Copia este prompt en el asistente de IA que estés usando.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/minghinmatthewlam/agent-guards.Cargando el README del repositorio…
Mostrando 40 de 64 skills recopiladas.
Run a session as a project coordinator and product partner: keep a board, dispatch work to subagents and task-card threads with a standard brief and workflow, track them with a check loop, and report to the human in priority order. Use when the user asks you…
Idioma del texto original: inglés
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
Idioma del texto original: inglés
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
Idioma del texto original: inglés
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling…
Idioma del texto original: inglés
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
Idioma del texto original: inglés
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you…
Idioma del texto original: inglés
Restate the last message in plain human language, with no jargon.
Idioma del texto original: inglés
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each…
Idioma del texto original: inglés
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for $create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove…
Idioma del texto original: inglés
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it…
Idioma del texto original: inglés
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding…
Idioma del texto original: inglés
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
Idioma del texto original: inglés
Catch the user up on everything in this chat since their last message, in plain words. Give each action item an executive summary with enough context to make the call. Use for /ketchup.
Idioma del texto original: inglés
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for $maintain-verification-skill or "audit the verify skill".
Idioma del texto original: inglés
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Idioma del texto original: inglés
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Idioma del texto original: inglés
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Idioma del texto original: inglés
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Idioma del texto original: inglés
Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.
Idioma del texto original: inglés
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Idioma del texto original: inglés
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can…
Idioma del texto original: inglés
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Idioma del texto original: inglés
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
Idioma del texto original: inglés
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
Idioma del texto original: inglés
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Idioma del texto original: inglés
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
Idioma del texto original: inglés
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
Idioma del texto original: inglés
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Idioma del texto original: inglés
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
Idioma del texto original: inglés
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
Idioma del texto original: inglés
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
Idioma del texto original: inglés
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
Idioma del texto original: inglés
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
Idioma del texto original: inglés
Apply when tempted to ask 'should I do X?' on reversible work.
Idioma del texto original: inglés
Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
Idioma del texto original: inglés
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
Idioma del texto original: inglés
Apply when integrating a new requirement into an existing design.
Idioma del texto original: inglés
Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
Idioma del texto original: inglés
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a…
Idioma del texto original: inglés
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
Idioma del texto original: inglés
Archivo de origen del README: README.md
Leer el README original