12 free templates

Agent Skills Workflow Templates

These free agent skill templates bundle SKILL.md instructions, Python tools, and custom actions into reusable agent workflows. Heym is source-available and self-hosted, so you can run Python skills next to your agents on your own infrastructure and reuse them across projects.

SKILL.md bundles
Python tools
file parsing
custom agent actions

Browse templates

Use cases

What you can automate with Agent Skills templates

Bundled SKILL.md

Ship an agent with a packaged skill that gives it a repeatable, expert capability.

Python tools

Call a Python skill from an agent to parse files, transform data, or write outputs.

File parsing

Decode and extract text from PDFs or feeds inside the agent run, then return clean results.

Custom actions

Define reusable actions an agent can invoke as typed tools.

Popular Agent Skills templates

YouTube Channel RSS to CSV — SKILL.md & Python Tutorial Tracker

Fetch any YouTube channel's public RSS feed and export video titles, URLs, and publish dates as a clean CSV — great for tracking SKILL.md and Python tutorial creators like Nate Herk.

PDF / DOCX Translation Agent

Translate the full text of any uploaded document using an AI agent.

Chat with Drive Docs

Ask questions about your Google Drive PDF files. An agent lists your Drive, reads the file you need, extracts its text, and answers in plain language.

Browse all Agent Skills templates

Pick a workflow, copy the JSON, and adapt the nodes for your team.

12 templates·Agent Skills

Sticky Note

YouTube Channel RSS to CSV

Fetch any YouTube channel's public video feed, export it as a clean CSV, and save to Drive — no API key needed.
Pre-wired to Nate Herk's channel (SKILL.md & Python tutorials).

Main path

Sticky Note

Before you run

No credential needed — YouTube RSS feeds are public.
To track a different channel, swap the channel_id in the FetchChannelFeed URL.
The Agent node requires an OpenAI (or compatible) credential to run the skill.

FetchChannelFeed

ParseToCSV

zai-glm-4.7

VideoCSV

YouTube Channel RSS to CSV — SKILL.md & Python Tutorial Tracker

Marketing & SEO

Fetch any YouTube channel's public RSS feed and export video titles, URLs, and publish dates as a clean CSV — great for tracking SKILL.md and Python tutorial creators like Nate Herk.

#YouTube#RSS#CSV

Sticky Note

Chat With Docs (Drive)

This workflow lets you chat with your Google Drive files.
Features:

List available Drive files

Sticky Note

Drive Tools:
1. listDriveFiles — Lists all files in Drive
2. readDriveFile — Reads a specific file (returns base64)
Python Skills:

userQuery

listDriveFiles

readDriveFile

docAgent

zai-glm-4.7

answer

Chat with Drive Docs

Document Ops

Ask questions about your Google Drive PDF files. An agent lists your Drive, reads the file you need, extracts its text, and answers in plain language.

#Drive#PDF#Agent

start

steelmanAgent

openai/gpt-5-nano

stresstestAgent

anthropic/claude-opus-4

gapfinderAgent

z-ai/glm-4.7

setFields

Sticky Note

Blind Eval Trio
Pre-commitment self-evaluation for agent runtimes.

3 cross-lab agents → 3 independent evaluations:
steelman (defends), stress_test (attacks), gap_finder (what's missing).
No synthesizer — calling agent integrates.

Structural integrity
• 3 model labs → cross-lab decorrelation
• Tool lockout per role (no role-switching)
• No synthesizer agent (3 raw outputs)
• Forced output structure + articulation gate

steelman
gpt-5-nano + harness_reasoning
Role: strongest case FOR the method.
Hard rule: pure advocacy. Zero smuggled critique.

stress_test
claude-opus-4 + harness_anti_deception

Role: where the method BREAKS.
Hard rule: severity-tagged failures + concrete scenarios.

gap_finder
glm-4.7 + harness_memory

Role: what's MISSING (steps + articulation depth).
Hard rule: name 3 deeper implicit assumptions.

Output: structured JSON
{ steelman, stress_test, gap_finder, usage_note }

Three voices, no synthesis. Integrate; do not aggregate.

Sticky Note

Verified across domains

Caught hidden behavior changes (refactor planning), compliance gaps (payments migration), premature containment (security IR), framing tensions (investigative cases), unvalidated assumptions (strategic decisions including meta-eval of itself).

Role discipline + cross-lab decorrelation generalize. No domain-specific tuning required.

Sticky Note

Example output

Task: Auto-merge Dependabot PRs after CI passes.

steelman defends:
"Leverages standard platform capabilities; CI gating preserves code quality; uniform across all updates."

stress_test attacks (HIGH):
"Dependency hijacking — compromised maintainer publishes backdoored version, CI passes (tests don't catch malware payload), auto-merge deploys to production."

gap_finder finds:
"Missing: scope limiting, version constraints, rollback procedure. 'CI catches breaking changes' silently assumes integration coverage AND env parity AND end-to-end scenarios."

→ One agent advocates, one attacks, one finds gaps. Calling agent integrates.

Sticky Note

Callable from any agent

heym exposes this workflow as an HTTP endpoint:
POST /api/workflows/{id}/execute/stream

SSE events stream as each node completes. Any agent runtime ;
Claude Code, Cursor, Codex, custom Python — can curl it directly. One workflow, infinite integrations.

Sticky Note

Built with heym + ejentum-mcp cognitive harness.
Repo:
github.com/ejentum/agent-teams
ejentum.com

Blind Eval Trio

AI Agents

Three cross-lab agents evaluate any decision blind: steelman defends, stress_test attacks, gap_finder finds what's missing. No synthesizer — you integrate.

#Multi-Agent#Evaluation#Ejentum

Sticky Note

CSV skill setup

Pick an LLM credential in csvStatsAgent.
Paste CSV with a header row into csvData.
The csv_summary_stats Python skill does the math, not the model.
No API key needed.

csvData

csvStatsAgent

z-ai/glm-4.7

statsResult

CSV Stats Analyzer (Agent Skill)

Data & Analytics

An agent runs a bundled Python skill that parses CSV text and returns per-column summary statistics — no API keys needed.

#Skills#Python#CSV

Sticky Note

HTML table skill setup

Pick an LLM credential in tableConverterAgent.
Paste HTML containing a table into htmlInput.
The html_table_to_markdown Python skill does the parsing.
No external dependencies.

htmlInput

tableConverterAgent

z-ai/glm-4.7

markdownResult

HTML Table to Markdown (Agent Skill)

Document Ops

An agent runs a bundled Python skill that converts HTML tables into clean Markdown tables using only the standard library.

#Skills#Python#HTML

Sticky Note

PII redactor setup

Pick an LLM credential in redactionAgent.
Paste text into rawText.
The pii_redactor Python skill removes emails, phones, cards, SSNs.
A helpful first pass, not a compliance guarantee.

rawText

redactionAgent

z-ai/glm-4.7

redactedResult

PII Redactor (Agent Skill)

Legal & Compliance

An agent runs a bundled Python skill that redacts emails, phone numbers, card numbers, and SSNs from text before it is shared.

#Skills#Python#PII

Sticky Note

Invoice skill setup

Pick an LLM credential in invoiceAgent.
Edit line_items, tax_rate, and discount_percent in invoiceInput.
The invoice_line_total Python skill does the math.
Figures are precise and rounded to cents.

invoiceInput

invoiceAgent

z-ai/glm-4.7

invoiceResult

Invoice Total Calculator (Agent Skill)

Finance Ops

An agent runs a bundled Python skill that computes line totals, discount, tax, and the grand total from invoice items.

#Skills#Python#Invoice

Sticky Note

Readability skill setup

Pick an LLM credential in readabilityAgent.
Paste copy into contentText.
The text_readability Python skill computes the scores.
Aim for higher Flesch Reading Ease for broad audiences.

contentText

readabilityAgent

z-ai/glm-4.7

readabilityResult

Text Readability Scorer (Agent Skill)

Marketing & SEO

An agent runs a bundled Python skill that scores text for readability with Flesch Reading Ease and grade level.

#Skills#Python#Readability

Sticky Note

Cease and desist PDF setup

Pick an LLM credential in ceaseDesistAgent.
Fill the parties, issue, and deadline in cdIntake.
The cease_desist_pdf Python skill renders the PDF.
Output is a draft for review, not legal advice.

cdIntake

ceaseDesistAgent

GLM-4.7

ceaseDesistResult

Cease and Desist Letter (Agent Skill, PDF)

Legal & Compliance

An agent drafts a cease and desist letter, then a bundled Python skill renders it into a formatted, downloadable PDF.

#Skills#Python#PDF

Sticky Note

Demand letter PDF setup

Pick an LLM credential in demandAgent.
Edit creditor, debtor, line_items, and deadline in demandIntake.
The demand_letter_pdf Python skill totals amounts and renders the PDF.
Output is a draft for review, not legal advice.

demandIntake

demandAgent

GLM-4.7

demandResult

Demand Letter Generator (Agent Skill, PDF)

Legal & Compliance

An agent drafts a formal payment demand letter; a bundled Python skill totals the amounts owed and renders a downloadable PDF.

#Skills#Python#PDF

Sticky Note

Privacy policy PDF setup

Pick an LLM credential in privacyAgent.
Edit company, website, and data collected in policyIntake.
The privacy_policy_pdf Python skill renders the numbered PDF.
Output is a draft for review, not legal advice.

policyIntake

privacyAgent

GLM-4.7

privacyResult

Privacy Policy Generator (Agent Skill, PDF)

Legal & Compliance

An agent drafts a GDPR and CCPA aware privacy policy; a bundled Python skill renders the numbered sections into a downloadable PDF.

#Skills#Python#PDF

Sticky Note

Before you run

Connect an LLM credential to TriageMobileCrash.
Connect GitHub and set the owner and repository.
Upload only logs you are authorized to process.
Test redaction with synthetic device IDs and tokens.
Review the generated issue before sharing it publicly.

MobileCrashFile

TriageMobileCrash

z-ai/glm-4.7

CreateMobileCrashIssue

CrashIssueReceipt

Mobile App Crash Log to GitHub Triage

Dev & IT Ops

Upload an iOS or Android crash log, redact sensitive identifiers, fingerprint the failure, and open a developer-ready GitHub issue.

#Mobile Apps#iOS#Android

All 12 Agent Skills templates, A to Z

Why teams run Agent Skills workflows on Heym

Heym is a source-available, self-hosted AI workflow platform for agentic automation: agents that call tools, retrieve from your own documents, and pause for human review when a step needs it.

Free and source-available

Released under MIT with a Commons Clause, with no per-task or per-execution pricing.

Self-hosted

Runs on your own infrastructure with Docker, so your data and credentials stay yours.

One-paste import

Copy a template JSON, paste it onto the canvas, and run it in minutes.

Agentic by default

Agent nodes, MCP tools, and built-in RAG on a visual workflow canvas.

Agent Skills templates FAQ

What is an agent SKILL.md?

A SKILL.md is a packaged instruction file that gives an agent a specific, reusable capability, often paired with a Python tool. These templates show skills bundled directly into a Heym agent workflow.

Can agent skills run Python?

Yes. Heym agents can call Python skills during a run to parse files, transform data, and generate outputs, then return the result as a tool response.

Can I customize a template after importing it?

Every node, prompt, credential, and connection is editable after import. Swap the model, change the trigger, add or remove tools, and rewire branches directly on the canvas without writing boilerplate.

Is Heym free and self-hosted?

Yes. Heym is source-available under an MIT license with a Commons Clause, so you can run every template on your own infrastructure with Docker. There is no per-task or per-execution pricing, and your data and credentials stay inside your environment.

What makes these different from ordinary automation templates?

Each one runs on an AI-native canvas, so agent nodes, MCP tools, and built-in RAG sit in the same workflow as the triggers, branching, and integrations. That is the difference between a fixed sequence of steps and an agentic workflow that can retrieve context, call tools, and pause for human review while it runs.

How to build an AI agent What is MCP?Browse all Heym nodes

Template categories

Explore other use cases

View all templates

Marketing & SEO

Content repurposing, social publishing, SEO research, analytics reporting, and audience monitoring for growth teams.

Sales & CRM

Lead qualification, CRM enrichment, personalized outreach, follow-up workflows, and revenue handoffs.

Customer Support

Email triage, FAQ replies, human approval checkpoints, inbox summaries, and customer escalation routing.

Legal & Compliance

Governed research, review checkpoints, policy-sensitive document handling, and audit-friendly agent workflows.

HR & Recruiting

Candidate search, resume-style ranking, recruiting summaries, interview preparation, and hiring pipeline automation.

Finance Ops

Invoice extraction, payment webhooks, receipt creation, pricing monitors, and finance data handoffs.

Document Ops

RAG ingestion, document Q&A, PDF and DOCX workflows, translation, file sharing, and structured extraction.

Data & Analytics

Spreadsheet enrichment, ETL-style syncs, schema remapping, BigQuery handoffs, and reporting pipelines.

Dev & IT Ops

Release monitoring, Sentry issue triage, API reliability, code review, WebSocket alerts, RabbitMQ jobs, and internal tool workflows.

App Integrations

Connect Slack, Discord, Telegram, HTTP APIs, MCP tools, and external systems with reusable workflow patterns.

Personal Productivity

Personal assistants, briefing emails, meeting summaries, lightweight research, reminders, and daily automation.

Education & Learning

Language learning, study guides, lesson planning, assessment feedback, research workflows, and LMS operations.

Healthcare

Clinical-style triage examples, structured health summaries, specialist review patterns, and careful human oversight.

Logistics & Supply Chain

Shipment tracking, delivery exceptions, carrier rates, freight audit, dock scheduling, and supply chain data checks.

Energy & Utilities

Smart meter anomalies, field work orders, outage updates, solar performance, utility bill checks, and interconnection reviews.

E-commerce

Return triage, review insights, order fraud screening, cart recovery, product catalog quality, and inventory checks.

AI Agents

General LLM and agent workflows for classification, generation, evaluation, image creation, and text-to-workflow examples.

Agent Teams

Orchestrator, researcher, writer, validator, and specialist agent patterns for multi-step AI work.

Operations Automation

Scheduled checks, debounce steps, generic routers, async dispatchers, and repeatable business operations.

What you can automate with Agent Skills templates

Bundled SKILL.md

Python tools

File parsing

Custom actions

Popular Agent Skills templates

YouTube Channel RSS to CSV — SKILL.md & Python Tutorial Tracker

PDF / DOCX Translation Agent

Chat with Drive Docs

Browse all Agent Skills templates

YouTube Channel RSS to CSV — SKILL.md & Python Tutorial Tracker

Chat with Drive Docs

Blind Eval Trio

CSV Stats Analyzer (Agent Skill)

HTML Table to Markdown (Agent Skill)

PII Redactor (Agent Skill)

Invoice Total Calculator (Agent Skill)

Text Readability Scorer (Agent Skill)

Cease and Desist Letter (Agent Skill, PDF)

Demand Letter Generator (Agent Skill, PDF)

Privacy Policy Generator (Agent Skill, PDF)

Mobile App Crash Log to GitHub Triage

Why teams run Agent Skills workflows on Heym

Free and source-available

Self-hosted

One-paste import

Agentic by default

Agent Skills templates FAQ

Related guides

Explore other use cases

Marketing & SEO

Sales & CRM

Customer Support

Legal & Compliance

HR & Recruiting

Finance Ops

Document Ops

Data & Analytics

Dev & IT Ops

App Integrations

Personal Productivity

Education & Learning

Healthcare

Logistics & Supply Chain

Energy & Utilities

E-commerce

AI Agents

Agent Teams

Operations Automation

YouTube Channel RSS to CSV — SKILL.md & Python Tutorial Tracker

Chat with Drive Docs

Blind Eval Trio

CSV Stats Analyzer (Agent Skill)

HTML Table to Markdown (Agent Skill)

PII Redactor (Agent Skill)

Invoice Total Calculator (Agent Skill)

Text Readability Scorer (Agent Skill)

Cease and Desist Letter (Agent Skill, PDF)

Demand Letter Generator (Agent Skill, PDF)

Privacy Policy Generator (Agent Skill, PDF)

Mobile App Crash Log to GitHub Triage