acquire-codebase-knowl…
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like…
Create and open a new desk in the workshop. Sets up the folder structure, initial journal, and desk identity so the next session that sits down finds the trail.
Claude Code
$ npx -y skills add github/awesome-copilot --skill desk-open --agent claude-code
Codex
$ npx skills add github/awesome-copilot --skill desk-open -a codex -y
Cursor
$ npx skills add github/awesome-copilot --skill desk-open -a cursor -y
Gemini CLI
$ npx skills add github/awesome-copilot --skill desk-open -a gemini-cli -y
GitHub Copilot
$ npx skills add github/awesome-copilot --skill desk-open -a github-copilot -y
OpenCode
$ npx skills add github/awesome-copilot --skill desk-open -a opencode -y
Windsurf
$ npx skills add github/awesome-copilot --skill desk-open -a windsurf -y
name: desk-open description: 'Create and open a new desk in the workshop. Sets up the folder structure, initial journal, and desk identity so the next session that sits down finds the trail.'
Create a new desk in the workshop with the standard structure.
Given a workshop directory and a desk name, create:
desks/<desk-name>/ journal.md # persistent memory — read at start, written at end .signals/ # structured signal output (JSON) — dashboard reads this
`desks/` is the default home. A desk can instead live in a group folder: any top-level folder whose name ends in `-desks` (for example `team-desks/<desk-name>/`). Use one only when the operator asks for that group, create the group folder if it doesn't exist, and read `desks/` in the steps below as that group folder.
1. **Choose a name.** Short, descriptive, kebab-case. The name is how the operator and other desks refer to this desk. Examples: `security-scan`, `api-review`, `ops`, `cloud-workshop`
2. **Check if it already exists.** If `desks/<desk-name>/` already has a `journal.md`, the desk is live — **do not overwrite it.** Instead, resume it: read the journal and continue from where it left off. If the operator explicitly wants a fresh start, they must rename or archive the existing desk first.
3. **Create the structure.** Make the directory, initial journal, and signals folder:
desks/<desk-name>/journal.md desks/<desk-name>/.signals/
4. **Write the first journal entry.** The journal starts with:
5. **Announce it.** Tell the operator what was created and what the desk's focus is.
This skill initializes storage — it does not launch a session. A desk becomes active when a Copilot session references its directory. The session workflow:
1. The operator (or TA) starts a session and says "sit at the `<desk-name>` desk" 2. The session reads the desk's `journal.md` to load priors. To find the desk, look in `desks/<desk-name>/`, then in each `<group>-desks/<desk-name>/`; if more than one has that name, ask which one (refer to it as `<group>-desks/<desk-name>`) 3. Work happens — the session uses `signal-write` to emit signals and `desk-journal` to persist state at the end 4. The next session repeats from step 2
The desk identity comes from which journal is read, not from a persistent process. Desks are long-running in *state* (the journal carries forward), not in *runtime* (each session is independent).
# <Desk Name> — Journal ## <date> — Desk opened - **Purpose:** <what this desk focuses on> - **Scope:** <repos, areas, or work this desk covers> - **Next step:** <what the first session should do>
disagree with other desks.
blind. Write enough that someone starting from zero finds the way.
Each desk's value comes from its specific frame — dilute the frame and you lose the value.
A community-created collection of custom agents, instructions, skills, hooks, workflows, and plugins to supercharge your GitHub Copilot experience.
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like…
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps…
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default,…
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks,…
Use this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like…
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…