Monitoring architect
Skill nevitonsantana/adaptive-skills/domain-packs/crisis-management/skills/monitoring-architect
38 portable Agent Skills for disciplined, reviewable AI-assisted work across Codex, Claude Code, GitHub Copilot, and compatible agents.
npx -y skills add nevitonsantana/adaptive-skills --skill monitoring-architectAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Design monitoring coverage as an operational sensing system with useful sources, tiers, keywords, noise filters, and readiness.
SKILL.md
1.9 KB, 351 tokens by cl100k_base, as published. Nobody here has run it
Overview
Use this skill when the work is about building or reviewing crisis monitoring coverage, not interpreting the crisis itself.
When to Use
- monitoring design
- source and tier planning
- coverage review
- noise reduction and readiness
When NOT to Use
- pure crisis analysis
- generic analytics with no monitoring architecture question
Core Moves
- Define the decision the monitoring must support.
- Choose the minimum sensing layers.
- Shape keywords, exclusions, tiers, and source mix.
- Review readiness and false confidence risks.
Optional Modules
- Source expansion — Assess whether more sources improve decisions or only add noise.
- Coverage risk — Describe which blind spots remain even after the proposed setup.
- Operational cadence — Note how the setup should be reviewed or tuned over time.
Activation Triggers
- Use source expansion when the request is to “monitor everything.”
- Use coverage risk when stakeholders may over-trust the setup.
- Use operational cadence when the monitoring will stay active for a while.
Expected Output
- monitoring design
- coverage logic
- readiness note
- blind-spot note
Verification
- The setup supports a real decision.
- Noise and coverage were both considered.
- Blind spots are explicit instead of hidden.
Handoff Signals
- The next move is crisis analysis or implementation work.
- A product or data contract change is required to support the architecture.
Pairs Well With
crisis-analystfeature-planning
Anti-patterns
- Treating source count as coverage quality.
- Designing monitoring with no decision in mind.
- Ignoring the cost of false confidence.