kharmanskyi/open-steps / skills/os-say-simple
os-say-simple
VerifiedALWAYS invoke this skill when the user asks for simpler or shorter about something said or written - "say it simply", "what does this mean", "I don't understand your answer", "too long", "wait, what?", "bro" - in any language, about any text: your own answer, a report, a review comment, an error. "I don't understand what to DO" is os-step-by-step; this skill restates text. It restates for a reader who does not read code: leads with the point, keeps every number, warning and caveat - no facts added, no bad news dropped. A number returns exactly that many points, most important first.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.1 KB |
| references/01-wall-of-text.md | markdown | 1.7 KB |
references/01-wall-of-text.md
View on GitHub# Example 1 - a status update nobody outside engineering can use
Source: a real end-of-day message, anonymised. Two calls against the same
text.
## The text
> Rebased onto main and force-pushed after the upstream squash-merge
> invalidated the branch ancestry. CI green except the flaky e2e lane (known,
> tracked). Bumped starlette to close the transitive CVE; lockfile
> regenerated. The reconcile worker now short-circuits on idempotency-key
> collision instead of raising, so Monday's retry storm can't recur. Left the
> feature flag off pending the grants ceremony.
## `os-say-simple`
> Monday's failure can't happen again: when the same request is submitted
> twice, the system now keeps one copy instead of crashing. A security hole
> in one of our libraries is closed. All automatic checks pass except one
> that is known to be unreliable. None of this is live yet - it waits behind
> a switch, until the database-permissions step that only you can run.
## `os-say-simple 3`
> 1. Nothing is live yet - it all waits on the permissions step that is yours.
> 2. Monday's double-submission failure is fixed for good.
> 3. A known security hole in one library is closed.
## What the rewrites did
| Move | Where |
|---|---|
| Branch mechanics dropped entirely | rebase and force-push change nothing for this reader |
| The caveat survived every version | "not live yet" is bad news, and in the 3-point version it ranks first |
| The not-quite-green status survived | "except one known unreliable check" - shortening may not turn amber into green |
| Terms became what the reader would see | "retry storm" → "crashing on a doubled submission" |
| The claims stayed the source's | nothing here was verified by the rewrite - as true as the message, no truer (rule 3) |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |