Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Skill Evolution Api

ASecurity

Use for WhatsApp automation with Evolution API, including instance lifecycle, QR pairing, inbound and outbound messages, webhooks, consent, tenant isolation, queues, idempotency, rate limits, retries, audit logs, and reliable delivery.

53 stars
0 votes
0 copies
0 views
Added 9/26/2026
ai-agentsgogitapisecurity

Works with

cliapi

Security Analysis

A100/100

Scanned 9/26/2026

$npx -y skills add IAPro-Community/Orquestrador-Maestro --skill skill-evolution-api --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Evolution Api?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skill Evolution Api
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/iapro-community-skill-evolution-api/badge)](https://www.skillsdirectory.com/skills/iapro-community-skill-evolution-api)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: skill-evolution-api
description: Use for WhatsApp automation with Evolution API, including instance lifecycle, QR pairing, inbound and outbound messages, webhooks, consent, tenant isolation, queues, idempotency, rate limits, retries, audit logs, and reliable delivery.
category: communication
risk: medium
source: evolution-api-local-patterns
last_verified: 2026-08-06
---

# Evolution API

Use this skill when integrating WhatsApp through Evolution API. Treat every message as sensitive customer communication.

## Core Workflow

1. Confirm the tenant, WhatsApp account owner, business purpose, user consent model, and allowed message categories.
2. Keep Evolution API keys, webhook secrets, and instance credentials server-side only.
3. Model each instance as tenant-owned state with lifecycle, QR pairing state, webhook status, heartbeat, and disconnect reason.
4. Queue outbound sends. Apply per-instance, per-tenant, and per-contact rate limits before enqueueing.
5. Assign every outbound request a stable idempotency key based on tenant, instance, recipient, template or body hash, and campaign or workflow ID.
6. Treat webhooks as at-least-once delivery. Verify signature when available, dedupe by provider message ID, and make handlers idempotent.
7. Persist delivery, read, inbound, disconnect, reconnect, and pairing events as append-only state transitions.
8. Redact message bodies in logs unless a support or audit policy explicitly requires short-lived encrypted retention.
9. Surface recoverable admin states: QR expired, disconnected, webhook failing, send queued, send failed, rate limited, and consent missing.

## Current API Boundary

- Target Evolution API v2+ and use the instance's documented base URL plus the `apikey` header.
- Common v2 routes include `POST /instance/create` and `POST /message/sendText/{instanceName}`; verify the exact route in the deployed instance's OpenAPI/docs before coding because route shapes can differ between v1 and v2.
- Starting with Evolution API v2.4.0, self-hosted instances require activation/licensing before business endpoints serve traffic. Add license status/activation to deployment readiness checks and surface `503` activation failures distinctly from WhatsApp failures.

## Consent and Compliance

- Require explicit opt-in before sending non-transactional messages.
- Store consent source, timestamp, contact identity, tenant, scope, and revocation timestamp.
- Stop queued campaign or automation messages immediately when consent is revoked.
- Keep templates, campaign labels, and operator identity attached to sends for audit.

## Minimal Data Model

- `whatsapp_instances`: tenant ID, owner ID, instance name, status, QR state, webhook status, last heartbeat, disconnect reason.
- `whatsapp_contacts`: tenant ID, normalized number, profile name, consent state, consent scope, last inbound time.
- `message_events`: tenant ID, instance ID, provider message ID, idempotency key, direction, status, retry count, error class, timestamps.
- `message_threads`: tenant ID, contact ID, assignment state, last message time, unread count.

## Verification

- Test QR pairing, reconnect, disconnect, outbound queueing, duplicate outbound retry, inbound webhook dedupe, revoked consent, and rate-limit behavior.
- Confirm API keys and message bodies are absent from client bundles and normal logs.
- Replay the same webhook payload twice and verify only one business effect occurs.

## Official References

- https://docs.evolutionfoundation.com.br/en/evolution-api/create-instance
- https://docs.evolutionfoundation.com.br/evolution-api/send-text-message
- https://github.com/evolution-foundation/evolution-api/releases

## Related Skills

- `skill-saas-admin-dashboard`
- `skill-unified-analytics`
- `skill-security-hooks`

Attribution

IAPro-CommunityIAPro-Community
View sourceSee grades on GitHubMore from IAPro-Community →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →