principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 23
- Forks
- 4
01 前言 Front Matter
- name
- principle-prove-it-works
- description
- Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
- disable-model-invocation
- true
03 SKILL.md 正文
Prove It Works
In DeepSeek Harness, read the DSH adapter once per session before you follow this skill. It maps the Cursor names in pstack skills to DeepSeek Harness.
Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."
Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.
Check the real thing, not a proxy:
- Check process liveness directly, not indirectly through derived state
- Read the actual value, not a cached or derived representation
- When verification fails, suspect the observation method before suspecting the system
Script the check when you can
The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word.
Keep the artifact visible for the human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the show-me-your-work skill).
04 同仓库更多 Skills
setup-project-docs
Bootstrap architecture, glossary, decision-record conventions, and root agent-doc pointers; rerun to fill approved gaps.
docs-drift
Audit living project documentation for drift and redundancy; repair approved findings.
decision-write
Write, update, land, or supersede decision records. Use for resolved alternatives, missing rationale, reversed decisions, or record-file changes. Land finds and verifies the implementation; Review-only updates keep the current status.
decision-audit
Read-only audit of decision records for a PR, local changes, or the whole repository. Report routing, status, scope, anchor, supersession, and overdue-review findings with command evidence.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
retro
Conduct a retrospective on a coding session.