improve monitoring-security skill with concrete configs and validation

[fernandezbaptiste]

hey @rayjun, nice work building out a full set of Claude Code skills for your ai-coding-context project. Kudos on the structured approach with 6 skills covering everything from debugging to vault management! I've just starred it.

ran your monitoring-security skill through agent evals and spotted a few quick wins that took it from ~65% to ~86% performance:

• added copy-paste-ready configuration examples for Docker Compose (network isolation + non-root), Prometheus Basic Auth, Grafana RBAC, and Nginx TLS reverse proxy, replacing the abstract guidance that scored low on actionability

• replaced the flat 4-step implementation list with a sequenced 5-step protocol (network isolation, auth, TLS, secrets, verification) with explicit validation checkpoints and expected outputs at each stage

• condensed the redundant core patterns section (which duplicated the quick reference table) and added a concrete verification step with 6 specific commands to confirm TLS, auth, security headers, and container user

this means you and your contributors get an instant quality signal and improvement suggestions before you review.

these were easy changes to bring the skill in line with what performs well against Anthropic's best practices. honest disclosure, I work at tessl.io where we build tooling around this. not a pitch, just fixes that were straightforward to make.

if you want to review your other skills, two options: I can open a follow-up PR with a GitHub Action that auto-scores skill.md changes on every PR (no signup, no token needed - it runs fully in CI with pinned versions you can inspect). this means you and your contributors get an instant quality signal and improvement suggestions before you review.

Alternatively, if you'd rather do it yourself, spin up Claude Code and run tessl skill review --optimize for your other skills.

happy to answer any questions on the changes.

[rayjun]

Are you using AI to create PRs in bulk?