/plugin-health
Check an installed plugin's health — verify manifest SHA256 matches files on disk, detect tampering or corruption. Use when the user asks if a plugin is working, reports a bug, or wants to validate integrity. Triggers on "plugin X está funcionando?", "health plugin X", "status
$ npx -y skills add evolution-foundation/evo-nexus --skill plugin-health --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/plugin-health
Context preview
The summary Claude sees to decide when to auto-load this skill.
Check an installed plugin's health — verify manifest SHA256 matches files on disk, detect tampering or corruption. Use when the user asks if a plugin is working, reports a bug, or wants to validate integrity. Triggers on "plugin X está funcionando?", "health plugin X", "status
SKILL.md
plugin-health.SKILL.mdname: plugin-health
description: Check an installed plugin's health — verify manifest SHA256 matches files on disk, detect tampering or corruption. Use when the user asks if a plugin is working, reports a bug, or wants to validate integrity. Triggers on "plugin X está funcionando?", "health plugin X", "status plugin X", "está ok o plugin Y?".
metadata:
category: plugins
version: 1.0.0
Plugin Health
Run on-demand integrity check for a plugin. Compares `.install-manifest.json` SHA256 entries against actual files on disk. Detects tampering, partial corruption, or missing files.
How to use
Step 1 — Resolve the slug
If not given, list and ask:
from dashboard.backend.sdk_client import evo
plugins = evo.get("/api/plugins")Step 2 — Run health check
health = evo.get(f"/api/plugins/{slug}/health")Response shape:
{
"status": "active" | "broken" | "routine_activation_pending",
"reason": "sha_mismatch" | "missing_files" | null,
"files": [".claude/agents/plugin-foo-agent.md", ...], // if broken
"checked_at": "..."
}Step 3 — Report
**If `active`:** plugin is healthy. Summarise: total files checked, all SHA256 matching, registered hooks/heartbeats/routines still wired.
**If `broken`:**
- List corrupted/missing files
- Suggest options:
- Reinstall: `plugin-install` with same source URL (overwrites files, preserves data)
- Uninstall + reinstall: clean slate
- Manual fix: edit files back to original state (if user knows what was changed)
**If `routine_activation_pending`:** scheduler was offline during install. Tell user to start/restart scheduler.
Error handling
- `HTTP 404 not_found` — plugin not installed.
- `HTTP 500 health_check_failed` — filesystem permission issue or manifest unreadable. Check `ADWs/logs/plugins/`.
Notes for the agent
- Broken state doesn't auto-disable. Plugin files may still work partially. User should decide whether to act.
- If multiple plugins broken at once, likely the user did a git operation or `.claude/` migration. Health check is diagnostic, not autofix.
Read more
name: plugin-health description: Check an installed plugin's health — verify manifest SHA256 matches files on disk, detect tampering or corruption. Use when the user asks if a plugin is working, reports a bug, or wants to validate integrity. Triggers on "plugin X está funcionando?", "health plugin X", "status plugin X", "está ok o plugin Y?". metadata: category: plugins version: 1.0.0
Plugin Health
Run on-demand integrity check for a plugin. Compares `.install-manifest.json` SHA256 entries against actual files on disk. Detects tampering, partial corruption, or missing files.
How to use
Step 1 — Resolve the slug
If not given, list and ask:
from dashboard.backend.sdk_client import evo
plugins = evo.get("/api/plugins")Step 2 — Run health check
health = evo.get(f"/api/plugins/{slug}/health")Response shape:
{
"status": "active" | "broken" | "routine_activation_pending",
"reason": "sha_mismatch" | "missing_files" | null,
"files": [".claude/agents/plugin-foo-agent.md", ...], // if broken
"checked_at": "..."
}Step 3 — Report
**If `active`:** plugin is healthy. Summarise: total files checked, all SHA256 matching, registered hooks/heartbeats/routines still wired.
**If `broken`:**
- List corrupted/missing files
- Suggest options:
- Reinstall: `plugin-install` with same source URL (overwrites files, preserves data)
- Uninstall + reinstall: clean slate
- Manual fix: edit files back to original state (if user knows what was changed)
**If `routine_activation_pending`:** scheduler was offline during install. Tell user to start/restart scheduler.
Error handling
- `HTTP 404 not_found` — plugin not installed.
- `HTTP 500 health_check_failed` — filesystem permission issue or manifest unreadable. Check `ADWs/logs/plugins/`.
Notes for the agent
- Broken state doesn't auto-disable. Plugin files may still work partially. User should decide whether to act.
- If multiple plugins broken at once, likely the user did a git operation or `.claude/` migration. Health check is diagnostic, not autofix.
Other skills on evo-nexus.
- /ai-image-creator
Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, proxied through Cloudflare AI Gateway BYOK). Also analyze/describe existing images using multimodal AI vision. Use when user asks to "generate an image",
Open skill - /create-agent
Create a new custom agent for the workspace. Guides the user through defining agent name, domain, personality, skills, model, and memory folder. Use when the user says 'create an agent', 'new agent', 'add an agent', 'I need a custom agent', or wants to create a specialized agent
Open skill - /create-command
Create a new slash command for Claude Code. Guides the user through defining the command name, what it does, and generates the markdown file in .claude/commands/. Use when the user says 'create a command', 'new command', 'add a slash command', 'I want a shortcut for', or wants
Open skill - /create-goal
Create a Mission, Project, or Goal (Mission → Project → Goal → Task hierarchy) in EvoNexus. Guides the user through picking a mission, choosing or creating a project, defining a measurable goal with metric_type and target_value. Writes to the SQLite goals tables via POST
Open skill - /create-heartbeat
Create a new heartbeat (proactive agent scheduled with a decision prompt) for EvoNexus. Guides the user through picking an agent, setting interval, wake triggers, and the decision prompt that governs when the agent acts. Writes to config/heartbeats.yaml with pydantic validation.
Open skill - /create-integration
Create a new custom integration (API/service wrapper) for the workspace. Guides the user through defining the integration's slug, display name, description, category, and required env keys. Writes .claude/skills/custom-int-{slug}/SKILL.md via POST /api/integrations/custom. Use
Open skill

