Skip to content

finding: no shipped example includes a skill, so SKILL.md is learned from an error #242

Description

@sagi5060

Problem

No shipped example includes a skill, so the SKILL.md contract is learned from an error message. A
clean-room reviewer's first failure was:

ConfigError: .../SKILL.md: missing a 'description' in its frontmatter.

The format is documented — concepts/skills.mdx:19-33 has a complete example — but the reviewer was
working from examples/, found no skill there, wrote one from memory of the directory listing in the
README, and failed. examples/ currently ships chat-agent-with-a-tool, workflow-with-an-approval
and ask-agentdeck; the first two have no skills/ directory at all.

Skills are one of the four things Deck.from_project() discovers, and the only one with no runnable
example.

Proposed shape

Add a skill to examples/chat-agent-with-a-tool rather than creating a fourth example — the agent
there already has a reason to consult one, and one directory is cheaper than a new example to keep
green:

examples/chat-agent-with-a-tool/.agentdeck/
├── agents/<bundle>/agent.py
└── skills/<name>/SKILL.md          # frontmatter + prose the agent follows

The SKILL.md should demonstrate the contract the docs describe — name matching the directory,
description as the disclosure text, prose instructions — and the README should show the run where
the skill's guidance visibly changes the answer, so the example proves progressive disclosure rather
than merely parsing.

Out of scope: a skill with scripts/, and anything touching #20 (consuming skills via the SKILL.md
protocol rather than as pre-wrapped tools) — this is one static skill exercising today's behavior.

Notes

Done when

  • examples/chat-agent-with-a-tool ships one skill under .agentdeck/skills/
  • Its README shows the skill's guidance changing the agent's answer
  • The example still runs with only OPENAI_API_KEY set
  • Deck.from_project() in that example discovers the skill without extra arguments

New to AgentDeck?

AgentDeck SDK is a production runtime around agents you already have — it supplies sessions,
streaming, one event log per run, human approval and run control, and leaves execution to the
OpenAI Agents SDK and LangGraph.

pip install agentdeck-sdk

Before working on this issue, run this example as a user wouldpython run.py in
examples/chat-agent-with-a-tool. Fifteen minutes there makes this issue read very differently.

Setup, the make check gate, the branch model (dev) and the CHANGELOG rule are in
CONTRIBUTING.md. Comment here to claim the issue — nobody
else gets assigned while you are working on it, and questions are welcome in
Discussions.

Metadata

Metadata

Assignees

No one assigned

    Labels

    findingAn observation that needs attention and a deeper look — not yet a bug, not yet a plangood first issueGood for newcomers

    Type

    No type

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions