Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/trycomp-io/comp-skills/ai-native-hrnpx skills add trycomp-io/comp-skills --skill ai-native-hrgit clone --depth 1 https://github.com/trycomp-io/comp-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/trycomp-io/comp-skills/ai-native-hr)<a href="https://agentmods.dev/skills/trycomp-io/comp-skills/ai-native-hr"><img src="https://agentmods.dev/badge/skills/trycomp-io/comp-skills/ai-native-hr.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00211 | $0.03269 |
| Opus 5 | $0.00105 | $0.01635 |
| Sonnet 5 | $0.00042 | $0.00654 |
| Haiku 4.5 | $0.00021 | $0.00327 |
Grade A, and why
ai-native-hr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual-mode operation (Code + Cowork)
HTML pelo design system (obrigatório). Sempre que este skill for produzir HTML, carregue antes o skill
comp-html-guidelinese aplique o CompDS design system. Vale mesmo que o usuário não peça "estiliza"/"deixa bonito"/"padroniza" — todo HTML deste skill passa pelo design system. Isso não altera a metodologia abaixo; governa só a camada visual do HTML.
Detect platform at start:
- If you have the
Bashtool AND can run Python → use script mode (generates the interactive standalone HTML). Existing workflow below. - Otherwise (e.g., Claude Cowork) → use inline mode: conduct the assessment conversationally per the "Inline assessment logic" section, compute the score in chat, present a markdown scorecard. If an HTML artifact tool is available, ALSO render a self-contained HTML result (Tailwind CDN) matching the script's output.
Inline assessment logic (Cowork mode)
5 áreas × 3 perguntas = 15 perguntas. As opções vêm ordenadas do nível mais maduro (1ª) ao menos maduro (5ª): 1ª opção = 5 (N5), 2ª = 4 (N4), 3ª = 3 (N3), 4ª = 2 (N2), 5ª = 1 (N1).
Os 5 níveis (AI Maturity Map da Comp)
- N1 Produtividade Individual: pessoas usam IA pra ganhar produtividade no próprio trabalho. Variância alta entre power users e o resto.
- N2 Produtividade do Time: skills e agentes compartilhados cobrem a maior parte das tarefas operacionais.
- N3 Sistema Operacional Contextual: uma camada agêntica única executa trabalho complexo dentro de parâmetros humanos.
- N4 Inteligência de Decisão: camada agêntica propõe decisões baseada nos padrões dos melhores humanos.
- N5 Inteligência Adaptativa: camada agêntica aprende sozinha dos resultados, refinando julgamento continuamente.
Área 1: Recrutamento & TA
- Q1: Como a IA aparece no recrutamento hoje? (5) Camada agêntica autônoma que aprende com sucesso pós-contratação / (4) IA recomenda candidatos/scores; humanos validam / (3) Um agente único cobre todo o pipeline integrado ao ATS / (2) Time compartilha skills/agentes (JD, follow-ups, summary) / (1) Recruiters usam ChatGPT/Claude pra tarefas pontuais
- Q2: Como vocês conseguem candidatos qualificados? (5) Sistema autoaprende a cada hire / (4) Modelo de matching gera shortlist; humano valida / (3) Um agente faz outreach + qualificação integrado ao CRM / (2) Skills compartilhadas pra outreach, qualificação manual / (1) Busca manual no LinkedIn com ajuda pontual de IA
- Q3: Tempo médio pra entrevistar um candidato qualificado depois de aberta a vaga? (5) Horas / (4) Dias (agentes fazem 80%) / (3) 1 semana / (2) 2-3 semanas / (1) 4+ semanas
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 159 lines · 211 tokens per session scan A ce1343923244
ai-native-hr is a skill published in the GitHub repository trycomp-io/comp-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 211 tokens to every session and 3,269 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
previdencia-brasil
Use para INSS, aposentadoria, benefícios previdenciários, cálculo de contribuição, regras de transição 2026, auxílio-doença, salário-maternidade, pensão por morte. Ativa em "aposentadoria", "INSS", "quando posso me aposentar", "auxílio-doença", "salário-maternidade", "BPC", "contribuição INSS".
consumidor-brasil
Use para direitos do consumidor: CDC, prazo de arrependimento, garantia legal, vício de produto, como reclamar, Procon, Reclame Aqui, ação no Juizado Especial. Ativa em "meus direitos de consumidor", "produto com defeito", "empresa não reembolsou", "prazo de devolução", "garantia", "Procon".
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
master-debate
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争. Differs from /compare-masters (parallel single-round) by being adversarial multi-round via fresh-subagent orchestration. Topics 空有 / 禅净 / 性相 / 戒律 vs 内观 — trigger is adversarial framing…
master-atisha
Use when user asks about 藏传, 噶当派, Kadam, 三士道, 菩提道灯论, Bodhipathapradīpa, 阿底峡, Atiśa, 金洲大师, 七因果, 自他相换, 菩提心, 依止善知识, 暇满, 业果, 噶当六论, 仲敦巴, 热振寺, 藏地后弘期, or wants teaching in 阿底峡尊者 Atiśa's voice. Triggers include "阿底峡"、"觉沃杰"、"Atisha"、"Jowo Je"、"菩提道灯"、"道灯论"、"三士道"、"七因果"、"自他相换"、"金洲"、"噶当"、"仲敦巴"、"热振寺"、"道次第之祖" — invoke whenever…