perses
Perses platform operations: dashboards, plugins, deployment, migration, and quality.
Best use case
perses is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Perses platform operations: dashboards, plugins, deployment, migration, and quality.
Teams using perses should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/perses/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How perses Compares
| Feature / Agent | perses | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Perses platform operations: dashboards, plugins, deployment, migration, and quality.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Perses Operations
Umbrella skill for all Perses platform operations.
## How to Use (MANDATORY)
**You MUST load the matching reference file before starting any Perses work.** The table below routes tasks to domain-specific references containing the actual methodology, commands, and patterns.
1. **Match** the user's task to a sub-domain in the table below
2. **Load** the reference file using `Read` tool on `${CLAUDE_SKILL_DIR}/references/<name>.md`
3. **Follow** the instructions in the loaded reference exactly
4. If the task spans multiple sub-domains, load each relevant reference
**Anti-pattern**: Do NOT attempt Perses operations from general knowledge alone. The reference files contain percli commands, CUE schema patterns, and deployment procedures specific to this toolkit's Perses setup.
## Sub-domains
| Task | Reference | When to Load |
|------|-----------|-------------|
| First-time setup, server deployment | `references/onboard-deploy.md` | New Perses installation or server configuration |
| Create or review dashboards | `references/dashboard.md` | Any dashboard CRUD operation |
| Manage datasources or variables | `references/datasource-variable.md` | Connecting data sources or template variables |
| Plugin development and testing | `references/plugin.md` | Building or testing Perses plugins |
| Grafana migration | `references/migration.md` | Converting Grafana dashboards to Perses |
| PromQL/LogQL/TraceQL queries | `references/query.md` | Writing or debugging queries |
| Project and RBAC management | `references/project.md` | Multi-tenant setup or permissions |
| Linting, code review, CUE schemas | `references/quality.md` | Code quality or CUE schema work |
| Dashboard-as-Code pipeline | `references/dac.md` | GitOps or CI/CD for dashboards |Related Skills
x-api
Post tweets, build threads, upload media via the X API.
worktree-agent
Mandatory rules for agents in git worktree isolation.
workflow
Structured multi-phase workflows: review, debug, refactor, deploy, create, research, and more.
workflow-help
Interactive guide to workflow system: agents, skills, routing, execution patterns.
wordpress-uploader
WordPress REST API integration for posts and media uploads.
wordpress-live-validation
Validate published WordPress posts in browser via Playwright.
with-anti-rationalization
Anti-rationalization enforcement for maximum-rigor task execution.
voice-writer
Unified voice content generation pipeline with mandatory validation and joy-check. 8-phase pipeline: LOAD, GROUND, GENERATE, VALIDATE, REFINE, JOY-CHECK, OUTPUT, CLEANUP. Use when writing articles, blog posts, or any content that uses a voice profile. Use for "write article", "blog post", "write in voice", "generate content", "draft article", "write about".
voice-validator
Critique-and-rewrite loop for voice fidelity validation.
vitest-runner
Run Vitest tests and parse results into actionable output.
video-editing
Video editing pipeline: cut footage, assemble clips via FFmpeg and Remotion.
verification-before-completion
Defense-in-depth verification before declaring any task complete.