gufranco
- 42 skills
- 0 followers
- 1 hour ago last updated
- ▌ Pr Summary · gufrancoGenerate a PR summary with reviewer suggestions based on file ownership. Fetches PR data, summarizes changes, highlights risks, and recommends reviewers from git history. Use when user says "pr summary", "summarize this PR", "who should review this", "generate PR description", when /morning finds a description that drifted from its diff, or wants a reviewer-ready summary of a pull request. For code review, use /review; for creating PRs, use /ship pr; for checking CI status, use /ship checks.
- ▌ Cross Model · gufrancoConsult a different model for orthogonal reasoning on a consequential decision, especially when confident. Discovers whichever model CLI is installed rather than assuming a vendor. Use when the user says "second opinion", "cross-model", "ask another model", "stress-test this", "what am I missing", "red-team this decision", or before committing to an architecture, a schema, a security boundary, or anything hard to reverse. For a reversible local decision or routine implementation, proceed directly; for a question with one verifiable answer, read the source instead.
- ▌ Investigate · gufranco bundleSystematic debugging with hypothesis testing, bounded retries, and optional edit freeze. Use when user says "debug this", "investigate", "why is this failing", "find the bug", "trace this error", "root cause", or needs structured debugging beyond reading an error message. For incident postmortems, use /incident; for code review, use /review; for running tests, use /test.
- ▌ Session Log · gufrancoSummarize the current session's files changed, tests run, commits, and decisions as handoff or standup notes.
- ▌ Concise Mode · gufrancoOpt-in terse-reply mode that drops articles, pleasantries, filler, and hedging while keeping full technical accuracy. Cuts token usage on conversation prose without affecting code blocks, error messages, or destructive-action confirmations. Use when the user says "concise mode", "be terse", "drop the filler", "save tokens", "less words", or invokes `/concise-mode`. Disable when the user says "normal mode", "stop concise", or "back to normal".
- ▌ Interview Me · gufrancoOne-question-at-a-time intent clarification for underspecified or ambiguous asks. Drives toward 95%+ intent confidence before any implementation. Use when user says "interview me", "grill me", "are we sure?", "stress-test my thinking", or when the request is too vague to act on without guessing. Use only while the request is underspecified; a concretely specified task proceeds straight to the work.
- ▌ Module Audit · gufranco bundleSurvey a codebase for shallow modules and produce a ranked report of consolidation opportunities with before-and-after diagrams.
- ▌ Review · gufranco bundleReview code, run QA analysis, or audit visual design, with subcommands code (default), qa, and design. Three-pass code review with 71-category checklist, 30-rule QA analysis with PICT and coverage delta, and frontend design/accessibility/performance/SEO audit. Use when user says "review this PR", "review my code", "check this diff", "QA analysis", "test coverage gaps", "design audit", "check accessibility", "check performance", "check SEO", or wants feedback on a specific change. For full architecture assessment, use /assessment; for security scanning, use /audit; for shipping code, use /ship.
- ▌ Cleanup · gufrancoList stale branches, long-open PRs, merged branches, and orphaned worktrees, then close or delete each one with confirmation.
- ▌ Explain · gufrancoExplain code with educational depth. Generates Mermaid diagrams for architecture and data flow, traces data through the codebase, explains design decisions with rationale, identifies patterns, and suggests improvements. Use when user says "explain", "explain this code", "how does this work", "walk me through", "what does this do", "trace the data flow", or wants to understand a file, directory, or system with educational depth. For code review, use /review; for debugging, use /investigate; for architecture assessment, use /assessment.
- ▌ Migrate · gufrancoMigrate a framework or library, or upgrade a major version, along the official migration path with one tested commit per step.
- ▌ Morning · gufranco bundleCross-account work triage. Sweeps every authenticated GitHub, GitLab, and Bitbucket identity plus the organizations they belong to, finds every pull request, issue, review request, and mention that demands a response, ranks by who is blocked, writes a dated report, then works the queue with per-item consent. Use when user says "morning", "inbox", "triage", "standup", "sweep", "rounds", "daily", "varredura", "what needs my attention", "what is waiting on me", or wants a start-of-day pass across all accounts. For a single pull request's review comments, use /respond; for performing one review, use /review; for one repository's branch hygiene, use /cleanup; for merging and deploying, use /deploy.
- ▌ Onboard · gufrancoOnboard to a new codebase with structured exploration. Scans the project, generates an architecture map with Mermaid diagrams, identifies entry points, explains the tech stack, lists key patterns and conventions, and produces a "start here" guide. Use when user says "onboard", "new project", "understand this codebase", "what does this project do", "walk me through the project", "project overview", or joins a new team or repository. For explaining a single file, use /explain; for code review, use /review; for assessment, use /assessment.
- ▌ Profile · gufrancoPerformance profiling and bottleneck identification. Measures database statements and time per request on the running app, scans the code for bottleneck patterns, ranks findings by impact, and suggests specific optimizations. Use when user says "profile", "why is this slow", "find bottleneck", "performance issue", "slow query", "slow endpoint", "optimize", or needs to find what is causing poor performance. For benchmark comparisons, use /benchmark; for load testing, use /test perf; for general code review, use /review.
- ▌ Resolve · gufrancoGuided merge conflict resolution with verification. Shows each conflict with context from both branches, suggests resolution based on understanding both changes, verifies tests pass after resolution, and checks that no functionality was lost. Use when user says "resolve conflicts", "merge conflict", "fix conflicts", "rebase failed", "conflict resolution", or has merge conflicts to resolve. Use only when a merge or rebase has stopped on conflicts; for general debugging, use /investigate; for code review, use /review.
- ▌ Respond · gufranco bundleRespond to incoming code review comments on a PR you authored. Fetches every unresolved comment across all channels, inline threads, review bodies, PR-level conversation, and commit comments, classifies each by author and intent, verifies against the current code, fixes what is real, replies only inside a human's inline thread, closes bot threads and unrepliable channels without a comment, and monitors CI. Use when user says "respond to review", "address comments", "handle reviewer feedback", "reply to PR comments", "my PR has comments", or wants a structured pass over reviewer feedback. For performing a review, use /review; for unattended CI and bot handling with no human threads, use /ship --pipeline.
- ▌ Incident · gufrancoGather incident context and write a blameless postmortem with timeline, root cause, and action items.
- ▌ Refactor · gufrancoGuided refactoring with behavior preservation verification. Identifies candidates (long functions, deep nesting, duplicated logic, god classes), proposes a refactoring plan, executes incrementally with tests between steps, and verifies no behavior change. Use when user says "refactor", "clean up this code", "simplify", "extract", "restructure", "reduce complexity", "split this file", or wants to improve code structure without changing behavior. For new features, use /plan; for bug fixes, use /investigate; for code review, use /review.
- ▌ Research · gufrancoMulti-source external research with entity resolution, query planning, parallel fan-out, cross-source clustering, and grounded synthesis. Use when user says "research X", "what does the community say about X", "compare X vs Y", "find prior art for X", "market scan for X", "what are people using for X", or asks for a survey of an external domain. For internal codebase questions, use /onboard; for debugging, use /investigate; for code review, use /review.
- ▌ Zoom Out · gufrancoStep back from a narrow code section and place it in its system context. Reads the file, traces callers and callees, identifies the module boundary, names the architectural role, and surfaces hidden coupling. Use when user says "zoom out", "what is this", "where does this fit", "give me context on this code", "what calls this", or feels lost in unfamiliar code. For line-by-line code review, use /review; for debugging, use /investigate; for onboarding to a whole repo, use /onboard.
- ▌ Benchmark · gufrancoMeasure API latency, bundle size, and database query time, and compare them against saved baselines to catch performance regressions.
- ▌ Fix Issue · gufrancoFix a GitHub issue by number. Fetches the issue, analyzes requirements, searches the codebase, implements the fix with tests, and commits referencing the issue. Use when user says "fix issue #N", "fix #N", "resolve issue N", "close issue N", when /morning works an assigned issue, or wants to implement a fix for a specific GitHub issue. For general debugging without an issue, use /investigate; for code review, use /review; for feature planning, use /plan.
- ▌ Skill New · gufrancoScaffold a new SKILL.md with the enforced frontmatter and six-section template, then validate it with the skill linter.
- ▌ Assessment · gufrancoAudit an implementation's architecture for completeness, missing patterns, and planted defects before a take-home or interview submission.
- ▌ Checkpoint · gufrancoSave and resume working state across sessions, with subcommands save, resume, and list. Captures git state, decisions made, remaining work, and modified files so a new session can pick up where the last one left off. Use when user says "checkpoint", "save progress", "save state", "resume", "pick up where I left off", or wants to preserve session context. For git commits, use /ship commit; for retrospectives, use /retro; for planning, use /plan.
- ▌ Gan · gufrancoGenerator-evaluator loop that iterates a feature build until it clears a scored rubric threshold.
- ▌ Tdd · gufrancoRed-green-refactor TDD loop for a single behavior. Writes a failing test first, runs it to confirm red, implements minimum code to make it green, then refactors with the test as a safety net. Use when user says "tdd", "test first", "red green refactor", "write the test first", or wants a disciplined test-first cycle. For bulk test backfill, use /test; for debugging existing failures, use /investigate; for planning a feature, use /plan.
- ▌ Plan · gufrancoPlan implementations, record architecture decisions, and scaffold boilerplate, with subcommands plan (default), adr, and scaffold. Creates spec folders, manages ADRs, and generates files from existing project patterns. Use when user says "plan this", "how should I implement", "design this feature", "create an ADR", "scaffold a service", "architecture decision", or needs to think through an approach before coding. For code review, use /review; for shipping, use /ship; for running tests, use /test.
- ▌ Ship · gufrancoShip code through the full delivery pipeline, with subcommands commit, pr, release, checks, and worktree. Handles semantic commits, pull requests with CI monitoring, tagged releases, pipeline diagnosis, and parallel worktree management. Use when user says "commit", "create a PR", "push", "release", "check CI", "pipeline status", "worktree", or wants to move code from working directory to production. For code review, use /review; for running tests, use /test; for planning, use /plan.
- ▌ Test · gufrancoRun tests, load benchmarks, coverage analysis, linting, and security scanning. Includes HTTP load testing with k6/wrk/hey/ab. Use when user says "run tests", "check coverage", "lint", "benchmark", "load test", "perf test", or wants to execute the project's test suite with results. For QA analysis of test gaps, use /review qa; for security auditing, use /audit; for writing test scenarios during planning, use /plan.
- ▌ Aside · gufrancoMid-task side question handler. Freezes the active task state, answers a side question without state mutation, then resumes the task exactly where it stopped. Lighter than /checkpoint save. Use when user says "aside", "quick question", "side question", "while we're at it", "before you continue", or interrupts mid-implementation with an unrelated question. For new scope, use /plan; for a retro, use /retro; for a true context switch, use /checkpoint save.
- ▌ Audit · gufranco bundleSecurity audit across dependencies, secrets, Docker, code patterns, images, STRIDE, and OWASP. Covers dependency vulnerability scanning and threat modeling. Use when user says "security audit", "scan for vulnerabilities", "check dependencies", "find secrets", "audit Docker", "CVE scan", "cso", "threat model", "owasp audit", "deep security scan", or wants to find security issues across the full project. For code review, use /review; for architecture completeness, use /assessment; for running tests, use /test.
- ▌ Brain · gufrancoRead from and write to the second brain vault. Subcommands - capture (default), ingest, ask, link, health, refresh, falsify, wrong, compile, eval. Files durable knowledge as specced notes, answers questions from what is already stored, keeps the graph honest as facts age, hunts facts that are wrong rather than merely old, and compiles the session memory directory from the vault. Use when user says "capture this", "remember this", "file this", "what do we know about X", "ask the vault", "vault health", "check the vault", "refresh stale facts", "the vault was wrong", "that is not true anymore", "falsify", "compile memory", "second brain", or names a note, entity, meeting, or decision to store. For external research, use /research; for codebase questions, use /onboard or /explain; for session retrospectives, use /retro.
- ▌ Guard · gufrancoSafety mode for risky operations that freezes edits to one directory, warns on destructive commands, and enforces scope.
- ▌ Infra · gufrancoManage infrastructure for local development, with subcommands docker, terraform, and db. Covers container orchestration with Colima awareness, IaC workflows with safety gates, and database migrations with ORM detection. Use when user says "docker compose", "start containers", "terraform plan", "run migration", "create migration", "database setup", or needs to manage local dev infrastructure. For production deploys, use CI/CD; for security scanning, use /audit; for Terraform test patterns, read standards/terraform-testing.md.
- ▌ Retro · gufrancoSession retrospective and codebase pattern discovery, with subcommands retro (default), which extracts corrections and preferences into durable config, and discover, which extracts codebase conventions into rule files. Enhanced with self-improving agent lifecycle. Use when user says "retro", "what did we learn", "save preferences", "discover patterns", "extract conventions", or after a significant multi-step session with corrections worth persisting.
- ▌ Setup · gufrancoInteractive first-time project setup that fills missing env values, starts required services, runs migrations and seeds, and verifies the app starts.
- ▌ Spike · gufranco bundleBuild a small throwaway artifact that answers exactly one open design question, then move it off the working branch onto an unmerged spike branch. Two routes inside the skill, a runnable terminal program for state, logic, or data-shape questions, and a side-by-side view comparison for presentation questions. Use when the user says "spike this", "build a quick throwaway", "let me play with the model", "try a few visual directions", or wants to de-risk a design choice before committing to it. For production features, use `/plan`; for refactoring an existing module, use `/refactor`; for a single polished design pass, use `/design`.
- ▌ Deploy · gufrancoMerge a shipped PR, verify the deployment, and monitor post-deploy health, with land and canary subcommands.
- ▌ Design · gufrancoDesign consultation, variant exploration, and design system scaffolding, with subcommands consult (default), variants, and system. Researches design patterns, proposes component hierarchies, generates design decisions document, and creates multiple visual approaches for comparison. Use when user says "design this", "design consultation", "design system", "component design", "design variants", "UI approach", "visual direction", or needs structured design thinking before implementation. For design review or audit of existing code, use /review design; for implementation planning, use /plan.
- ▌ Hotfix · gufrancoEmergency production fix that branches from the latest release tag, applies a minimal fix, ships with expedited review, and backports to main.
- ▌ Readme · gufranco bundleGenerate a README and GitHub repo description from the actual codebase, always in English, Japanese, Simplified Chinese and Hong Kong Traditional Chinese, in the marketing variant or the --variant assessment variant.