Skip to content

meiluosi/rewrite-fidelity-skill

rewrite-fidelity

Verified

Use after any rewrite, simplification, or plain-language pass — English or Chinese — to check that the new text still says what the original said: same numbers, same code and identifiers, same conditions and exceptions, same requirement strength (MUST/SHOULD/MAY, 必须/建议/可以), same hedges (may have / 可能), same negations and scope, same threshold direction (at least vs at most, 以上 vs 以下), same comparison direction (A beats B vs B beats A), no stronger claim (suggests vs proves, 可能 vs 一定). Pairs with asd-ste100, zh-disambiguate, jianming-zhongwen and any other rewrite skill. Triggers: check the rewrite, did the rewrite change the meaning, verify nothing was lost, fidelity check, 改写有没有改意思, 核对改写, 保真检查, 对比原文和改写稿. Not a style checker: it never judges whether the rewrite reads better.

examples/README.md

View on GitHub
# Examples

Each folder holds an `original.txt`, a `rewrite.txt`, and the exit code that `scripts/fidelity.py` must return (`expected-exit`). `run-examples.sh` checks all of them.

| Folder | Rewrite quality | Script result | What it shows |
|---|---|---|---|
| `en-good-split` | good | 0 errors, 2 warnings | Splitting one sentence repeats "if" and adds "not". The count goes up, so the script warns but does not fail. |
| `en-hedge-promoted` | bad | 3 errors | "may have occurred" → "failed", "could be caused by" → "causes", "at most 3 times" → "3 times", "before" dropped. |
| `zh-good-split` | good | 0 errors, 1 warning | Restructured into two sentences. `除非 … 否则` adds one condition marker. |
| `zh-meaning-drift` | bad | 4 errors | 可能、大约、不建议、除非、否则 all dropped. 不建议 became 不要 (advice became a ban). |
| `zh-detached-condition` | **bad** | **0 errors** | `除非所有迁移都已经手动完成。` became its own sentence. Every marker survived, but the condition no longer attaches to the instruction. Only the Pass 2 claim check in SKILL.md finds this. |

The last example is the reason SKILL.md requires both passes.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall