Agent skill

Opensource Guide Coach

by calf-ai in calf-ai/calfkit-sdk

A skill your agent uses when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding…

Apache-2.0Auto-check passedBackend & APIs

Install Opensource Guide Coach

skills CLI
$ npx skills add calf-ai/calfkit-sdk --skill opensource-guide-coach -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install calf-ai/calfkit-sdk opensource-guide-coach --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/calf-ai/calfkit-sdk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/opensource-guide-coach .claude/skills/opensource-guide-coach && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
opensource-guide-coach
GitHub stars
149
Used in
1 other repo
Token cost
~2.1k tokens
SKILL.md length
1,032 words
Files
4 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding…

  • Works in 5 steps: Identify the situation → Choose the smallest useful guide set → Convert guidance into action → …
  • A user wants guidance on starting
  • SKILL.md covers Overview, Source Of Truth, When To Use and Working Style, plus 14 more sections
  • Reaches opensource.guide

What it does

Opensource Guide Coach is an agent skill from calf-ai/calfkit-sdk. Use when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding, community health, maintainer burnout, code of conduct, metrics, legal basics, or open source project adoption.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/attribution.md`, `references/guide-map.md` and `references/persona-router.md`).

It sits in Backend & APIs, covering Open source maintenance, Event-driven systems and Policy and terms drafting. It works with OpenAI, Pydantic AI, Python and Apache Kafka. The repository describes itself as: 🐮 Build distributed, event-driven agents. The licence is Apache-2.0.

When your agent uses it

  • A user wants guidance on starting
  • Contributing to
  • Sustaining an open source project
  • Asks about contributor onboarding

Example prompts

  • “/opensource-guide-coach”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Identify the situation
  2. Choose the smallest useful guide set
  3. Convert guidance into action
  4. Link back to the official source
  5. Stay advisory by default

What it can do on your machine

Read from SKILL.md and the folder at commit d50af54. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • opensource.guide

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Opensource Guide Coach loads about 2.1k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 1,032 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from calf-ai/calfkit-sdk at commit d50af54, republished under its Apache-2.0 licence (© calf-ai). 1,032 words, ~2,084 tokens.

Download SKILL.mdSave it as .claude/skills/opensource-guide-coach/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
opensource-guide-coach
description
Use when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding, community health, maintainer burnout, code of conduct, metrics, legal basics, or open source project adoption.

Overview

Use the official Open Source Guides as a coaching framework for open source questions.

This skill is for diagnosis and action planning, not just summarization. Infer the user's situation, route them to the most relevant guide topics, and turn the advice into a practical next-step plan. Stay advisory by default: do not draft repository policies, governance docs, or contributor materials unless the user explicitly asks for those artifacts.

Source Of Truth

Treat the guides as curated community practice, not binding policy. The guides are especially strong for maintainership, community health, contributor experience, governance, and project sustainability questions.

When To Use

Use this skill when the user is trying to:

  • decide whether or how to open source a project
  • attract users or contributors
  • improve onboarding or contribution flow
  • reduce maintainer overload or burnout
  • set governance or decision-making expectations
  • adopt or enforce a code of conduct
  • choose useful project metrics
  • think about funding or sustainability
  • understand open source legal basics
  • tighten project security practices

Do not use this skill for:

  • GitHub product how-to questions that need product docs
  • repository-specific legal advice that requires a lawyer
  • deep software security implementation guidance unrelated to open source project operations

Working Style

1. Identify the situation

Infer:

  • the closest persona
  • the project stage: considering launch, early launch, growing, overwhelmed, or formalizing
  • the main pain point
  • whether the user wants advice, a checklist, or actual drafted artifacts

If details are missing, make a reasonable inference and state it briefly. Do not interrogate the user for every unknown if a safe assumption will do.

2. Choose the smallest useful guide set

Pick 1-3 guide topics.

  • Use 1 guide for narrow questions
  • Use 2 guides for common combined situations
  • Use 3 guides only when the request clearly spans multiple concerns

Do not dump the entire guide catalog on the user.

3. Convert guidance into action

Translate the guide themes into a prioritized plan that fits the user's scale.

  • Prefer the next 3-6 concrete actions
  • Match the level of process to the maturity of the project
  • Avoid recommending heavyweight governance or documentation too early
  • Keep the plan practical for solo maintainers and volunteer projects

For each recommended guide, include the official opensource.guide URL and one short sentence on why it applies.

  • Use the canonical URL from references/guide-map.md
  • Do not shorten, guess, or rewrite article slugs
  • Use the official article title exactly as written in references/guide-map.md
5. Stay advisory by default

Unless the user explicitly asks for drafting help:

  • do not write a full CONTRIBUTING.md
  • do not write a governance charter
  • do not write a code of conduct
  • do not generate a full legal policy

If the user does ask for an artifact, say which guide(s) you are basing it on and then draft only the requested artifact.

Routing Heuristics

Reach for these patterns first:

  • Launch decision, project scope, expectations, readiness: starting-a-project
  • How newcomers can help, contribution flow, first PR path: how-to-contribute
  • Adoption, awareness, project discovery: finding-users
  • Welcoming environment, community participation, contributor experience: building-community
  • Maintainer workload, process clarity, saying no, automation: best-practices
  • Shared decision-making, leadership models, formal rules: leadership-and-governance
  • Sustainability, sponsorship, funding models: getting-paid
  • Behavior expectations and enforcement norms: code-of-conduct
  • Measuring health and progress: metrics
  • Licensing and legal basics: legal
  • Burnout, boundaries, maintainership balance: maintaining-balance-for-open-source-maintainers
  • Security hygiene, project trust, dependency and vulnerability practices: security-best-practices-for-your-project

Common pairings:

  • First launch + adoption: starting-a-project + finding-users
  • Contributor growth + community experience: how-to-contribute + building-community
  • Maintainer overload + burnout: best-practices + maintaining-balance-for-open-source-maintainers
  • Governance + conduct expectations: leadership-and-governance + code-of-conduct
  • Trust + sustainability for mature projects: security-best-practices-for-your-project + best-practices or getting-paid

Canonical title reminders:

  • starting-a-project -> Starting an Open Source Project
  • code-of-conduct -> Your Code of Conduct
  • security-best-practices-for-your-project -> Security Best Practices for your Project
Show full SKILL.md (385 more words)Show less

Response Contract

Always use this structure:

Respond in plain Markdown only.

  • Do not emit pseudo-tool calls
  • Do not emit XML-like tags
  • Do not emit internal reasoning markers
  • Do not rename the section headings below
  • If you begin responding, complete all five sections
  • Never return empty wrappers, placeholders, or partial scaffolding

Situation

State the inferred persona, project stage, and main challenge in plain language. If you made an assumption, note it in one sentence.

Relevant Guides

List 1-3 guides. For each one include:

  • official title copied exactly from references/guide-map.md, including capitalization
  • why it applies here
  • official URL

Preferred format:

**Official Title**

Why it applies: ...

URL: <https://opensource.guide/...>

Provide a prioritized numbered list. Keep it concrete and proportionate to the user's scale.

Watch-outs

Call out risks, anti-patterns, or ways the user could over-process the problem.

Optional deeper reading

Include any extra guide links only if they are genuinely useful. If not, say that the guides above are enough for now.

Mini example:

Situation

You are an early-stage solo maintainer deciding whether your side project is ready for open source.

Relevant Guides

Starting an Open Source Project

Why it applies: It helps you decide whether to launch now and what basics to prepare first.

URL: https://opensource.guide/starting-a-project/

  1. Clarify the project scope and your maintenance boundaries.
  2. Add a license, README, and minimal contributor expectations.
  3. Share with a small early audience before a broader announcement.

Watch-outs

Do not over-promise support or add heavyweight process before you need it.

Optional deeper reading

If you want to think about early contributor experience, read How to Contribute to Open Source next.

Quality Bar

Your answer should:

  • sound like coaching, not policy boilerplate
  • reflect the likely persona and maturity level
  • use official guide links, not third-party summaries
  • avoid presenting legal content as legal advice
  • avoid copying long passages from the source material
  • leave the user with a clear next move

Escalation Rules

Escalate carefully when:

  • the user is asking for legal certainty rather than general guidance
  • the user needs incident response or code-level security help
  • the user wants formal governance that may be disproportionate for a tiny project
  • the user is clearly burned out and needs boundaries more than process

In those cases, keep the recommendation practical and say what this skill can and cannot confidently cover.

© calf-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/opensource-guide-coach of calf-ai/calfkit-sdk.

  • SKILL.md
  • references/attribution.md
  • references/guide-map.md
  • references/persona-router.md

Open the folder on GitHubat commit d50af54

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in calf-ai/calfkit-sdk, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Opensource Guide Coach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Opensource Guide Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Opensource Guide Coach this skillcalf-ai/calfkit-sdk1491 repos~2.1kAutomated safety check: PassApache-2.0
Using Message Queuesancoleman/ai-design-components526—~2.9kAutomated safety check: PassMIT
Streaming Dataancoleman/ai-design-components526—~2.9kAutomated safety check: PassMIT
Deepstream DevNVIDIA/skills3.5k—~3.3kAutomated safety check: PassApache-2.0
Flowfile Frame And CodegenEdwardvaneechoud/Flowfile373—~12kAutomated safety check: PassMIT
Io ConnectorsKilo-Org/kilo-marketplace190—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Using Message Queues

    ancoleman/ai-design-components

    Async communication patterns using message brokers and task queues.

    526 GitHub stars~2.9k tokensUpdated 10 mo ago
    Backend & APIsAuto-check passed
  • Streaming Data

    ancoleman/ai-design-components

    Build event streaming and real-time data pipelines with Kafka, Pulsar, Redpanda, Flink, and Spark.

    526 GitHub stars~2.9k tokensUpdated 10 mo ago
    Backend & APIsAuto-check passed
  • Deepstream Dev

    NVIDIA/skills

    Official

    NVIDIA DeepStream SDK development with Python pyservicemaker API.

    3.5k GitHub stars~3.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Flowfile Frame And Codegen

    Edwardvaneechoud/Flowfile

    Deep dive into flowfileframe — the Polars-LazyFrame-shaped Python API that builds an in-process flowfilecore FlowGraph as a side effect of every method call — covering the FlowFrame/Expr internals…

    373 GitHub stars~12k tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Io Connectors

    Kilo-Org/kilo-marketplace

    Guides development and usage of I/O connectors in Apache Beam.

    190 GitHub stars~1.3k tokensUpdated 10 days ago
    DatabasesAuto-check passed
  • Windmill Trigger Type Checklist

    windmill-labs/windmill

    Checklist of every backend, frontend, CLI and capture change needed to add a new TriggerCrud-based trigger type, such as Azure, GCP or Kafka, to Windmill.

    18k GitHub stars~4.7k tokensUpdated today
    Backend & APIsAuto-check passed

More from calf-ai/calfkit-sdk

  • Diataxis Docs Writer

    calf-ai/calfkit-sdk

    Write or improve software documentation using the Diátaxis framework — four documentation types (tutorials, how-to guides, reference, explanation), each serving a different user need.

    149 GitHub starsUsed in 1 repo~3k tokens
    Auto-check passed

Questions about Opensource Guide Coach

What does Opensource Guide Coach do?

A skill your agent uses when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding…. Opensource Guide Coach is an agent skill from calf-ai/calfkit-sdk. Use when a user wants guidance on starting, contributing to, growing, governing, funding, securing, or sustaining an open source project, or asks about contributor onboarding, community health, maintainer burnout, code of conduct, metrics, legal basics, or open source project adoption.

When should I use Opensource Guide Coach?

Opensource Guide Coach fits situations like: A user wants guidance on starting; contributing to; sustaining an open source project; asks about contributor onboarding.

How do I install Opensource Guide Coach in Claude Code?

Run `npx skills add calf-ai/calfkit-sdk --skill opensource-guide-coach -a claude-code`. Or copy the skill folder (.agents/skills/opensource-guide-coach in calf-ai/calfkit-sdk) into .claude/skills/opensource-guide-coach in your project. Claude Code loads it when a task matches its description.

How do I install Opensource Guide Coach in Codex?

Run `npx skills add calf-ai/calfkit-sdk --skill opensource-guide-coach -a codex`. Or copy the skill folder (.agents/skills/opensource-guide-coach in calf-ai/calfkit-sdk) into .agents/skills/opensource-guide-coach in your project. Codex loads it when a task matches its description.

Can I use Opensource Guide Coach in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add calf-ai/calfkit-sdk --skill opensource-guide-coach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/opensource-guide-coach, .gemini/skills/opensource-guide-coach, .github/skills/opensource-guide-coach and .opencode/skills/opensource-guide-coach in your project.

What does Opensource Guide Coach need to run?

SKILL.md names no scripts, command-line tools or credentials: Opensource Guide Coach is instructions for the agent only.

Does Opensource Guide Coach access the network?

SKILL.md names 1 domain. In commands or code: opensource.guide; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Opensource Guide Coach safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Opensource Guide Coach use?

Opensource Guide Coach is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Opensource Guide Coach use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Opensource Guide Coach?

Skills that share tags, products or a category with Opensource Guide Coach: Using Message Queues (ancoleman/ai-design-components, 526 stars), Streaming Data (ancoleman/ai-design-components, 526 stars), Deepstream Dev (NVIDIA/skills, 3.5k stars) and Flowfile Frame And Codegen (Edwardvaneechoud/Flowfile, 373 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Opensource Guide Coach?

calf-ai (a GitHub organization) maintains it in calf-ai/calfkit-sdk, which has 149 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on August 31, 2026.

Source: calf-ai/calfkit-sdk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.