mqmalagris

@mqmalagris source repo

28 skills
0 followers
9 hours ago last updated

▌
SEO · mqmalagris bundle
Deterministic LLM-first SEO audits for websites, blog posts, and GitHub repositories. Use this when the user asks to "perform SEO analysis", "run SEO audit", "analyze SEO", "check technical SEO", "review schema", "Core Web Vitals", "E-E-A-T", "hreflang", "GEO", "AEO", or GitHub repository SEO optimization. For full/page/repo audits, run bundled scripts for evidence and return prioritized, confidence-labeled fixes.

0
installs
▌
Heist · mqmalagris bundle
Turn a settled feature scope into a concrete implementation plan and write it to docs/plans/NNNN-<slug>.md. Plans the job like a heist — crew (files touched), sequence (ordered tasks), getaway (rollback/risks), payoff (acceptance criteria). Use when user has a PRD, ADR, or settled feature spec and wants a step-by-step build plan before coding. Triggers on /heist, "plan this feature", "implementation plan", "break this down", "how do we build X", or after to-prd / compass when ready to code.

0
installs
▌
Semver · mqmalagris bundle
Decide the correct Semantic Version bump for a change (major/minor/patch) by analyzing the diff against the project's public surface and running the ecosystem's breaking-change detector, then apply it (bump the manifest + changelog). Stack-agnostic, detects Rust/Cargo, npm/pnpm/yarn, Go modules, Elixir/Hex, Python, or a plugin.json/VERSION file from whatever manifest is present. Use when deciding a version bump, judging whether a change is breaking, choosing what version to release, reviewing an API or public-surface change for compatibility, or before tagging a release. Triggers on SemVer, semantic versioning, major/minor/patch, breaking change, "what version", "bump version", or /semver.

0
installs
▌
To Prd · mqmalagris bundle
Turn the current conversation context into a PRD and publish it to GitHub Issues, also persisting it to docs/prds/NNNN-<slug>.md for downstream skills (heist, maestro). Use when user wants to create a PRD from the current context. Triggers on /to-prd, "write a PRD", "draft a PRD", "spec this out", "feature spec", or after /grill-me when scope and Glossary are settled.

0
installs
▌
Compass · mqmalagris bundle
Software engineering coach for architecture, design, principle-based code review, refactoring, testing, DevOps, and concept explanation. Use when the user wants help architecting a system, choosing a paradigm or pattern, getting design advice before coding, reviewing code against engineering principles, refactoring smelly code, deciding a testing strategy, or explaining SE concepts (SOLID, GoF patterns, MVC, microservices, TDD, CI/CD, etc.). Triggers on /compass, "swe-compass" (legacy), "software design advice", "architecture review", "refactor this", "review code against principles", or any request involving design principles, design patterns, software architecture, or engineering trade-offs. For line-by-line bug-hunting on a diff/PR, defer to the dedicated code-review skill. Stack-agnostic by default — discusses stack with the user, defers to user's final choice, then optimizes patterns for that stack.

0
installs
▌
Maestro · mqmalagris bundle
Verify plans, PRDs, and ADRs for parallel-execution feasibility, build a conflict graph from files-touched data, judge whether parallelizing is actually worthwhile, then orchestrate agents in git worktrees to implement, test, and clean up when it is. Use when the user asks to parallelize work across plans, run plans concurrently, split feature work across multiple agents, set up git worktrees for several plans, dispatch agents to implement plans, check if PRDs/ADRs/plans conflict, decide if work from the same or different phases can run in parallel, or runs /maestro.

0
installs
▌
Brag Doc · mqmalagris bundle
Maintain a monthly brag document (accomplishment log) and roll it up into a promo packet, self-review, or CV material. Blends Lucas Faria's 4-field monthly template with Julia Evans' impact-first categories. Use when the user wants to log what they shipped, prep for a performance or promotion cycle, write a self-review, remember work from months ago, feed achievements to cv-craft, or runs /brag-doc. Modes: draft, example, review, compile. Targets: work (employment, any employer), side (public / side-project work).

0
installs
▌
Cv Craft · mqmalagris bundle
Maintain a canonical master CV in Markdown and produce tailored, ATS-friendly resumes and recruiter-screen prep packs from job descriptions. Supports four modes — bootstrap (build master from scratch via interview), sync (import existing resume in any format into master, with optional standalone rewrite output), tailor (generate CV matched to a JD), and screen-prep (draft answers for first recruiter-call questions). Use when the user asks to update their CV/resume, rewrite an existing CV, tailor a resume to a job posting, prepare for a recruiter screen, import a resume PDF/docx into Markdown, or runs /cv-craft.

0
installs
▌
Dev Flow · mqmalagris bundle
Route a dev task through the right subset of the canonical skill chain (adhd → grill-me → to-prd → compass → heist → maestro → code → review-pass → pr-craft), matching ceremony to stakes. Detects the task tier (bug / feature / architecture / client), shows the exact chain it will run and what it skips, confirms, then drives the sub-skills in order — pausing where each needs user input. Use when the user says "start a feature", "new feature", "kickoff", "route this through the workflow", "run the chain", "which skills for this", or /dev-flow. NOT for tasks already mid-chain (a PRD/plan exists) — invoke the specific next skill instead.

0
installs
▌
Grill Me · mqmalagris bundle
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree, then emitting a Design Notes + Glossary + edge-case block and persisting it to docs/intent/NNNN-<slug>.md for handoff to /to-prd. Use when user wants to stress-test a plan, get grilled on their design, do a pre-PRD design review, challenge an idea before writing it up, or mentions "grill me" or runs /grill-me.

0
installs
▌
LLM Wiki · mqmalagris bundle
Build and maintain an LLM-maintained wiki — a persistent, interlinked Markdown knowledge base distilled from curated raw sources (Karpathy's LLM Wiki pattern). Three operations: ingest (read a source, write and update pages, log it), query (answer from the wiki with citations, file good answers back), lint (contradictions, stale claims, broken links, orphans). Path-agnostic: the user picks where the wiki lives, the skill remembers it. Works on a fresh directory, a repo's docs/, or an existing memory directory. Use when the user wants to file a document or incident writeup into their knowledge base, asks what their notes say about a topic, wants the wiki checked for contradictions or staleness, mentions an LLM wiki, Memex, or second brain, or runs /llm-wiki.

0
installs
▌
Pr Craft · mqmalagris bundle
Create a pull request with a structured, concise description derived from the diff and conversation context. Use when the user asks to "create a PR", "open a PR", "PR to <branch>", "raise a pull request", or wants the full branch → commit → push → gh pr create flow. Also opens GitHub-native stacked PRs — an ordered series of dependent PRs, one per layer — when the user says "stack this", "stacked PR", or the change is too large/layered to review as one. Produces a body with Problem / Root cause / Fix / Test / Out of scope sections and references task/ticket IDs.

0
installs
▌
Sentinel · mqmalagris bundle
Close the loop after ship — scan a repo (and optionally its live prod signal) for post-release trouble, then file what it finds as docs/intent/NNNN-<slug>.md so it re-enters the dev-flow chain as ordinary work. Detects recurring fix classes, reverts, and threshold breaches on the outcome metric a feature named at plan time. Read-only on code — it never fixes, commits, or opens a PR. Use when the user says "sentinel", "what's rotting", "post-ship check", "did anything regress", "watch this repo", "maintain scan", or runs /sentinel — and as the scheduled Maintain stage that dev-flow's chain ends without.

0
installs
▌
Aso Craft · mqmalagris bundle
App Store Optimization for iOS and Android from one per-locale Markdown source. Probes keyword candidates against live App Store data for competitor density, incumbent difficulty and search intent (free, no API key), assigns each surviving term to the surface that actually indexes it per store, then lints the listing: hard character limits, target-keyword coverage gaps, keyword budget spent twice, keyword stuffing, and URLs or support emails broken by translation. Use when the user wants to do ASO, research or validate app store keywords, pick an app name / subtitle / short description / keyword field, check store metadata character limits, localize a store listing for search, audit why an app is not ranking, prepare an App Store or Play submission, or runs /aso-craft.

0
installs
▌
Periscope · mqmalagris bundle
Role-play a senior / staff / principal engineer looking at your company, then sweep the surfaces you grant it for opportunities across three lenses: tech (decisions forming, uncaught risk, missing conventions), product (problems unvalidated, outcomes uninstrumented), and org (knowledge siloed, friction repeating, decisions with no owner). Returns at most 5 ranked openings, each with the specific first move and a ready-to-approve draft. Built on the principle "promotions lag behavior: you operate at the next level first, the title follows." Surfaces and tools are declared by the user at onboarding, never assumed. Read-only by default; never posts without explicit per-message approval. Logs approved contributions to an evidence trail that feeds brag-doc. Use when the user says "periscope", "senior scan", "staff scan", "promo scan", "what needs my attention", "where should I weigh in", "where can I have the most impact", "any opportunities", "catch me up", or wants more scope, visibility, or to operate above the

0
installs
▌
Code Craft · mqmalagris bundle
Language- and framework-specific code best practices and idioms — complementary to compass (stack-agnostic architecture coach). Two modes: reader (rule + reason + example for a topic) and reviewer (apply rules to user code, flag violations with fixes). Ships rules for TypeScript, Rust, CSS/SASS, Tailwind, Dart, Go, Python and frameworks React, Next.js, RN+Expo, Hono, Cloudflare Workers, Astro, Svelte, Drizzle, Supabase, AWS Lambda+SAM, Terraform, Flutter. Use when the user asks for language-specific best practices ("TS best practices", "is this idiomatic Rust", "/code-craft ts"), wants a code review focused on language idioms (not architecture — see compass), or asks how to do X the right way in a specific language/framework.

0
installs
▌
Babysit Prs · mqmalagris bundle
Babysit a GitHub PR from review all the way to MERGED. Fetches all feedback (human + bot reviews like Copilot/Qodo/CodeRabbit, inline review threads, top-level reviews, issue comments, and CI check status), triages each item for validity, fixes the valid ones, posts a per-item fix report referencing the commit, resolves the addressed threads, then self-schedules the next pass (its own loop, no /loop prefix needed) and keeps going until the PR is merged. Use when the user says "babysit this PR", "watch the PR", "address the PR feedback", "keep checking the PR until it's merged/good", "handle the review comments", or runs /babysit-prs. Stack-agnostic — any gh-based repo, any language.

0
installs
▌
Cagan Check · mqmalagris bundle
Apply Marty Cagan product principles (Inspired, Empowered, Transformed) plus Teresa Torres' Continuous Discovery to a software dev's workflow from the Product Trio's engineering seat. Runs structured reviews for feature kickoff, sprint planning/estimation, client discovery calls, and pull requests — checking problem framing, outcome metrics, the five big risks (value/usability/feasibility/viability/ethical), feature-factory smells (incl. Cutler 2025 updates: high WIP, Team Tetris, success theater), prototyping fit, instrumentation, customer touchpoint cadence. Outputs green/yellow/red flags per dimension with concrete next actions. Use when user says /cagan-check, "starting a feature", "vou começar feature", "kickoff", "planning", "estimativa", "estimation", "discovery", "review this PR" with feature context, or asks to apply Cagan/SVPG/Torres/product-trio thinking. Adapts to the reader's employment context — in-house product team, or client-services work (agency, consultancy, contractor) where a paying stake

0
installs
▌
Review Pass · mqmalagris bundle
Single review-only entry point for an existing diff — runs a live-run check (`/run`) → code-review → implementation-review (and security-audit only when the change touches a trust boundary), then consolidates every finding into one go/no-go verdict. Use when you have a change ready and want it reviewed without running the whole dev-flow build chain. Triggers on /review-pass, "review this diff", "review my changes", "is this ready to commit", "give this a once-over". NOT for reviewing a remote GitHub PR (use /code-review) or for a task still being built (use /dev-flow).

0
installs
▌
Audit Report · mqmalagris bundle
Render audit findings as a designed, paginated A4 PDF report with a cover page, severity donut and category bar charts, colored severity chips, evidence-backed strengths, prioritized recommendations, and copy-ready GitHub issue blocks. English by default, with a pt-BR label pack for when the user is working in Portuguese. Self-verifying (page count plus page rasterization before delivery), and it leaves a re-runnable generator script beside the report. Use when the user asks for a security audit report as a PDF, a findings report with charts, a formatted deliverable from a code review or audit, GitHub issue text generated from findings, or says "gere um relatório em PDF" / "relatório de auditoria". Pairs with /wstg mode 2 (which produces the findings) and works for any audit, not only security. Runs in an isolated venv, installs nothing globally.

0
installs
▌
Commit Report · mqmalagris bundle
Generate a work report tunable to audience (dev / pm / client) and deliver it as a copy-ready channel block or a written doc. Two modes: `quick` (git-only, zero-config — prose + bullets from the current repo) and `standup` (multi-source — GitHub PRs/reviews/comments + git across repos + deploys + optional tracker, framed as an impact narrative). Use when the user asks for a standup, status update, work summary, "what did I ship today", commit recap, end-of-day report, PM/client update, a report to paste into a channel, or a standup doc — or runs /commit-report. Triggers on "write a report", "summarize commits", "standup", "report for the PM", "update for the client", "send a report", "what did I do today/yesterday". Default delivery is a copy-ready block; `--doc` writes the full report to a file; `--metrics` appends flow metrics (human review coverage, rework depth, artifact lag, spec churn, caught-vs-escaped defects, recurring fix classes) derived from git and gh. Quick mode default scope = `--since-mine` (c

0
installs
▌
Publish Skill · mqmalagris bundle
Publish one of the user's own skills from ~/.claude/skills to the mqmalagris/agent-skills GitHub repo — copies the skill under skills/<name>/, mints its .claude-plugin/plugin.json, upserts the marketplace.json entry, bumps its version, and opens a PR against main (CI-gated). Use when the user says 'publish this skill', 'push <skill> to my repo', 'add <skill> to agent-skills', 'ship this skill', or wants a locally-authored skill added to their public skill collection. NOT for third-party skills (those go in THIRD_PARTY.md, not vendored) or for editing skill content.

0
installs
▌
Portfolio Sync · mqmalagris bundle
Sync the current project into a central project-portfolio Markdown archive — a comprehensive log of every project the user has worked on (stack, role, scope). Path-agnostic: the user picks where the archive lives, the skill remembers it. Gathers project signals (git log, manifests, README, structure), matches existing entries by folder name, proposes add/amend for user confirmation before writing. Use when user asks to update their portfolio, log a project, sync the archive, document the current project, or runs /portfolio-sync. Distinct from cv-craft (which produces actual CVs from this archive as source).

0
installs
▌
Security Audit · mqmalagris bundle
Focused security review of a CHANGE (a diff, a branch, a PR), layered on the wstg-security-testing skill. Finds HIGH-CONFIDENCE, concretely exploitable vulnerabilities the change newly introduces (injection, broken authn/authz, secrets and data exposure, unsafe deserialization, crypto misuse, SSRF) and audits dependencies when a lockfile moved, using the repo's own package manager. Runs as Check 7 of /implementation-review, and standalone when the user says 'review this diff for security', 'is this change safe', 'security-check my PR', 'threat check this branch', or before shipping something that touches auth, user input, secrets, or untrusted data. NOT for whole-codebase or posture audits ('audit this repo', 'is my app secure', 'find every IDOR', 'auditoria de seguranca') — this skill is diff-scoped and its precedents suppress absence-shaped findings, so on a codebase-wide ask it can report clean on a vulnerable repo; route those to /wstg mode 2. Maps findings to WSTG IDs via /wstg, then reports only finding

0
installs
▌
Parallel Worktrees · mqmalagris bundle
Playbook for running work in parallel across git worktrees, so several agents (or one agent dispatching many) edit the same repo at once without colliding. Covers the go/no-go decision, partitioning files so agents don't touch the same file, which isolation mechanism to use (Agent isolation:worktree, Workflow isolation:worktree, EnterWorktree, or manual git worktree), and integrating + cleaning up afterward. Use when the user says 'work in parallel', 'multiple agents', 'fan out', 'dispatch agents', 'git worktree', 'parallelize this across worktrees', or wants concurrent work on one codebase. Defers to /maestro when formal plans/PRDs/ADRs already exist to parallelize.

0
installs
▌
Testing Philosophy · mqmalagris bundle
Defines what a good test is: behavior over implementation details, and the Testing Trophy with a hard floor on end-to-end coverage for user-facing features. Stack-agnostic, any language (TS/JS, Rust, Go, Elixir, Python, ...) and any layer (frontend, backend, CLI, library). REQUIRED BACKGROUND for skills that plan or review tests (implementation-review, heist, review-pass). Use when proposing, writing, or reviewing automated tests, or when the user asks whether tests are good, what to test, why a test is brittle, or whether e2e is needed.

0
installs
▌
Implementation Review · mqmalagris bundle
Pre-commit quality gate. Invoke before every git commit, after the live-run check (/run). Seven checks run as parallel subagents: plan gaps, use-case coverage gaps, missing test scenarios, test-philosophy violations (Kent Dodds Testing Trophy), SOLID violations, Clean Code violations, and security vulnerabilities (via /security-audit, which layers on /wstg). Surfaces findings before they land in history. Also invoke when the user says 'review this', 'am I done', 'did I miss anything', or 'check the quality'.

0
installs
▌
Wstg Security Testing · mqmalagris bundle
Web application security testing using the OWASP Web Security Testing Guide (WSTG) methodology — its 12 categories and ~109 test cases (INFO, CONF, IDNT, ATHN, ATHZ, SESS, INPV, ERRH, CRYP, BUSL, CLNT, APIT). Four modes — guide an authorized pentest, self-review your own app, generate/score a coverage checklist, or review a code diff/PR against relevant WSTG tests. Mode 2 is the whole-codebase audit path and carries a systematic protocol (reference/CODEBASE-AUDIT.md) for stack detection, route-handler enumeration, tenant-isolation sweeps, frontend-gate-to-endpoint cross-referencing, and secret sweeps across git history and deploy configs. Bundles the full test reference, detection payloads, a reporting template, and scripts to look up WSTG IDs and build/score checklists. Use when the user mentions OWASP WSTG, web security testing, pentesting a web app or API, security review against WSTG, XSS/SQLi/SSRF/IDOR/auth/session/CSRF/JWT testing, multi-tenant or RLS isolation gaps, hardcoded secrets, a WSTG-XXXX-NN ID

0
installs

28 published skills