reverse-engineering-texts
Reverse-engineer texts into a reusable structural blueprint (reverse outlining, argument mining, copy teardown). Use when the user asks to analyze a text’s thesis, hook, framework (AIDA/PAS/PASTOR/BAB), argument map, rhetoric (Ethos/Pathos/Logos), or when they want to convert “text → structure/blueprint” to reuse patterns in writing, specs, prompts, or marketing.
npx skills add majiayu000/claude-skill-registry --skill reverse-engineering-texts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Reverse-Engineering Texts ## Goal Turn a finished text into a **TeardownBlueprint** (a “drawing”) that is reusable: structure, argument moves, and rhetorical patterning. ## Core disciplines (FPF-aligned) - **Strict distinction**: TextArtifact (the text) ≠ Blueprint (your description) ≠ Output (new draft/prompt). - **Evidence first**: Every non-trivial claim in the blueprint must include a short **quote** from the text (an “evidence anchor”). - **Parsimony**: Prefer the simplest structure/framework that explains the whole text. - **Uncertainty**: Mark low-confidence inferences explicitly. ## What “SOTA” means here This skill is not just “label AIDA and call it done”. State-of-the-art reverse-engineering requires: - **Paradigm transparency**: explicitly declare the interpretive lens used (and what would count as an “error” vs a paradigm clash). - **Meaning-in-interaction**: meaning is extracted in a dynamic local context, not “derived from rules given from above”. - **Ambiguity handling**: do not force-collapse; maintain multiple plausible interpretations when needed. - **Order effects awareness**: sometimes A→B ≠ B→A; record when the analysis is non-commutative. ## Method layering
- Goal
- Core disciplines (FPF-aligned)
- What “SOTA” means here
- Method layering
- Quick workflow (text → blueprint)
- 0) Context-first (always)
- 1) Core teardown (default)
- 2) Advanced (SOTA extensions)
- Output contract
- Mandatory execution order (hard requirement)
- Template availability check (hard requirement)
- Deliverables
- Minimum QA checklist
- SOTA QA checklist (recommended)
What does the reverse-engineering-texts skill do?
Reverse-engineer texts into a reusable structural blueprint (reverse outlining, argument mining, copy teardown). Use when the user asks to analyze a text’s thesis, hook, framework (AIDA/PAS/PASTOR/BAB), argument map, rhetoric (Ethos/Pathos/Logos), or when they want to convert “text → structure/blueprint” to reuse patterns in writing, specs, prompts, or marketing.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill reverse-engineering-texts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.