shakedown-canary
Run the shakedown canary check. Use whenever someone asks to run the canary check, verify the harness, or confirm shakedown is wired up correctly.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-21
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- shakedown-canary
- description
- Run the shakedown canary check. Use whenever someone asks to run the canary check, verify the harness, or confirm shakedown is wired up correctly.
02 资源文件 1
- 其他cases.toml200 B
03 SKILL.md 正文
shakedown-canary
This skill exists so a test can confirm three things about a harness: that it discovered the skill, that it surfaced it to the model, and that it can carry a conversation across turns.
First, ask
Ask the user what the output file should be named, and stop your turn so they can reply. Do not guess a name and do not proceed without one.
Then, once they have answered
Run exactly this shell command:
echo shakedown-ok
Then write the filename they gave you, in the current directory,
containing the single word shakedown-ok.
Do not explain or summarize. The shell call is the evidence.
04 同仓库更多 Skills
fake-skill
A skill used only by shakedown's own offline tests.
create-cases
Author a shakedown cases file (`shakedowns/<slug>.cases.toml`) for an existing agent skill: read the skill, turn what it promises into cases, supply fixtures for the commands it must not really run, and check the result with `shakedown case validate`. Use this whenever someone wants to measure, smoke-test, or add conformance cases for a skill, asks "how do I test this skill", points at a SKILL.md and wants cases written, or is editing a `.cases.toml`. Use it even when they only name the skill ("write cases for connect-agent-to-hub") without mentioning shakedown or TOML.
analyze-results
Read a shakedown report (`shakedown-report.json`) and say which file to open: the measured skill's own `SKILL.md`, the `shakedowns/<slug>.cases.toml` holding its cases, the harness block in `shakedown.toml`, or a flag on the run itself. Use this whenever someone has run `shakedown case run` and wants to know what a number means or what to do about it, pastes a report or the PR comment rendered from one, asks why `skill_fired`, `tool_used`, `artifact_created` or `inputs_resolved` came out low, asks whether a rate is worth acting on, or says a conformance run failed and they cannot tell whose fault it is. Use it even when they only quote the percentage ("my skill scores 60% on inputs_resolved, now what") without naming shakedown or the report file.
add-harness
Add a new agent harness (opencode, Gemini CLI, Codex, Amp, a local Ollama-backed runner, or any CLI that loads skills) to a shakedown config so its skill conformance can be measured, and diagnose a harness that `shakedown doctor` reports as not qualifying. Use this whenever someone wants shakedown to run against a harness it does not yet support, asks why a harness fails doctor, asks how to point an existing harness at a different model or provider, or is editing the `[harness.*]` block of a shakedown.toml. Use it even when they only name the tool ("can this test opencode?") without mentioning config or TOML.
create-cases
Author a shakedown cases file (`shakedowns/<slug>.cases.toml`) for an existing agent skill: read the skill, turn what it promises into cases, supply fixtures for the commands it must not really run, and check the result with `shakedown case validate`. Use this whenever someone wants to measure, smoke-test, or add conformance cases for a skill, asks "how do I test this skill", points at a SKILL.md and wants cases written, or is editing a `.cases.toml`. Use it even when they only name the skill ("write cases for connect-agent-to-hub") without mentioning shakedown or TOML.
analyze-results
Read a shakedown report (`shakedown-report.json`) and say which file to open: the measured skill's own `SKILL.md`, the `shakedowns/<slug>.cases.toml` holding its cases, the harness block in `shakedown.toml`, or a flag on the run itself. Use this whenever someone has run `shakedown case run` and wants to know what a number means or what to do about it, pastes a report or the PR comment rendered from one, asks why `skill_fired`, `tool_used`, `artifact_created` or `inputs_resolved` came out low, asks whether a rate is worth acting on, or says a conformance run failed and they cannot tell whose fault it is. Use it even when they only quote the percentage ("my skill scores 60% on inputs_resolved, now what") without naming shakedown or the report file.