Wendy Certificates logo

Wendy Certificates

Organization
wendylabsinc
wendy-certificates

Expert guidance on requesting, renewing, and revoking certificates in the Wendy ecosystem via pki-core. Use when developers mention: (1) requesting or issuing a certificate, (2) operator or service identity certs, (3) entitlement-bearing certs or field/USB access, (4) CSR, proof-of-possession, or cnf.jkt binding, (5) cert renewal or revocation, (6) service accounts, machine users, or CI credentials, (7) ML-DSA or post-quantum signing, (8) SPIFFE URIs or tenant_uuid.

Overview

Publisherwendylabsinc
Repositoryclaude-skills
Skill namewendy-certificates
Stars
62
Forks
5
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by wendylabsinc on GitHub. Read the source before you install it.

Installation

Install the Wendy Certificates AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/wendylabsinc/claude-skills/tree/main/wendy-certificates
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/wendylabsinc/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/wendy-certificates .claude/skills/wendy-certificates
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wendy Certificates in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wendy Certificates on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wendy Certificates is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Wendy Certificates

How principals in the Wendy ecosystem get, renew, and lose certificates. pki-core is the sole issuer — every cert it mints binds a client-held key, never a bare identity claim. Which cert type a flow needs depends on where authorization will be enforced: the cloud-facing cert stays identity-only because cloud authorizes live against its own mutable state, while any cert used where there is no live authority to consult offline — an operator's cert for direct field/USB device access — must carry entitlements; device certs are identity-only, and entitlements ride on operator certs only (§4.2). Full flow-level detail — including how the two credential shapes interact with the rest of the AAA contract — lives in the wendy-aaa-interop skill; this skill is the certificate-request/renewal/revocation slice of it.

Decision Table: Which Cert / Which Path

NeedPath
Identity-only operator cert (steady-state login/session)Direct pki-core endpoint — no cloud in this path
Entitlement-bearing cert (direct field/USB device access)Operator-signed request + CSR → cloud attaches a grant → relayed to pki-core
Device cert (enrollment, first touch, recovery)Enrollment flows — see the wendy-device-enrollment skill
Service account / machine userIdentical operator flow, through a different wendy-auth front door (§5.2, D17)

(§5.2, D17)

Key Rules (non-negotiable)

  1. Client-generated keys only. Private keys are always generated on the client; pki-core's engine-side GenerateKeyAndIssueCert is prohibited for principal certs. The sole exception is the server-keygen-over-USB fallback, for a device that genuinely cannot generate its own key, with in-memory zeroization after use (§5.2).
  2. extractable:false is the floor. The Wendy frontend holds the signing key as a WebCrypto key with extractable:false explicitly set (§4.1/§7) — not a platform default; high-assurance operators use a FIDO2/passkey hardware authenticator instead, so signing happens inside the device and malware can only use the key while resident, never exfiltrate it (§7).
  3. No pure bearer PATs. Only sender-constrained tokens exist in this system — a copy-pasteable secret is rejected outright, for humans and service accounts alike (D17).
  4. Request-signing is JWS/COSE with ML-DSA, not RFC 9421. Proof-of-possession is a signature over a canonical request descriptor, algorithm ML-DSA per RFC 9964 (default leaf ML-DSA-65), enveloped as JWS (HTTP/cloud) or COSE_Sign1 (edge/gRPC) — not RFC 9421 HTTP Message Signatures, whose registry has no ML-DSA algorithm (§4.1).

Service Accounts & CI

A service account is a normal user behind a different wendy-auth front door, flagged and privileged by cloud exactly like a human — same §5.2 cert flow (issuance + renewal + in-flight status check), no weaker path. It gets its own service SPIFFE kind (spiffe://wendy.sh/tenant/<uuid>/service/<name>) so audit and offline enforcement can tell human and machine principals apart.

CI never holds a long-lived secret: wendy-cloud-action federates the job's IdP OIDC token into wendy-auth, which mints a wendy-auth token bound to an ephemeral in-job key; the job then calls the same identity-cert endpoint for a short-lived cert. No PAT ever exists at any point in this flow (D17).

Self-Hosted Rule (mandatory)

The wendy stack (wendyos / wendy-agent) must ALWAYS be able to run without the SaaS stack. Before shipping any interop change, consult the wendy-self-hosted skill: keep the self-hosted path intact, or create it where it doesn't exist yet. A SaaS-only feature is an incomplete feature.

Source of Truth

This skill distills the AAA Contract v0.21 (Approved 2026-08-29). The living contract lives in Linear: AAA Contract — Authentication, Authorization, Accounting. It is versioned and evolving: check it for flow-level detail, and if it disagrees with this skill, the contract wins — then update this skill.

Related Skills

  • wendy-aaa-interop — the full contract this skill distills a slice of
  • wendy-device-enrollment — device certs: first touch, tiers, post-expiry recovery
  • wendy-security-baselines — the invariants any interop change must respect
  • wendy-self-hosted — the standing dual-path rule

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wendy Certificates AI skill do?

Expert guidance on requesting, renewing, and revoking certificates in the Wendy ecosystem via pki-core. Use when developers mention: (1) requesting or issuing a certificate, (2) operator or service identity certs, (3) entitlement-bearing certs or field/USB access, (4) CSR, proof-of-possession, or cnf.jkt binding, (5) cert renewal or revocation, (6) service accounts, machine users, or CI credentials, (7) ML-DSA or post-quantum signing, (8) SPIFFE URIs or tenant_uuid.

Why use Wendy Certificates on TypingMind?

Because you install it once and use it with any model. Wendy Certificates is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wendy Certificates in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wendylabsinc/claude-skills/tree/main/wendy-certificates. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wendy Certificates?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wendy Certificates?

As many as you like. As long as a model supports skills, you can use Wendy Certificates with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wendy Certificates AI skill free?

It is published on GitHub by wendylabsinc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇