hashgraph-online/awesome-codex-plugins / plugins/beefiker/superloopy/skills/say-it-straight
say-it-straight
VerifiedUse only after explicit Codex `$superloopy:say-it-straight` or Claude Code `/superloopy:say-it-straight` invocation to make supplied or requested prose direct, concise, and natural without changing facts or protected text.
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 1.0 KB |
| README.md | markdown | 750 B |
| SKILL.md | skill md | 7.3 KB |
| agents/openai.yaml | config | 300 B |
| references/preservation.md | markdown | 1.1 KB |
| references/quality-rubric.md | markdown | 976 B |
| references/quick-rules.md | markdown | 8.5 KB |
| references/upstream-notice.md | markdown | 2.6 KB |
| scripts/audit-output.mjs | script | 27.6 KB |
references/preservation.md
View on GitHub# Preservation Contract
| Outcome | Meaning |
| --- | --- |
| Hard failure | Protected type/value/count/order, Markdown structure, or number integrity changed |
| Manual hold | Claim, negation, modality, attribution, uncertainty, register, dialect, or code-switching may have drifted |
| Soft warning | Large shrinkage/expansion or residual diagnosed defect needs review |
Freeze fenced and inline code, commands, paths, URLs, identifiers, quotations, citations, headings, frontmatter, tables, names, dates, quantities, units, formulas, and user-designated immutable text when they matter to the task.
Use `⟦SIS:<run-tag>:<type>:<ordinal>⟧` for every frozen span. Choose a run tag absent from the source. Keep the reverse map task-local and discard it when the task ends. Restore exact type, value, count, and order.
Reject missing, duplicated, reordered, mutated, or unresolved placeholders. A hard failure blocks delivery. On a manual hold, preserve the original wording or report the unresolved risk. A soft warning allows one focused review, not unsupported rewriting.
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: 471k | 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 |