felipeblassioli

felipeblassioli/agent-skills

Agent Claude CodeCursor

Use when benchmark or comparison results need a concise evidence-based analysis of what changed, what patterns matter, and which follow-up should happen next.

felipeblassioli/agent-skills

Agent Claude CodeCursor

Use when adapting a source tree into a Cursor pack or bundled skill and you need a quick artifact matrix, source classification, or migration concerns before scaffolding.

felipeblassioli/agent-skills

Agent Claude CodeCursor

Use when two candidate outputs should be compared blindly without knowing which skill or pack variant produced them.

felipeblassioli/agent-skills

Agent Claude CodeCursor

Use when grading eval outputs for an authoring workflow against explicit expectations and collecting evidence into grading.json.

felipeblassioli/agent-skills

Agent Claude CodeCursor

Use when comparing two skill source trees for package shape, trigger quality, hot-path size, supporting resources, safety, and repository fit before or alongside behavior evals.

felipeblassioli/agent-skills

Cursor rule Cursor

When authoring Cursor packs or installed bundled skills, keep skills, packs, rules, subagents, and docs separated by purpose rather than copying mixed source trees directly.

felipeblassioli/agent-skills

Cursor rule Cursor

After substantive skill or pack-authoring changes, prefer a small eval loop with explicit expectations, evidence-based grading, and review output rather than relying on prose confidence alone.

felipeblassioli/agent-skills

Skill Claude Code

Audit and improve existing Cursor skills and packs, and review installed or repository-first-party skill portfolios for overlap, trigger collisions, and compliance with docs/architecture.md. Covers single-skill compliance review, diagnostic improvement recommendations for an existing skill or pack, lightweight…

felipeblassioli/agent-skills

Skill Claude Code

Maintain governed root skills, pack-bundled skills, Cursor packs, and repo scripts/tools in felipeblassioli/agent-skills. Covers SemVer bumps with the bundled bump scripts, registry alignment (skill-registry.json, cursor-pack-registry.json), release-artifact refreshes (CHANGELOG, VERIFICATION, ROADMAP, RELEASE-POLICY…

felipeblassioli/agent-skills

Skill Claude Code

Write, adapt, and validate Cursor skills and packs in felipeblassioli/agent-skills. Covers greenfield skill authoring through Socratic discovery, distilling reference material into a skill, scaffolding a pack under packs/ /, evaluating an external skill candidate before import, decomposing a Claude-style plugin into…

felipeblassioli/agent-skills

Cursor rule Cursor

Persistent project guidance for one narrowly scoped behavior.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when creating or evaluating an architecture decision record, choosing between technologies with trade-offs, or documenting a design decision for a new component or service.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when reviewing code changes for correctness, security, performance, maintainability, or merge readiness, especially from a PR URL, diff, or set of changed files.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when behavior diverges from expectations, an error or stack trace needs diagnosis, or something broke after a deploy and the root cause is not yet obvious.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when preparing to deploy a service or release, especially when verifying tests, approvals, migrations, feature flags, rollback triggers, or post-deploy checks.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when writing or updating technical documentation such as READMEs, API docs, runbooks, architecture docs, or onboarding guides.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when triaging a production incident, drafting status updates, assessing severity, coordinating mitigation, or writing a blameless postmortem after resolution.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when preparing a daily standup update, summarizing recent work into yesterday, today, and blockers, or turning rough notes and recent activity into a concise team update.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when designing a system, service, or architecture from requirements and constraints, especially for API design, data modeling, service boundaries, scale, or reliability trade-offs.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when auditing technical debt, prioritizing refactors, evaluating code health, or building a maintenance backlog with impact, risk, and effort trade-offs.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Use when designing a test strategy, choosing test types and coverage priorities, or building a test plan for APIs, data pipelines, frontend systems, or infrastructure.

felipeblassioli/agent-skills

Agent Claude CodeCursor

Reads and analyzes Google Cloud application logs for Cloud Run services, Cloud Run-backed functions, Cloud Functions, and GKE or Kubernetes workloads. Use when investigating errors, latency, unexpected behavior, or trace-linked requests without flooding the parent context with raw log JSON. Applies discovery-first…

felipeblassioli/agent-skills

Cursor rule Cursor

Production and sensitive-data guardrails for GCP log investigations: discovery-first queries, bounded windows, redaction, and concise summaries.

felipeblassioli/agent-skills

Agent Claude CodeCursor

Adapts the reusable node-test-verifier pack to a specific repository by inspecting package.json, local agent guidance, and test scripts, then writing a canonical repo-local verifier contract plus any thin overlay references needed by the project.