K assets and GSAP animations.
ai-automation-qa-pack
Professional QA & UAT documentation generator for AI automation agencies and complex agent deployments.