RADAR DE SKILLS · GITHUB
Agent Skills úteis, classificados pelo uso real.
Compare Skills verificados por finalidade, conteúdo do pacote, instalações e evidências da fonte antes de adicioná-los.
- ESCOPO DO CATÁLOGO
- VERIFICADO
- Skills
- 5.771
- repositórios
- 824
- última sincronização
- 8 de set. de 2026
membranedevdirectus
Directus integration. Manage Collections, Users, Presets, Dashboards, Flows. Use when the user wants to interact with Directus data.
- instalações
- 1
- GitHub Stars
- 267
- Atualizado
- 28 de abr.
michael-denyerpoteto-mode
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.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-boundary-discipline
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.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-experience-first
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-guard-the-context-window
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.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-minimize-reader-load
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.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerprinciple-separate-before-serializing-shared-state
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.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerreflect
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyershow-me-your-work
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerthermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyertypescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
michael-denyerwhat-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update
- instalações
- 1
- GitHub Stars
- 239
- Atualizado
- 8 de set.
secondskybun-sqlite
Use for bun:sqlite, SQLite operations, prepared statements, transactions, and queries.
- instalações
- 1
- GitHub Stars
- 215
- Atualizado
- 7 de set.
pproencatailwind-ui-refactor
Refactoring UI design patterns for Tailwind CSS applications. This skill should be used when writing, reviewing, or refactoring HTML with Tailwind utility classes to improve visual hierarchy, spacing, typography, color, depth, and polish. Triggers on tasks involving UI cleanup, design review, Tailwind refactoring, component styling, or visual improvements.
- instalações
- 1
- GitHub Stars
- 204
- Atualizado
- 15 de ago.
mohitmishra786clang
Clang/LLVM compiler skill for C/C++ projects. Use when working with clang or clang++ for diagnostics, sanitizer instrumentation, optimization remarks, static analysis with clang-tidy, LTO via lld, or when migrating from GCC to Clang. Activates on queries about clang flags, clang-tidy, clang-format, better error messages, Apple/FreeBSD toolchains, or LLVM-specific optimizations. Covers flag selection, diagnostic tuning, and integration with LLVM tooling.
- instalações
- 1
- GitHub Stars
- 198
- Atualizado
- 27 de jun.
mohitmishra786static-analysis
Static analysis skill for C/C++ codebases. Use when hardening code quality, triaging noisy builds, running clang-tidy, cppcheck, or scan-build, interpreting check categories, suppressing false positives, or integrating static analysis into CI. Activates on queries about clang-tidy checks, cppcheck, scan-build, compilecommands.json, code hardening, or static analysis warnings.
- instalações
- 1
- GitHub Stars
- 198
- Atualizado
- 27 de jun.
modularclosure-migration
- Migrates Mojo code off legacy parametric closures (capturing[], @parameter / @parameter, apifn) onto value-taking unified closures (api(args, fn) with {imm} / {mut} / {var} / named capture lists). Use when removing parametric overloads, fixing "capturing thin" conversion errors, rewriting nested launch/callback closures, or migrating any API that took a comptime function parameter. Also use when CI SIGSEGVs while compiling a Mojo object with compileoffloadclosure func must be fully bound — that is host elaboration; verify with kgen -elaborate, not remote GPU execution.
- instalações
- 1
- GitHub Stars
- 188
- Atualizado
- 6 de set.
modulardebug-model
Debug silent corruption when a MAX model loads, compiles, serves, and generates tokens but output disagrees with a reference implementation. Use whenever parity debugging stalls on scalar taps, the model returns gibberish or wrong greedy tokens, logit cosine is high but argmax differs, or generation is coherent then diverges — during an architecture port, a quantization bring-up, a multi-GPU conversion, or after a MAX upgrade. Triggers on "parity failure", "silent corruption", "logits match but tokens diverge", "top-1 mismatch", "greedy divergence", and "model serves but generates garbage". Not for crashes on load or pre-serve scaffolding (use import-model). Mandates reference-vs-MAX tensor-dump comparators first, verify fixes numerically before recompiling, and serve-vs-pipeline bisect when dumps match but text diverges.
- instalações
- 1
- GitHub Stars
- 188
- Atualizado
- 6 de set.
modulareval-model
Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it with model-card or reference scores, verifying that a new MAX model produces correct answers, or running repeatable dataset evaluations against a MAX OpenAI-compatible endpoint.
- instalações
- 1
- GitHub Stars
- 188
- Atualizado
- 6 de set.
modularimport-model
Use when importing a new model architecture into MAX from a Hugging Face model ID. Triggers on: "import a model into MAX", "add model to MAX", "bring up in MAX". Workflow: inspect Hugging Face config and modeling code, scaffold from a similar MAX architecture, implement each graph layer to match HF, serve, then verify against the Hugging Face reference. When the server runs but output is wrong (gibberish, greedy mismatch, coherent-then-diverges), load debug-model for the divergence hunt instead of scalar-tap iteration.
- instalações
- 1
- GitHub Stars
- 188
- Atualizado
- 6 de set.
modularmojo-syntax
Help to write Mojo code using current syntax and conventions. Always use this skill when writing any Mojo code, including when other Mojo-specific skills (e.g., mojo-gpu-fundamentals) also apply. Use when writing Mojo code, translating projects to Mojo, or otherwise generating Mojo. Use this skill to overcome misconceptions with how Mojo is written.
- instalações
- 1
- GitHub Stars
- 188
- Atualizado
- 6 de set.
modularnew-modular-project
Creates a new Mojo or MAX project. Use when wanting to start a new Mojo or MAX project, initializing the pixi or uv environment to use Mojo or MAX, or when the user wants to begin a new Mojo or MAX project from scratch.
- instalações
- 1
- GitHub Stars
- 188
- Atualizado
- 6 de set.