Create your own skills — teach your AI security engineer your way of working

Create your own skills to teach me exactly how your team works. Unlike a regular Pleri prompt — where I apply fresh judgment each time — a skill locks in the process so the output is consistent and repeatable, every run, without anyone having to repeat instructions. Think of a skill as your team’s institutional knowledge, packaged so I can act on it. If we run weekly security reviews a certain way, investigate vulnerabilities with a specific checklist, or always notify a particular channel before closing a finding — that’s a skill worth capturing. Your skills follow the Agent Skills open standard. That means skills you build in Pleri can be exported and used elsewhere, and skills built in Claude Code or another compatible tool can be imported directly into Pleri.

Finding and managing skills

Skills live in the Skills section in the main navigation. From there you can:

Browse all your active skills and templates
Install skills from the Skill Library
Create a new skill from scratch
Import a skill from a file or GitHub URL
Enable or disable skills without deleting them

Four ways to get started

Option 1: Install from the Skill Library

The fastest way to get started. The Skill Library is a curated collection of ready-to-use skills maintained by Plerion — open source and free. Go to Skills → Library, browse the catalog, and click Add on anything that looks useful. Every skill in the library follows the AgentSkills open standard, so you know exactly what you’re getting. You can use them as-is or fork them as a starting point for your own playbooks.

Option 2: Import a file

If someone has shared a skill ZIP with you, go to Skills and click Import. Drop the ZIP in — it will unpack the project files and register the skill automatically. Every skill includes a call instruction that tells you how to trigger it. Open a new chat and use that phrase, and I’ll load the skill and follow its playbook.

Option 3: Build from a prompt

Start a new chat and describe the outcome you want:

Create a skill that runs a daily check on our S3 buckets for public access and notifies #cloud-security if anything is found.

I’ll draft a skill for you. Iterate until it does what you need, then save it. This works best for simpler, repeatable tasks where the steps are straightforward.

Option 4: Use the editor

For anything involving scripts — Python, shell, or other executables — use the skill editor directly. Define the steps, upload your scripts as project files, and wire them together. This is how you get deterministic outputs. When a skill calls a script, I run the script and use its output directly, rather than asking the model to calculate or guess. Use this for anything where precision matters: cost calculations, network tests, data extractions, compliance checks with exact thresholds. Go to Skills and click New skill to open the editor.

How skills load

When a conversation starts, I scan the skill catalog and ask: does any skill match what’s being asked? If yes, I load it immediately and follow the playbook it defines — before doing anything else. This means your custom workflows run consistently, every time, without anyone having to remind me.

Creating a skill manually

When you click New skill, you’ll be asked for:

Name — a short slug used to identify the skill, e.g. weekly-k8s-review
Display name — the human-readable label shown in the UI, e.g. Weekly Kubernetes review
Description — the most important field. This is what I read to decide when to load the skill. Be specific about what triggers it and what it should not be used for
Instructions — the full playbook I follow once the skill is loaded. Use clear, step-by-step language
Tags — optional labels for organizing and filtering your skills, e.g. security, aws, compliance

A good description includes explicit trigger phrases and an exclusion line. For example: “Use for weekly Kubernetes security reviews. Do NOT use for ad hoc cluster questions or one-off CVE lookups.”

Skill scope

Every skill has a scope that controls who can see and use it:

Personal — private to you. Only you can see, edit, and trigger this skill. Great for personal workflows, experiments, or role-specific playbooks you don’t need to share
Tenant — shared across your entire organization. Only admins can create or modify tenant skills, but they apply to every user automatically. Use these for agreed-upon team processes like escalation procedures or compliance checks
Template — published as a starting point others can fork. Templates appear in the skill gallery and can be installed by anyone in your organization. When someone installs a template, they get their own editable personal copy

Tenant skills take precedence over personal skills. If a personal skill and a tenant skill share the same name, the tenant skill wins — so admins can enforce organization-wide standards that individuals can’t accidentally override.

Start with a personal skill to iterate quickly, then promote it to tenant scope once the team agrees on the process.

Organizing skills with tags

Tags let you group and filter skills so they’re easier to find as your collection grows. You can add up to 20 tags per skill, each up to 64 characters. Good tags are short and meaningful — think of them like labels on a folder. Some examples:

Tag	What it groups
`aws`	Skills that work with AWS resources
`compliance`	Audit and compliance workflows
`weekly`	Scheduled review skills
`incident`	Incident response playbooks
`team:security`	Skills owned by the security team

You can set tags when creating a skill or ask me to update them anytime:

Add the tags "aws" and "compliance" to my weekly-k8s-review skill.

Skill Library

The Skill Library is a curated, open-source collection of skills maintained by Plerion in the plerionhq/pleri-skills repository. Every skill in the library:

Follows the AgentSkills open standard
Is reviewed and maintained by the Plerion team
Is free to use, fork, and customize

Go to Skills → Library to browse what’s available and install with one click.

Currently available skills

Skill	Category	What it does
Brand Guidelines	General	Keeps responses aligned with Plerion’s brand voice and communication standards
Cloud Cost Analyzer	Reporting	Analyzes cloud spend, identifies idle and oversized resources, and highlights cost savings opportunities

More skills are added regularly. If you’ve built something useful for your team, consider contributing it back — it only takes a SKILL.md file.

Installing a skill from the library

Go to Skills → Library
Find the skill you want and click Add
The skill is now active in your sessions

When you install a library skill, you get your own personal copy. You can rename it, edit the instructions, or promote it to tenant scope — it’s yours to customize.

Template skills

Not sure where to start? The skill template gallery gives you pre-built playbooks you can install with one click. Each template covers a common security workflow, ready to use out of the box or customize to fit your team. Go to Skills and click Templates to browse the gallery. Available templates include:

Template	What it does
Incident Response Runbook	Structured incident response following NIST SP 800-61 and SANS frameworks
Executive Risk Report	CxO-level risk summaries with trend analysis
Compliance Audit	Audit against SOC 2, ISO 27001, PCI-DSS, NIST CSF, CIS Benchmarks, and HIPAA
Vulnerability Triage	CVE investigation with CVSS scoring and composite risk assessment
Brand Guide	Enforce brand voice, formatting, and terminology standards in reports
Weekly Security Digest	Structured weekly summaries with metrics and trends

When you install a template, it creates a personal copy you own. You can rename it, edit the instructions, attach your own files, or promote it to tenant scope — the template is just a starting point.

Importing skills

You can import skills from external sources instead of building from scratch. This is useful for sharing skills across teams, pulling in community playbooks, or migrating skills between environments.

Import from a zip file

Go to Skills and click Import. Upload a .zip file containing a SKILL.md at the root. The SKILL.md file uses frontmatter to define the skill metadata:

---
name: my-custom-skill
description: Use when asked to run a custom security check.
instructions: |
  1. Pull all open findings from the last 7 days
  2. Group by severity
  3. Post a summary to Slack
---

Any other files in the zip (scripts, references, assets) are automatically uploaded and attached to the skill.

Import from GitHub

You can also import directly from a GitHub repository URL. Paste the repo URL and I’ll pull the skill definition from it. Supported formats:

https://github.com/owner/repo — imports from the repo root
https://github.com/owner/repo/tree/branch/subdirectory — imports from a specific subdirectory

The repository must contain a SKILL.md file at the target location.

If an imported skill has the same name as an existing skill, a numeric suffix is added automatically (e.g., my-skill becomes my-skill-2) so nothing gets overwritten.

Attaching files

Skills can carry supporting files — scripts, reference documents, or other assets your playbook depends on. Files live in three directories:

Directory	Purpose
`scripts/`	Executable scripts I can run directly, e.g. a Python cost calculator or network test
`references/`	Supporting docs, checklists, or runbooks I should consult
`assets/`	Other resources, templates, or data files

You can upload files directly from the Skills page, or ask me to create them for you.

Examples

Here are a few examples to show what’s possible.

Branded security reports

Attach your brand guidelines as a reference file, point me to your logo, and I’ll apply your color palette, typography, and layout rules every time I generate an HTML report.

Name: branded-security-report
Description: Use when asked to generate a security report, executive summary, or
  board-ready output. Do NOT use for quick chat summaries or Slack messages.

Instructions:
1. Load references/brand-guidelines.md for color palette, fonts, and layout rules
2. Use the logo at https://cdn.example.com/logo/plerion-logo.png in the header
3. Structure the report with: executive summary, key findings, risk breakdown, recommended actions
4. Apply the primary color (#FF6B35) to headings and severity badges
5. Include a footer with the report date and "Confidential — internal use only"
6. Output as HTML, ready to print or export to PDF

Weekly Kubernetes security review

Name: weekly-k8s-review
Description: Use when asked to run a weekly Kubernetes security review. Covers
  cluster misconfigurations, RBAC risks, pod security, and image vulnerabilities.
  Do NOT use for ad hoc cluster questions.

Instructions:
1. Pull all open Kubernetes findings from the last 7 days
2. Group by severity: critical, high, medium
3. For each critical finding, check if a Jira ticket already exists — create one if not
4. Summarize the top 5 risks with recommended next steps
5. Post a summary to #security-reviews in Slack

CVE triage for Python services

Name: python-cve-triage
Description: Use when asked to triage or investigate a CVE affecting our Python
  services. Do NOT use for non-Python languages or general CVE lookups.

Instructions:
1. Search our code repositories for the affected package and version
2. List all impacted services with their current version and owner
3. Assess exploitability — is this actually reachable in our environment?
4. Draft a Jira ticket for each affected service with severity, impact, and a fix recommendation
5. Flag any service in production as P1

Production finding escalation

Name: prod-finding-escalation
Description: Use when a critical or high finding is detected in a production account.
  Triggers on phrases like "production finding", "prod alert", or "escalate finding".
  Do NOT use for staging or dev environments.

Instructions:
1. Confirm the finding is in a production-tagged account
2. Assess blast radius — what assets are affected?
3. Create a Jira P1 ticket assigned to the on-call engineer
4. Send a Slack message to #security-incidents with the finding summary and ticket link
5. Set a follow-up task to check status in 24 hours

Script-backed network test

For tasks that need precise, deterministic results, attach a script and I’ll call it directly:

Name: network-connectivity-test
Description: Use when asked to run a network connectivity or reachability test.
  Do NOT use for general network troubleshooting questions.

Instructions:
1. Run scripts/network-test.py with the target host and port as arguments
2. Parse the output: latency, packet loss, open ports
3. Flag any result outside acceptable thresholds
4. Create a Jira ticket if a critical service is unreachable
5. Post a summary to #infrastructure

Attach scripts/network-test.py and I’ll call it directly — the numbers come from the script, not the model.

Working with skills conversationally

You can also ask me to create, update, or manage skills directly in chat:

Create a skill that runs a daily check on our S3 buckets for public access.
It should notify #cloud-security if anything is found.

Show me all our skills and their current status.

Update the python-cve-triage skill to also check our Bitbucket repositories.

Add the tags "aws" and "security" to the weekly-k8s-review skill.

Smarter questions, better guidance

When a skill needs input before proceeding, I’ll ask structured questions with clear options. Each option includes a short label and a description of the trade-offs so you can decide quickly. When it helps, I’ll show side-by-side previews so you can compare approaches visually. You’ll also see contextual nudges throughout the UI that suggest relevant skills, highlight best practices, and guide you toward the right workflow for the task at hand.

Disabling a skill

If a skill is no longer relevant, you can disable it from the Skills page. Disabled skills stay saved but won’t appear in the catalog or be loaded by me — so you can safely pause them without losing the playbook.

Limitations

Text files only: Skill files support text-based formats — .md, .txt, .py, .sh, .js, .ts, .json, .yaml, .yml, .csv, .html, and .css. Binary files such as images, PDFs, and office documents are not supported. For logos and images, reference them by URL in your skill instructions instead.
File size: Individual files are capped at 400KB.
Logos by URL: Logo and image assets must be hosted externally and referenced as a URL in your skill instructions or brand guidelines file.
Tags: Up to 20 tags per skill, each up to 64 characters.

​Finding and managing skills

​Four ways to get started

​Option 1: Install from the Skill Library

​Option 2: Import a file

​Option 3: Build from a prompt

​Option 4: Use the editor

​How skills load

​Creating a skill manually

​Skill scope

​Organizing skills with tags

​Skill Library

​Currently available skills

​Installing a skill from the library

​Template skills

​Importing skills

​Import from a zip file

​Import from GitHub

​Attaching files

​Examples

​Branded security reports

​Weekly Kubernetes security review

​CVE triage for Python services

​Production finding escalation

​Script-backed network test

​Working with skills conversationally

​Smarter questions, better guidance

​Disabling a skill

​Limitations

Finding and managing skills

Four ways to get started

Option 1: Install from the Skill Library

Option 2: Import a file

Option 3: Build from a prompt

Option 4: Use the editor

How skills load

Creating a skill manually

Skill scope

Organizing skills with tags

Skill Library

Currently available skills

Installing a skill from the library

Template skills

Importing skills

Import from a zip file

Import from GitHub

Attaching files

Examples

Branded security reports

Weekly Kubernetes security review

CVE triage for Python services

Production finding escalation

Script-backed network test

Working with skills conversationally

Smarter questions, better guidance

Disabling a skill

Limitations