principle-prove-it-works
Use at the end of every task, before you say it succeeded. Check the actual output yourself, for example by exercising the feature, reading back what got stored, or opening the diff. A proxy signal, a subagent's self-report, or a successful compile does not count.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- principle-prove-it-works
- description
- Use at the end of every task, before you say it succeeded. Check the actual output yourself, for example by exercising the feature, reading back what got stored, or opening the diff. A proxy signal, a subagent's self-report, or a successful compile does not count.
- disable-model-invocation
- true
03 SKILL.md 正文
Prove it works
Look at the real artifact before calling a task finished: exercise the feature, read the value that was stored, examine the diff. Proxies, self-reports, and a successful compile do not count as evidence.
When it applies
The end of every task, before you report success.
What to do
- Expect indirect checks to tempt you. File timestamps, a subagent's summary, and a cached screenshot feel cheaper than looking, but acting on a wrong inference costs more.
- Check whether a process is alive by querying the process, not by reading a status file it last wrote.
- Read the value at its source rather than a cached copy or something computed from it. After changing a firewall rule, send a request that should be blocked and confirm it is blocked. Do not stop at "the config file contains the rule."
- When a verification fails, suspect the observation method first.
- Prefer a deterministic script that reruns the comparison over a one-time visual check. Run that script and keep what it prints as an artifact the reviewer can execute again (principle-build-the-lever).
- Show that artifact to the user in the reply. Reserve committing it for big or complicated work that needs an audit trail, such as a big port or migration, using the show-me-your-work skill.
A delegate reporting "all tests pass" may have run a subset. Rerun the command or read its captured output before repeating the claim.
The failure it prevents
False "done" claims, trust in subagent summaries, and the belief that a green build means working software.
Done when
Evidence from the real artifact accompanies the claim of completion.
Compare principle-explain-the-number: that one asks whether a measurement means what it claims, and this one asks whether the output exists and behaves correctly.
Related: principle-build-the-lever, principle-sequence-verifiable-units, principle-explain-the-number, create-verification-skill.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.