Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN.
$ npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Hermes-brasil/hermes-brasil anti-ai-slop --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/anti-ai-slop .claude/skills/anti-ai-slop && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "anti-ai-slop" agent skill from https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slop into .claude/skills/anti-ai-slop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-ai-slop", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slopType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Hermes-brasil/hermes-brasil anti-ai-slop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/anti-ai-slop .agents/skills/anti-ai-slop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "anti-ai-slop" agent skill from https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slop into .agents/skills/anti-ai-slop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-ai-slop", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Hermes-brasil/hermes-brasil anti-ai-slop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/anti-ai-slop .cursor/skills/anti-ai-slop && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "anti-ai-slop" agent skill from https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slop into .cursor/skills/anti-ai-slop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-ai-slop", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Hermes-brasil/hermes-brasil.git --path skills/anti-ai-slop--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Hermes-brasil/hermes-brasil anti-ai-slop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/anti-ai-slop .gemini/skills/anti-ai-slop && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "anti-ai-slop" agent skill from https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slop into .gemini/skills/anti-ai-slop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-ai-slop", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Hermes-brasil/hermes-brasil anti-ai-slopInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/anti-ai-slop .github/skills/anti-ai-slop && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "anti-ai-slop" agent skill from https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slop into .github/skills/anti-ai-slop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-ai-slop", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Hermes-brasil/hermes-brasil anti-ai-slop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hermes-brasil/hermes-brasil.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/anti-ai-slop .opencode/skills/anti-ai-slop && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "anti-ai-slop" agent skill from https://github.com/Hermes-brasil/hermes-brasil/tree/main/skills/anti-ai-slop into .opencode/skills/anti-ai-slop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-ai-slop", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
anti-ai-slopProtocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN.
Anti AI Slop is an agent skill from Hermes-brasil/hermes-brasil. Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN. Use em toda peça escrita antes da entrega final — léxico, estrutura, tom, semântica, self-check e variações por canal.
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Verification before completion. The repository describes itself as: Comunidade brasileira de Hermes Agent (Nous Research) — skills, guias e integrações em português. The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 8f94818. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Anti AI Slop loads about 3.8k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 2,013 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Hermes-brasil/hermes-brasil at commit 8f94818, republished under its MIT licence (© Hermes-brasil). 2,013 words, ~3,797 tokens.
.claude/skills/anti-ai-slop/SKILL.md (or your agent's skills folder).Carregue esta skill na fase de revisão de toda peça escrita. Aplique com disciplina. Não é sugestão, é protocolo.
AI slop é uma textura específica de prosa gerada por LLM, reconhecível pela combinação de quatro vícios:
Não é "texto ruim". É uma textura que cumula. Um sintoma isolado pode ser inocente; três ou quatro juntos é diagnóstico.
delve · navigate (uso abstrato) · explore (uso abstrato) · foster · leverage · unlock · harness · embrace · embark · journey · transform (uso vago) · elevate · empower · unleash · craft (quando "make" basta) · cultivate (em contextos não-agrícolas) · streamline · optimize (uso vago)
navegar (uso abstrato) · explorar (idem) · desbloquear · alavancar · fomentar · potencializar · transformar (uso vago) · elevar · empoderar · mergulhar (uso metafórico) · trazer à tona · lançar luz sobre · desvendar · abraçar (uso metafórico) · cultivar (em contextos não-agrícolas) · entregar valor · agregar valor
robust · comprehensive · powerful · innovative · cutting-edge · groundbreaking · revolutionary · game-changing · seamless · holistic · dynamic · vibrant · compelling · meaningful · essential (uso vago) · crucial (uso inflacionado) · vital (uso inflacionado)
robusto · abrangente · poderoso · inovador · revolucionário · transformador · dinâmico · vibrante · holístico · completo · único (no sentido vago) · incrível · fascinante · significativo (uso vago) · essencial (uso inflacionado) · crucial (idem) · imperdível
It's worth noting that · It's important to remember that · In today's fast-paced world · Whether you're X or Y · Not only X but also Y (uso obsessivo) · At the end of the day · On the other hand (uso excessivo) · Furthermore (uso obsessivo) · Moreover (idem) · In conclusion (em texto curto) · It goes without saying that
Vale destacar que · É importante mencionar que · Vale lembrar que · Vale ressaltar · No mundo de hoje · No cenário atual · No final do dia · No fim das contas · Por outro lado (uso excessivo) · Ademais · Outrossim · Em suma · Em última análise · Cabe destacar · Importante mencionar
EN: potentially · arguably · essentially · basically · really · very · simply · somewhat · quite
PT-BR: potencialmente · basicamente · essencialmente · realmente · simplesmente · de certa forma · de alguma maneira · meio que
Use uma vez quando precisar de verdade. Cinco vezes vira muleta de modelo medroso.
EN:
PT-BR:
EN:
PT-BR:
Conte as palavras de cada frase de um parágrafo. Se a variação for menor que 50% entre a frase mais curta e a mais longa, reescreva. Prosa humana respira — alterna ar e densidade.
Exemplo ruim (uniforme):
O marketing digital tem se mostrado uma estratégia eficaz para empresas modernas. As organizações que adotam essas práticas conseguem resultados significativos. É importante implementar essas táticas com planejamento adequado. (13, 11, 11 palavras — ritmo de metrônomo)
Exemplo bom (variado):
Marketing digital funciona. As empresas que tratam isso como projeto sério — calendário editorial, KPIs claros, alguém responsável — colhem resultados em seis meses. O resto continua publicando no vazio. (3, 22, 6 palavras — respira)
Slop hedge porque tem medo de errar. Prosa humana arrisca opinião quando o gênero permite.
Slop: "Pode-se argumentar que essa abordagem talvez não seja a mais rigorosa em certos contextos."
Prosa: "Essa abordagem é preguiçosa."
Não significa ser grosseiro. Significa se comprometer com o que está dizendo.
Slop ama afirmar verdades universais como se fossem descoberta:
Teste: se a frase é verdade para qualquer pessoa em qualquer contexto, ela está vazia.
Reescreva com substância concreta.
Sempre que possível, troque conceito por exemplo concreto, sentimento por número, geral por específico.
Dois exemplos específicos vencem oito exemplos genéricos.
Caçar slop é metade do trabalho. Cultivar prosa que respira é a outra metade.
Antes de declarar texto pronto, releia procurando especificamente:
Não precisa fazer todos a cada vez. Mas o item 9 é não-negociável.
❌ Slop:
Em um mundo cada vez mais digital, navegar pelo universo do marketing online pode parecer desafiador. Vale destacar que, com as estratégias certas, é possível alavancar seu negócio de forma transformadora.
✅ Humanizado:
Em 2024 dei consultoria pra 14 negócios pequenos no Brasil. Treze deles começaram a entrevista dizendo "preciso de marketing digital". Nenhum sabia dizer qual problema esperava resolver.
❌ Slop:
Ao abraçar essas práticas, você desbloqueia um potencial transformador. Lembre-se: a jornada começa com um único passo. O futuro é seu.
✅ Humanizado:
Faz isso por três meses. Se não ver mudança em métricas concretas, abandona e tenta outra coisa.
❌ Slop:
A inteligência artificial tem se mostrado uma ferramenta poderosa e versátil em diversas áreas. Suas aplicações abrangentes permitem que empresas dinâmicas potencializem seus resultados de forma significativa.
✅ Humanizado:
IA hoje serve pra três coisas no negócio pequeno: rascunhar texto, transcrever áudio, classificar dado. O resto é hype. Se alguém te oferecer "transformação por IA" sem nomear qual dessas três, é vendedor.
❌ Slop:
🚀 Você já se perguntou como alavancar seu negócio?
Aqui estão 3 estratégias incríveis:
✨ Inove constantemente 🎯 Foque no cliente 💪 Persista
A jornada começa agora! 💫
✅ Humanizado:
Três coisas que aprendi vendendo consultoria em 2024:
Cliente que pede desconto antes da proposta nunca paga em dia.
Briefing de menos de 15 minutos sempre vira retrabalho.
Quem diz "tem que ser viral" não vai investir no que precisa pra viralizar.
Slop tem texturas diferentes em canais diferentes. Atenção redobrada nos pontos típicos:
Texto humano comete imperfeições controladas. Texto humano arrisca opinião. Texto humano se compromete. Texto humano respira.
Slop é a textura do medo: medo de errar, medo de comprometer, medo de não agradar, medo de parar.
Quando estiver em dúvida sobre uma frase, pergunte: alguém com convicção sobre o tema escreveria isso? Se a resposta é "não, é genérico demais", reescreva.
A meta não é "texto perfeito". É texto que soe escrito por alguém que pensou no que estava dizendo.
© Hermes-brasil, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/anti-ai-slop of Hermes-brasil/hermes-brasil.
Open the folder on GitHubat commit 8f94818
Anti AI Slop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Anti AI Slop this skillHermes-brasil/hermes-brasil | 154 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Show Me Your Work Decision Logcursor/plugins | 11k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| Scope Creep Guardlennney/stop-that-shit | 2.5k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Verification Before Completionfarm-fe/farm | 5.6k | 47 repos | ~1k | Automated safety check: Pass | MIT | |
| PUA High-Agency Governancetanweai/pua | 20k | — | ~502 | Automated safety check: Pass | MIT | |
| Loop Change Verifiercobusgreyling/loop-engineering | 11k | 1 repos | ~709 | Automated safety check: Pass | MIT |
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
lennney/stop-that-shit
Keeps an agent focused on the requested work by applying a five-step ladder that checks for direct solutions, real gaps and speculative defenses before adding anything.
farm-fe/farm
A skill your agent uses when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any…
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
cobusgreyling/loop-engineering
Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
Hermes-brasil/hermes-brasil
A runbook, written in Portuguese, for keeping Hermes Agent healthy on a VPS: updates, gateway restarts, health checks and hosts without a systemd user bus.
Hermes-brasil/hermes-brasil
Portuguese notes on a podcast interview with a Nous Research co-founder about Hermes Agent: memory over models, self-improvement, anti-sycophancy and open source.
Hermes-brasil/hermes-brasil
Runs a project on one Kanban board shared by people and AI agents, where a dispatcher splits goals into tasks and any task can go to either a human or an agent.
Hermes-brasil/hermes-brasil
Runs a B2B prospecting pipeline for local shops in Brazil: Google Places lead collection, WhatsApp or Instagram filtering, messaging and SQLite logging.
Hermes-brasil/hermes-brasil
Portuguese guide to building a retrieval-augmented generation assistant over a company's documents, with embeddings, section-based chunking, retrieval and a client workflow.
Hermes-brasil/hermes-brasil
Use quando precisar de pesquisa multi-persona com síntese protegida por evidências.
Categories
Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN. Anti AI Slop is an agent skill from Hermes-brasil/hermes-brasil. Protocolo de revisão editorial para eliminar AI slop em textos PT-BR e EN.
Anti AI Slop fits situations like: tasks that involve Verification before completion.
Run `npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a claude-code`. Or copy the skill folder (skills/anti-ai-slop in Hermes-brasil/hermes-brasil) into .claude/skills/anti-ai-slop in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a codex`. Or copy the skill folder (skills/anti-ai-slop in Hermes-brasil/hermes-brasil) into .agents/skills/anti-ai-slop in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Hermes-brasil/hermes-brasil --skill anti-ai-slop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/anti-ai-slop, .gemini/skills/anti-ai-slop, .github/skills/anti-ai-slop and .opencode/skills/anti-ai-slop in your project.
SKILL.md names no scripts, command-line tools or credentials: Anti AI Slop is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Anti AI Slop is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Anti AI Slop: Show Me Your Work Decision Log (cursor/plugins, 11k stars), Scope Creep Guard (lennney/stop-that-shit, 2.5k stars), Verification Before Completion (farm-fe/farm, 5.6k stars) and PUA High-Agency Governance (tanweai/pua, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Hermes-brasil (a GitHub organization) maintains it in Hermes-brasil/hermes-brasil, which has 154 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 5, 2026.
Source: Hermes-brasil/hermes-brasil on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.