fixtures/copilot-validation/.github/skills/echo-test/SKILL.md
Validates skill invocation, parameter passing, and shell execution on Copilot CLI
npx skillsauth add rp1-run/rp1 echo-testInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a validation skill for testing Copilot CLI harness primitives. Execute each step below and report results.
This skill accepts two parameters from the user's invocation text:
Parse these from the user's slash command invocation. For example:
/echo-test "hello world" -> MESSAGE="hello world", FORMAT="plain"/echo-test "hello world" json -> MESSAGE="hello world", FORMAT="json"If MESSAGE is missing, respond with: [FIXTURE] Error: MESSAGE parameter is required. Usage: /echo-test <message> [format]
Report the parsed parameters:
[FIXTURE] Parameters received:
MESSAGE: <parsed message>
FORMAT: <parsed format>
Run the following shell command to verify Bash tool access:
echo "[FIXTURE] Shell execution working -- $(date -u +%Y-%m-%dT%H:%M:%SZ)"
Report the output.
.rp1/context/index.md and confirm it contains "Copilot Validation Fixture".rp1/work/echo-test-output.md:# Echo Test Output
- Message: <MESSAGE>
- Format: <FORMAT>
- Timestamp: <current UTC time>
- Status: PASS
.md files in .rp1/context/.rp1/work/echo-test-output.md with - Verified: trueReport each operation as PASS or FAIL.
Run the following command to verify rp1 CLI integration:
rp1 agent-tools rp1-root-dir
Report whether the command executes successfully and returns valid JSON.
Output a summary in the requested FORMAT:
Plain format:
[FIXTURE] Echo Test Complete
Parameters: PASS/FAIL
Shell: PASS/FAIL
File Read: PASS/FAIL
File Write: PASS/FAIL
File Search: PASS/FAIL
File Edit: PASS/FAIL
Agent Tools: PASS/FAIL
JSON format:
{
"fixture": "echo-test",
"results": {
"parameters": "PASS|FAIL",
"shell": "PASS|FAIL",
"file_read": "PASS|FAIL",
"file_write": "PASS|FAIL",
"file_search": "PASS|FAIL",
"file_edit": "PASS|FAIL",
"agent_tools": "PASS|FAIL"
}
}
tools
Plan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
documentation
Ask about rp1 capabilities, discover skills, and get workflow guidance.
tools
Generate an evidence-grounded markdown walkthrough for a pull request.
development
Run a bounded, evidence-driven two-agent debate into a separate rp1 debate artifact with backend locks only.