How do I install the Camada Agentica skill?

Run npx skillmds@latest add talhamah56/camada-agentica in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Camada Agentica safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Camada Agentica?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Camada Agentica free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Camada Agentica?

talhaMah56 (@talhamah56) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Camada Agentica by talhamah56 — Agent Skill

Name: Camada Agentica
Rating: 4.2 (5 reviews)
Author: talhaMah56

Camada Agentica

Use to propose and generate the project's agentic layer — rules (CLAUDE.md, settings.json), subagents (.claude/agents), skills (.claude/skills), and workflows/CI — tuned to the stack, tools, process, and domain. Proposes with justification and generates only what is approved. Runs standalone as the project evolves or new tools arrive. Trigger with /camada-agentica.

talhaMah56 Updated Sep 22, 2026

File contents

Translation note: Originally authored in Portuguese (pt-BR) by Igor Uehara (igoruehara/spec-driven, MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.

Skill: Project agentic layer

Tunes the layer that lets humans and agents operate the pipeline. Principle: propose with justification (which input motivates each item), generate only what is approved. Reference: docs/engineering/agentic-layer.md.

Gather the context

Stack and quality gates (CLAUDE.md, ADRs), tools (integrations.md), process (Scrum/Kanban), and domain (context-map.md, glossary.md). This is what decides which artifacts make sense.

Propose (do not generate without OK)

Rules: adjustments to CLAUDE.md per stack; .claude/settings.json with an allowlist of the stack's common commands and hooks. ⚠️ Permissions/hooks are sensitive — confirm each one.
Agents (subagents) in .claude/agents/<name>.md (use docs/engineering/_templates/subagent.template.md): e.g. spec-reviewer (DoR gate), domain-modeler, adr-writer, <stack>-tester.
Skills in .claude/skills/<name>/ (use docs/engineering/_templates/skill.template.md): according to the tools, /spec-to-jira, /publicar-confluence (tools-aware).
Workflows: hooks in settings.json (lint/test on Stop). For CI/CD (pipeline gates) delegate to the /setup-ci skill; the PR/MR gate is left to your own review process.

Rules

Each proposal cites the input that motivates it (e.g. Python stack → pytest-tester + allowlist).
Unapproved items become adoption roadmap items (record them in your own planning doc).
Map each artifact in docs/engineering/agentic-layer.md.

---name: camada-agenticadescription: Use to propose and generate the project's agentic layer — rules (CLAUDE.md, settings.json), subagents (.claude/agents), skills (.claude/skills), and workflows/CI — tuned to the stack, tools, process, and domain. Proposes with justification and generates only what is approved. Runs standalone as the project evolves or new tools arrive. Trigger with /camada-agentica.---> **Translation note:** Originally authored in Portuguese (pt-BR) by Igor Uehara ([igoruehara/spec-driven](https://github.com/igoruehara/spec-driven), MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source.# Skill: Project agentic layerTunes the layer that lets humans and agents **operate the pipeline**. Principle: **propose with justification (which input motivates each item), generate only what is approved.** Reference: `docs/engineering/agentic-layer.md`.## Gather the contextStack and quality gates (`CLAUDE.md`, ADRs), tools (`integrations.md`), process (Scrum/Kanban), and domain (`context-map.md`, `glossary.md`). This is what decides which artifacts make sense.## Propose (do not generate without OK)- **Rules:** adjustments to `CLAUDE.md` per stack; `.claude/settings.json` with an allowlist of the stack's common commands and hooks. ⚠️ Permissions/hooks are sensitive — confirm **each one**.- **Agents (subagents)** in `.claude/agents/<name>.md` (use `docs/engineering/_templates/subagent.template.md`): e.g. `spec-reviewer` (DoR gate), `domain-modeler`, `adr-writer`, `<stack>-tester`.- **Skills** in `.claude/skills/<name>/` (use `docs/engineering/_templates/skill.template.md`): according to the tools, `/spec-to-jira`, `/publicar-confluence` (tools-aware).- **Workflows:** hooks in `settings.json` (lint/test on `Stop`). For **CI/CD** (pipeline gates) delegate to the `/setup-ci` skill; the PR/MR gate is left to your own review process.## Rules- Each proposal cites the **input** that motivates it (e.g. Python stack → `pytest-tester` + allowlist).- Unapproved items become **adoption roadmap items** (record them in your own planning doc).- Map each artifact in `docs/engineering/agentic-layer.md`.

Frequently asked questions