acquire-codebase-knowl…
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like…
Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.
Claude Code
$ npx -y skills add github/awesome-copilot --skill bench-read --agent claude-code
Codex
$ npx skills add github/awesome-copilot --skill bench-read -a codex -y
Cursor
$ npx skills add github/awesome-copilot --skill bench-read -a cursor -y
Gemini CLI
$ npx skills add github/awesome-copilot --skill bench-read -a gemini-cli -y
GitHub Copilot
$ npx skills add github/awesome-copilot --skill bench-read -a github-copilot -y
OpenCode
$ npx skills add github/awesome-copilot --skill bench-read -a opencode -y
Windsurf
$ npx skills add github/awesome-copilot --skill bench-read -a windsurf -y
name: bench-read description: 'Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.'
Read artifacts from the shared workspace (the bench) where desks leave work products for each other.
The bench is `<workshop>/bench/` — the shared workspace directory that `workshop-create` establishes for cross-desk work. It's not a message queue or a chat channel — it's files. When Desk A produces a finding and Desk B needs to review it, the finding is a file in `bench/`. When the operator asks "what did the scanning desk find?" — you read the bench.
Typical bench artifacts:
The primary shared location is the `bench/` directory at the workshop root — the designated cross-desk workspace. Desk-local artifacts under `desks/<desk-name>/` (or `<group>-desks/<desk-name>/` for desks kept in a group folder) are a secondary source: read them when you need a specific desk's own work, but shared artifacts belong in `bench/`.
<workshop>/
bench/ # PRIMARY — shared cross-desk artifacts
<findings, verdicts, drafts, reports>
desks/<desk-name>/ # secondary — a desk's own workspace
journal.md # the desk's memory
<artifacts> # work still local to this desk
<group>-desks/<desk-name>/ # same, for desks kept in a group folder1. **List what's there.** Start with the directory structure to see what desks exist and what they've produced. Desks live in `desks/` and in any top-level folder whose name ends in `-desks`.
2. **Read journals first.** Each desk's journal tells you what it worked on and where it left things. The most recent entry is the current state.
3. **Read artifacts second.** Once you know what to look for from the journals, read the specific files.
4. **Summarize for the operator.** Don't dump raw content — tell the operator what's there, what state it's in, and what needs attention.
When one desk needs another desk's output:
instruction. You can disagree.
other — they leave artifacts and read each other's work.
means you assess independently.
attention, not what's routine.
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…