← all publishers

DieGopherLT

@diegopherlt source repo

Report this profile Claim this profile

• 27 skills
• 0 followers
• 1 week ago last updated

1. ▌
   Task Planning · diegopherlt bundle

   Turn an approved plan into a multi-session run: create a dedicated worktree, decompose the work into sessions of letter-group blocks sized by friction, open the binnacle that carries the run's state across /clear boundaries, and register only the current session's tasks with TaskCreate. Invoke this skill immediately when the user gives a substantial request — one that touches 2+ files, involves 3+ sequential steps, requires executing an approved plan, or comes right after exiting plan mode with ExitPlanMode. Trigger on signals like "let's do it", "go ahead and implement", "execute the plan", "make it so", "start working", "implement this", or any multi-part request where the user is clearly kicking off real implementation work. When in doubt about whether the scope is large enough, invoke it — the overhead is small and the structure it provides prevents skipped steps and messy commit history.
   0 installs
2. ▌
   Claude Five Prompting Guide · diegopherlt bundle

   Guidelines for prompting and building context for Claude 5 generation models (Sonnet 5, Opus 5, Fable 5), based on Anthropic's official guidance from July 2026. Use this skill whenever the user asks how to prompt Claude 5 models, wants to write or review a system prompt, CLAUDE.md, skill, or agent harness targeting these models, mentions "unhobbling", "unknowns", "blind spot pass", "context engineering", or asks why an agentic task came back wrong despite detailed instructions. Also use it when auditing existing prompts or rules for over-constraint, or when migrating prompts written for Claude 4-era models. When invoked with file path arguments, audit those files against the guide (prefer delegating the audit to a read-only sub-agent and returning only findings).
   3 installs
3. ▌
   Stabilize · diegopherlt bundle

   Esta skill debe usarse cuando el usuario pide "stabilize", "estabiliza los flujos", "cosecha las sesiones", "harvest flows", "mina los transcripts", "convierte lo repetido en skill", o cuando decide actuar sobre el aviso del hook session-harvest de que la cola alcanzo su umbral — ese aviso es una notificacion al usuario, y correr esta skill es siempre decision suya. Tambien usarla si el usuario menciona querer extraer flujos mecanicos repetidos (migraciones, wiring, boilerplate) de sesiones pasadas y convertirlos en skills o rules del proyecto ("cosecha los flujos", "estabiliza lo aprendido"). Mina los transcripts encolados con agentes transcript-digester en paralelo, cruza sesiones buscando flujos y convenciones recurrentes ademas de correcciones explicitas del usuario, verifica cada candidato con practice-verifier y materializa solo los confirmados como recursos del proyecto o memoria de feedback. Ejecutable en background.
   0 installs
4. ▌
   Smell Scan · diegopherlt bundle

   This skill should be used when the user says "scan this for smells", "audit this code", "what code smells does X have", "review this for quality issues", "find code smells in", or asks about the code quality of a specific file, function, or class. Covers the full refactoring.guru taxonomy of 26 smells across 5 categories, producing located, confidence-scored findings mapped to concrete refactoring techniques — not generic Clean Code advice.
   0 installs
5. ▌
   Squash Suggester · diegopherlt

   Analyzes a branch's commit history and produces a squash plan for interactive rebase — a markdown file with a table of every commit, its recommended action (pick, squash, or fixup), and the reasoning, preserving atomicity and bisectability throughout. Invoke immediately whenever the user says "suggest squashes", "squash plan", "clean up my branch", "compact the history", "squash commits before merge", "prepare branch for PR", "organize commits", or mentions wanting fewer commits before merging or opening a PR. Don't wait for the user to specify a target branch — default to main and proceed. The output is a ready-to-use reference for running git rebase -i.
   0 installs
6. ▌
   Document Sockets · diegopherlt bundle

   Esta skill debe usarse cuando el usuario pide "documenta los sockets", "documenta los eventos", "documentar websockets", "document the sockets", "document socket events", "necesito la doc de los sockets para el frontend", o cuando menciona documentar eventos de socket.io para consumo desde el frontend. Tambien activar cuando el usuario menciona pasar eventos al frontend, compartir contratos de sockets, o preparar documentacion de eventos en tiempo real. No usar para endpoints HTTP REST (usar document-endpoints en su lugar).
   1 install
7. ▌
   Conflict Resolver · diegopherlt

   Resolves git conflicts in progress — for both rebases and merges. Invoke immediately whenever the user says "help with rebase", "rebase conflict", "merge conflict", "I have conflicts", "rebase is stuck", "resolve this conflict", "rebase went wrong", or is mid-rebase or mid-merge and needs guidance on what to keep. Don't wait for the user to ask explicitly — if git status shows conflict markers or a rebase/merge is active, invoke this skill. Analyzes the commit history of every branch involved via parallel sub-agents to understand each side's intent before touching any conflict marker.
   1 install
8. ▌
   Create Specification · diegopherlt

   Create a new, closed and self-contained specification file optimized for Generative AI consumption and cold execution via the /goal command. Scaffolds the managed Design Gaps section that the close-design loop consumes. Use when the user wants to write a new spec, draft a specification, capture requirements, or plan a substantial change as a cold-executable spec.
   1 install
9. ▌
   Update Specification · diegopherlt

   Update an existing specification file optimized for Generative AI consumption, based on new requirements or code changes. Also the living-document maintainer for the spec-kit closure loop: folds accepted Design Gaps into the spec body and removes resolved entries from the managed section. Use when the spec drifted from the code, requirements changed, the implementation diverged, or the user says to sync, revise, or update the spec.
   0 installs
10. ▌
    Document Endpoints · diegopherlt bundle

    Esta skill debe usarse cuando el usuario pide "documenta los endpoints", "documenta la API", "documentar las rutas", "document the endpoints", "document the API", "necesito la doc de los endpoints para el frontend", o cuando menciona documentar endpoints HTTP para consumo desde el frontend. Tambien activar cuando el usuario menciona pasar endpoints al frontend, compartir contratos HTTP, o preparar documentacion de rutas REST. No usar para WebSockets ni socket.io (usar document-sockets en su lugar).
    1 install
11. ▌
    Plan Constraints · diegopherlt

    Constraints, structure and template for implementation plans. Invoke immediately upon entering plan mode, before drafting any plan — and also when reviewing an existing plan, re-planning mid-task after a scope change, or when the user asks for an implementation plan, spec, or breakdown in any form. The plan is not ready to present until it satisfies this skill's checklist.
    1 install
12. ▌
    Workflow Creator · diegopherlt bundle

    Designs, writes, or audits dynamic workflows for Claude Code — the JavaScript orchestration scripts the Workflow tool runs to fan many subagents across one large job (triggered by 'ultracode' or by asking to "use a workflow"). Use this skill proactively whenever the user says "create a workflow", "write a dynamic workflow", "orchestrate subagents", "fan out agents", "parallelize this with agents", "codebase-wide audit", "massive bug hunt", "ultracode workflow", "port this from X to Y", "migrate the whole repo", or describes work a single pass can't hold (repo-wide audits, large migrations, language ports, verified multi-source research). Also use it to audit or review an existing workflow script — "audit this workflow", "review my orchestration script", "is this workflow correct", "improve this workflow" — checking data-flow shape, per-role thinking load, and runtime safety. For authoring a single isolated sub-agent that reports back once, this is not the skill. Reach for this even when the user only hints at
    0 installs
13. ▌
    Resume From Binnacle · diegopherlt bundle

    User-invoked shortcut to resume a multi-session run from its binnacle: locates .claude/binnacle.md at the current worktree root, delegates to the binnacle skill's resume procedure in full, optionally warms context with read-only explorers when the latest entry points at code it does not explain, and continues the work. Invoked manually as /resume-from-binnacle at the start of a cold session, to avoid retyping the resume prompt every time.
    2 installs
14. ▌
    Claude Code Agent Creator · diegopherlt bundle

    Crea archivos markdown de sub-agentes de Claude Code (con YAML frontmatter y system prompt) listos para colocar en ~/.claude/agents/, .claude/agents/ o agents/ de un plugin. Usa esta skill proactivamente cuando el usuario diga "crea un agente", "create an agent", "necesito un sub-agente que...", "scaffold an agent", "haz un auditor", "make a code reviewer agent", "agente que revise", "agente que audite", "agente que investigue", o cuando describa funcionalidad especializada que conviene aislar en un sub-agente (ej. "necesito algo que revise PRs", "quiero un agente que analice seguridad"). Cubre seleccion de tools con principio de menor privilegio, tuning de description para auto-invocacion, eleccion de arquetipo (auditor / researcher / implementer / orchestrator), calibracion de modelo + effort segun la carga de razonamiento de la tarea (mas mecanico = modelo mas ligero y menos effort) e incluye un sistema de scoring de confianza 0-100 con umbral >=80 para agentes tipo auditor.
    1 install
15. ▌
    Typescript Migration · diegopherlt bundle

    Esta skill debe usarse cuando el usuario pide "migra este proyecto a TypeScript", "convierte de JS a TS", "agrega TypeScript a este proyecto", "migrate to TypeScript", "add types to this codebase", "quiero tipado estatico en este proyecto", o menciona querer convertir un proyecto JavaScript existente a TypeScript de forma incremental. Ejecuta un pipeline autonomo de 5 fases (auditar proyecto, instalar tooling y renombrar archivos, extraer tipos compartidos, tipar chunks en paralelo, consolidar con strict progresivo y gate de build final) aislado en un worktree dedicado. No la uses para proyectos nuevos iniciados directamente en TypeScript ni para agregar tipos a un solo archivo.
    0 installs
16. ▌
    Commit · diegopherlt

    Execute a complete, standards-compliant git commit. Invoke immediately whenever the user says "commit", "make a commit", "commit these changes", "let's commit", "ship this", "stage and commit", or any phrase that signals they want to record changes to git history. Do not wait for the user to specify format details — own the full workflow: staging, linting, message authoring, approval when the commit is standalone, and execution. If in doubt, invoke it — a bad commit message is permanent history.
    1 install
17. ▌
    Branching · diegopherlt

    Apply the correct branch naming convention before creating a new git branch or worktree. Invoke whenever the user says "create a branch", "new branch", "branch off", "checkout -b", "switch to a new branch", "create a worktree", "new worktree", "worktree for X", or any phrase where a new branch or worktree is about to be created. Also invoke when the user wants to rename or review an existing branch whose name does not follow the convention. Propose the name before executing.
    1 install
18. ▌
    Close Design · diegopherlt

    Harden a spec-driven specification until its design is closed — no missing, ambiguous, or unverifiable design decisions remain. Runs an autonomous loop-until-dry under the /goal command: each round spawns a FRESH closed-design-enforcer sub-agent that detects net-new design gaps, which this skill deduplicates and logs into the spec's managed Design Gaps section, until a round finds nothing new. Then it runs a single human arbitration gate. Use this whenever the user wants to "close the design", "harden the spec", "find design gaps", "make the spec ready for cold execution", or before implementing any spec via implement-spec. Invoke proactively once a spec draft exists and before implementation begins.
    1 install
19. ▌
    Binnacle · diegopherlt bundle

    Open, structure, and resume the durable log of a multi-session run: a .claude/binnacle.md file at the root of the run's worktree, created from a bundled template, ignored through the repo's local exclude file, and written as an immutable reverse-chronological changelog with a line-count cursor (read_until_line) so a cold session restores the run with one bounded Read. Invoke when task-planning opens a run, and whenever a fresh session finds a binnacle in its worktree and must resume the run it describes. Session-closing entries are written by the log-binnacle skill, not here.
    0 installs
20. ▌
    Implement Spec · diegopherlt

    Implement a closed spec file end-to-end, dispatching to the execution strategy that fits the work. Designed to run alongside the /goal command, which drives it non-stop until the spec is implemented, quality-reviewed, and verified to actually work. Acts as a pure dispatcher: it separates strategy selection from execution, choosing write-directly, agent-waves, or workflow based on scale and orchestration closure. Use after a spec's design is closed (via close-design) and the user wants it built. Trigger on "implement the spec", "build this spec", "execute the spec", or a /goal aimed at a spec file.
    1 install
21. ▌
    Rulify · diegopherlt bundle

    Esta skill debe usarse cuando el usuario pide "aligerar el CLAUDE.md", "dividir el CLAUDE.md", "extraer reglas a .claude/rules", "rulify", "claudemd splitter", "convertir secciones del CLAUDE.md en rules bajo demanda", o menciona que su CLAUDE.md crecio demasiado, supera las 200 lineas, o quiere migrar a carga contextual con globs. Divide un CLAUDE.md monolitico en archivos `.claude/rules/*.md` cargados bajo demanda via frontmatter `paths`, fusionando con reglas existentes y dejando el CLAUDE.md base con solo informacion que aplica a todo el proyecto.
    0 installs
22. ▌
    Split Component · diegopherlt

    Esta skill debe usarse cuando el usuario pide "dividir componente", "separar componente", "split component", "extraer componentes", "componente muy grande", "refactorizar componente grande", "break down component", "este archivo tiene muchas responsabilidades", o menciona que un archivo React tiene demasiado codigo, demasiado estado, o demasiada logica mezclada con UI. Analiza un componente React y lo divide en piezas mas manejables siguiendo el patron smart/dumb components.
    0 installs
23. ▌
    Refactor · diegopherlt bundle

    This skill should be used when the user says "refactor this", "fix this smell", "apply Extract Method", "apply [technique name]", "clean up this code", or passes a finding code from smell-scan (e.g. B1, D3, C2). Also trigger when the user wants to apply a specific refactoring.guru technique to a specific location, or to apply everything (or everything in a domain) flagged by a prior smell-scan. Carries each finding's technique, file, location, and smell context into a safe test → refactor → test → commit cycle, delegating edits to the refactoring-applier agent.
    0 installs
24. ▌
    Log Binnacle · diegopherlt bundle

    Write the closing entry of a work session into the run's binnacle (.claude/binnacle.md): insert an immutable entry at the top of the changelog, advance the session checkbox and current_session, update status and last_updated, and recalculate the read_until_line cursor. Invoke when the task titled "invoke log-binnacle" is reached — the explicit last task of every session in a task-harness run — when a resume detects the previous session died without closing and needs a recovery entry, or whenever the user asks to close, log, or checkpoint the current session before a /clear.
    1 install
25. ▌
    Claudify · diegopherlt bundle

    Esta skill debe usarse cuando el usuario pide "documenta el modulo", "claudify", "generate module docs", "actualiza el CLAUDE.md de este modulo", "onboarding del modulo", "necesito un CLAUDE.md para X", o quiere crear/actualizar un CLAUDE.md a nivel de modulo. Corre como fork en background — no roba contexto a la sesion principal y devuelve solo un resumen de una linea. Genera documentacion token-efficient con referencias LSP-optimizadas (`file::Symbol`) enfocada en informacion no-obvia que ahorra al agente tener que inferirla del codigo.
    1 install
26. ▌
    Remember · diegopherlt bundle

    Esta skill debe usarse cuando el usuario pide "recuerda que", "guarda esto", "anota esto", "no olvides que", "remember this", "save this", "store this", "keep in mind", "where should I save", "donde guardo esto", o menciona querer persistir informacion del proyecto. Proporciona clasificacion automatica al destino correcto de memoria de Claude Code segun la naturaleza del contenido.
    0 installs
27. ▌
    Lib Advisor · diegopherlt

    Search, evaluate and select libraries when a problem is "standard" — meaning someone has almost certainly solved it already. The strongest trigger is mid-planning of a new feature — while drafting or reviewing an implementation plan (plan mode, task-planning), run the standard-problem test on each planned component before the plan commits to a manual implementation. Also use this skill whenever the user is about to implement non-trivial functionality that sounds like a solved problem (programmatic SSH, retry/backoff, argument parsing, schema validation, date handling, HTTP routing, queues, templating), asks "should I implement X myself or use a lib?", "is there a library for X?", asks to compare libraries, or starts writing infrastructure-flavored code from scratch. Also use it when evaluating whether an existing dependency should be replaced, or when designing a public API and the prose-quality taxonomy (Facade / Fluent Interface / Internal DSL) applies.
    1 install