felipeblassioli

felipeblassioli/agent-skills

Plugin Claude Code

Felipe Blassioli's personal marketplace of Claude Code plugins — GCP/SRE observability tooling and skill-authoring governance. Public and personal; no warranty.

felipeblassioli/agent-skills

Agent Claude Code

Read-only Claude Code subagents wired for this repository. Each keeps its behaviour in a harness-agnostic system prompt (action language, model aliases not raw slugs, minimal read-only tools) so the ADR-0004 export adapter can retarget it to Codex / Cursor / other harnesses.

felipeblassioli/agent-skills

Agent Claude Code

Use before promoting or releasing a skill/plugin, or on demand, to review the marketplace tier for cross-artifact drift — marketplace.json vs each plugin.json, metadata.json vs CHANGELOG vs skill-registry.json versions, and skills that silently duplicate an existing artifact. Complements the per-skill…

felipeblassioli/agent-skills

Agent Claude Code

Use before a commit or push, or on demand, to scan staged, unstaged, or untracked changes for private or employer work references, non-personal identities, or leaked GitHub / Slack / Linear / GCP identifiers before they enter this public repository. Complements the deterministic scope-guard hook by catching…

felipeblassioli/agent-skills

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing scope-guard-pretooluse.sh via bash. From felipeblassioli/agent-skills.

felipeblassioli/agent-skills

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, executing validate-skill-on-edit.sh via bash. From felipeblassioli/agent-skills.

felipeblassioli/agent-skills

Settings file Claude Code

Agent settings declaring 2 hook events (PreToolUse, PostToolUse).

felipeblassioli/agent-skills

Cursor rule Cursor

This is felipeblassioli's personal agent-skills repository.

felipeblassioli/agent-skills

Cursor rule Cursor

Cursor rule "10-commit-conventions" from felipeblassioli/agent-skills, covering commit conventions, format, scopes, separation of concerns and rules.

felipeblassioli/agent-skills

Cursor rule Cursor

Cursor rule "20-skill-authoring" from felipeblassioli/agent-skills, covering skill authoring, required files, skill.md constraints, metadata.json schema and after any skill change.

felipeblassioli/agent-skills

Cursor rule Cursor

PR creation workflow for the agent-skills repo. Applied when creating pull requests, opening PRs, or preparing PR descriptions.

felipeblassioli/agent-skills

Cursor rule Cursor

Prevent PRs from being opened against wrong GitHub repository.

felipeblassioli/agent-skills

Cursor rule Cursor

Before changing a maintained artifact, classify its type and maturity using docs/ADR/ADR-0003-artifact-maturity-model.md and docs/specs/artifact-maintenance-workflow.md.

felipeblassioli/agent-skills

Instructions file GitHub Copilot

Instructions for felipeblassioli/agent-skills: Review changes under packs/ and the cursor-pack registry/scripts as installable runtime packaging, not as generic docs or JSON edits.

felipeblassioli/agent-skills

Instructions file GitHub Copilot

Instructions for felipeblassioli/agent-skills: Review skill-registry.json and skill-management scripts as part of the installable packaging contract for the repository.

felipeblassioli/agent-skills

Instructions file GitHub Copilot

Instructions for felipeblassioli/agent-skills: Treat rules-based skill changes as build-backed changes, not as markdown-only edits.

felipeblassioli/agent-skills

Instructions file GitHub Copilot

Instructions for felipeblassioli/agent-skills: Review changes under skills/ as installable skill packages, not as generic markdown edits.

felipeblassioli/agent-skills

Instructions file CodexOpenCode

AGENTS.md instructions for felipeblassioli/agent-skills, covering agents.md, repository overview, structure, authoring doctrine and artifact maturity workflow.

felipeblassioli/agent-skills

Instructions file

Claude Code instructions for felipeblassioli/agent-skills, a project described as: My personal official collection of agent skills, react ones forked from vercel.

felipeblassioli/agent-skills

Instructions file Gemini CLI

Gemini CLI instructions for felipeblassioli/agent-skills, a project described as: My personal official collection of agent skills, react ones forked from vercel.

felipeblassioli/agent-skills

Plugin Claude Code

Model routing (model-recommender), prompt authoring (smart-prompt), adversarial prompt review (prompt-audit), and escalation-tier tailoring (tailor-to-fable), driven by a shared, self-refreshing /.claude/model-profiles.md so routing never drifts between them or from loop-compiler.

felipeblassioli/agent-skills

Hook

Runs when a session starts, executing check-model-profiles.sh via bash. From felipeblassioli/agent-skills.

felipeblassioli/agent-skills

Skill Claude CodeCodex

Recommends which Claude model and effort level to run for a task. Classifies the task into an archetype → tier + effort using the rubric in /.claude/model-profiles.md, then resolves today's model string from that file's tiertomodel. Use when deciding which model to use, routing a task or phase to a model, picking an…

felipeblassioli/agent-skills

Skill Claude CodeCodex

Adversarially reviews a draft prompt against a versioned rule set to find what will make it underperform — archetype mismatch, wrong prescription level for the target model, the Fable reasoning-echo trap, negatives that should be positives, unstated expectations, rejected params, and more — then returns tagged…