Skills in this repository
SkillsMP has collected 66 skills from davesnx/setup. Open a skill to review its source and details.
davesnx/setupShowing 26 of 66 collected skills.
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.
Puts real design variations of one project file on the user's own localhost, behind a small card that flips them with arrow keys, then keeps listening for their verdict. Use to compare design directions or alternatives. Works in an empty folder or a real…
Use for explicit React or Next.js performance work involving rendering, data fetching, bundles, RSC, hydration, or measured regressions. Do not use for visual design, layout, styling, accessibility, or general component edits; use impeccable for those. Load…
Draft, edit, or analyze X posts and threads using supplied material and analytics. Not developer documentation or independent research.
Consult shared code standards for a relevant design decision or an explicit standards reference request, not for every code change.
Reconstruct recent working context from chat history, repository state, and shared records like issues and incidents. Use for 'recall my work on X', 'catch me up', 'where did I leave off', 'what did we decide', 'resume work on X', or to summarise past…
Use when the user asks to control a Flipper Zero over USB serial, inspect its device information or storage, read CLI output, release a busy serial port, or dump or emulate the user's own NFC cards. Uses the local flipper command. Not for firmware…
Design production modules, interfaces, seams, types, signatures, and dependency structure before implementation. Use ONLY when the requested result is a production code shape or integration contract, such as 'architect this' or 'design this module'. Do not…
Build throwaway, self-contained, drivable HTML artifacts to answer state-model, transition, policy, scheduling, or algorithm questions. Use ONLY when the requested result is a disposable interactive logic experiment used to test behavior before production…
Use when asked to open, create, submit, or prepare a pull request, or to write or edit a PR title or body. Checks readiness, uses comment-purge when cleanup is authorized, writes in repository terms with behavioral evidence and a merge-risk line, and…
Finish sancho.dev drafts with stub, outline, or partial SKILLS state. Fill gaps from evidence and ask for missing author decisions; supports post interviews.
Run bounded, measured experiments when the user explicitly requests autoresearch or optimization of a metric.
Use for explicit domain modeling, ubiquitous language, glossary or CONTEXT.md, context maps, or ADR work. Not for TDD, test-first, red-green-refactor, or integration tests alone. Load tdd too only when test-first work is explicitly requested.
Review the active session for durable lessons only when the user explicitly asks to reflect. Propose changes; wait for approval before edits.
Sync shared agent skills between the Mac and nspawn through the setup Git repository. Not upstream skill vendoring.
Use for explicit TDD, test-first, or red-green-refactor requests, including test-first integration tests. Not for generic implementation, bug fixes, tests alone, or domain artifacts. Load domain-modeling too only when explicitly requested.
Review code changes, commits, or PRs on request, including deep, adversarial, and blast-radius reviews. Report verified risks; edit or publish only with authorization.
Simplify code while preserving behavior when asked for cleanup, refactoring, or Simplify. Not an automatic post-edit pass or prose cleanup.
Use when the user asks to list local Enpass credential titles, retrieve or copy an Enpass password, or provide an Enpass secret to a command. Uses the safe local `enpass` wrapper and prevents broad substring matches or password exposure in agent output. Works…
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.
Diagnosis loop for bugs and performance regressions. Use when the user explicitly asks to diagnose or debug, or provides a concrete runtime failure, shares a log file or measured regression.
Give a short visual explanation in chat by default. Create one self-contained HTML file only when the user explicitly requests HTML, a presentation, or an interactive explanation. Use ONLY when the user explicitly asks to use the eli5 skill.
Syntax guide for mlx, the JSX syntax for OCaml. Use when writing, reading, or reviewing a .mlx file, when the user asks for JSX or HTML-like elements in OCaml, or when a function must be callable as an mlx tag.
Install and configure mlx, the JSX syntax for OCaml, in a dune project. Use when the user asks to set up, enable, or add mlx or JSX to an OCaml project, when a .mlx file exists but dune-project has no mlx dialect, or when mlx-pp, ocamlmerlin-mlx, or…