MiguelPecegueiro

@miguelpecegueiro source repo

8 skills
0 followers
13 hours ago last updated

▌
Grill Me · miguelpecegueiro
Run a pre-build architectural alignment interview before implementation begins. Use when the user says "grill me", "grill me on this", "let's do a grill me session", or "I want to lock decisions before building". The goal is to surface assumptions, resolve ambiguities, and lock architectural decisions one at a time so that implementation starts from a shared and documented understanding. Claude acts as a discussion partner and devil's advocate — not as the agenda driver.

0 installs
▌
Create Pr · miguelpecegueiro
Create a pull request for the current feature branch. Use when the user says "create PR", "open a PR", "create-pr", or "submit this for review". Reads the diff and commit history, writes a clear PR description using the What/Why template, and opens the PR via gh CLI. Always targets the default branch unless told otherwise.

0 installs
▌
Review Pr · miguelpecegueiro
Review pull requests thoroughly, then deliver a short GitHub-ready comment (2-4 lines) plus optional detailed notes only when asked. Use when the user asks for a PR review, code review on a pull request link, or review feedback to post on GitHub. Also handles security-focused PR reviews when the user asks to "check for bad practices", "security review this PR", or "scan the diff for vulnerabilities" — in that case follow the Security lens section.

0 installs
▌
Write Docu · miguelpecegueiro
Write complete technical documentation for the current project or codebase. Use when the user says "write-docu", "write documentation", "document this project", or "generate docs for this repo". Analyses the full codebase, creates or updates markdown files in the docs/ folder, and produces documentation detailed enough for someone picking up the project for the first time to understand how it works, how it is structured, and how to implement a feature or hotfix.

0 installs
▌
Security Scan · miguelpecegueiro
Run a full security audit of the current codebase and produce a dated findings report saved to docs/. Use when the user says "security scan", "run security-scan", "audit this codebase for security issues", or "I need ISO 27001 evidence for this repo". Also triggers before a major release or after a significant feature is merged. Output is a markdown report saved to docs/security-scan-YYYY-MM-DD.md.

0 installs
▌
Feature Session · miguelpecegueiro
Manages persistent session memory files per Asana task. Use when the user says "start session GC-123", "update session GC-123", "close session GC-123", "show session GC-123", or "list sessions". Files live at repo root and are safe to commit. Multiple team members can load the same session on their own machines. Session memory is opt-in per feature — not automatic.

0 installs
▌
Vibe Code Intake · miguelpecegueiro
Analyse a codebase and produce a Vibe-Code Confidence Score (0–100) plus a classification of authorship style. Use as a pre-step before any code review, intake, or audit when the origin of the code is unknown or suspected to be AI-generated without engineering oversight. The score and classification determine the review posture for subsequent analysis. Trigger whenever someone shares a codebase, repo, or set of source files and asks about code quality, authorship, or whether it was AI-generated. Also triggers on "run vibe-code-intake", "score this codebase", or "is this vibe-coded".

0 installs
▌
Generate Cursor Context · miguelpecegueiro
Generates or regenerates the .cursor/rules/context.mdc file for a GoConnection repository. Use this skill whenever you need to initialise Cursor rules for a repo, update the rules after significant changes to the codebase or docs, or when context.mdc is missing, stale, or incorrect. Triggers on phrases like "generate cursor context", "update cursor rules", "initialise repo rules", "create context.mdc", or "cursor rules are out of date". Always use this skill rather than writing context.mdc manually.

0 installs

8 published skills