Menu
O SkillsMP coletou 13 skills de plimeor/agent-skills. Abra uma skill para revisar a origem e os detalhes.
Mostrando 13 de 13 skills coletadas.
Write coding plans for implementation, debugging, refactoring, migrations, design parity, and long-running agent tasks. Use when drafting, refining, or validating a development plan, /goal prompt, implementation approach, scope and non-goals, work sequence,…
Idioma do texto original: inglês
Author, refactor, or diagnose a repository's AGENTS.md (and CLAUDE.md) and/or README.md as complementary entrypoints. Use when writing, shrinking, splitting, or reviewing those files, when AGENTS.md is bloated or contradictory, or when a README cannot keep…
Idioma do texto original: inglês
Assess whether a design holds up against modern software-engineering principles: complexity and cognitive load, change economics, boundary correctness, and agent legibility. Use when the user asks whether a design, module boundary, API, data flow, design doc,…
Idioma do texto original: inglês
Review concrete code plan drafts, specs, diffs, and implementation shapes, including parity audits of an implementation against an authoritative source or reference implementation. Use for code-review requests, exhaustive or line-by-line review requests,…
Idioma do texto original: inglês
Build a deployable crew skill from local Claude Code / Grok session history (discover → clean → signals → role inference → boundary validation). Run live-LLM evals from evals/evals.json, including against an already-installed crew when the user asks. Use when…
Idioma do texto original: inglês
Run a team of sub-agents under an orchestration blueprint: scout the surface, split it into atomic work units, dispatch them with baked context packets, have independent skeptic lanes attack every material claim, and synthesize one result with coverage and…
Idioma do texto original: inglês
Produce a single portable local HTML file as the final deliverable — a report, doc, dashboard, landing page, demo, tool, or presentation rendered as one .html that opens straight from disk. Use when the user asks for an HTML page/file/artifact saved locally,…
Idioma do texto original: inglês
Use before finalizing a non-trivial answer, recommendation, review, or decision, especially when shallow reasoning, stale context, a false frame, overconfidence, or transferring an outside framework or analogy onto the user's specific case could distort it,…
Idioma do texto original: inglês
Decide the smallest useful test strategy for a coding task without letting tests drive production-only complexity. Use when adding tests, choosing unit/integration/E2E level, reviewing mocks, doing TDD, or when an agent is about to add or modify tests.
Idioma do texto original: inglês
Read the main content of a specific webpage URL when the user asks to summarize, inspect, cite, reference, or extract facts from that URL, including "read this", "look at this link", "based on this article", or equivalent reference requests. Owns URL…
Idioma do texto original: inglês
Create, diagnose, outline, rewrite, or polish blog posts, articles, and newsletters. Use for drafting from notes, article outlines, structure and readability optimization, polishing rough notes toward publishable form, feedback on whether a draft reads well,…
Idioma do texto original: inglês
Humanize Chinese or English drafts. Use when the user asks to make writing less AI-like, more human, more natural, less generic, more authored, or when a draft feels over-polished, too symmetrical, generic, translated, or detached from the author's real…
Idioma do texto original: inglês
Simulate a specified reader persona reading an article and report raw reading-experience feedback, not writing advice. Use when the user asks how a specific audience would experience a draft, whether readers can understand it, or wants reader simulation,…
Idioma do texto original: inglês