skills/translation-reframing-audience-shift/SKILL.md
Adapts content for different audiences while preserving core accuracy, changing tone, depth, emphasis, and framing to match audience expertise and goals. Use when technical content needs business framing, strategic vision needs tactical translation, expert knowledge needs simplification, formal content needs casual tone, long-form needs summarization, internal content needs external framing, or cross-cultural adaptation is needed. Use when user mentions "explain to", "reframe for", "translate for [audience]", "adapt for [executives/engineers/customers]", or "same content, different audience".
npx skillsauth add lyndonkl/claude translation-reframing-audience-shiftInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Copy this checklist and track your progress:
Translation & Reframing Progress:
- [ ] Step 1: Analyze source and target audiences
- [ ] Step 2: Identify translation type and constraints
- [ ] Step 3: Apply translation strategy
- [ ] Step 4: Validate fidelity and appropriateness
- [ ] Step 5: Refine and deliver
Step 1: Analyze source and target audiences
Characterize both audiences using Audience Analysis framework (expertise, goals, context, constraints). Identify gap between source and target.
Step 2: Identify translation type and constraints
Classify as: technical↔business, strategic↔tactical, expert↔novice, formal↔informal, long↔short, internal↔external, or cross-cultural. See Common Translation Types for patterns.
Step 3: Apply translation strategy
For simple cases → Use resources/template.md for structured translation. For complex cases (multiple audiences, high stakes, nuanced reframing) → Study resources/methodology.md for advanced techniques.
Step 4: Validate fidelity and appropriateness
Self-assess using resources/evaluators/rubric_translation_reframing_audience_shift.json. Check: semantic accuracy preserved? tone appropriate? emphasis aligned with audience priorities? See Validation section.
Step 5: Refine and deliver
Create translation-reframing-audience-shift.md with source, target audience, translated content, and translation rationale. See Delivery Format.
Before translating, characterize source and target:
1. Expertise Level
2. Primary Goals
3. Context & Constraints
4. Cultural/Demographic
Mapping exercise: Source audience is [expertise/goals/context] → Target audience is [expertise/goals/context] → Gap requires [translation strategy].
Technical → Business:
Business → Technical:
Strategic → Tactical:
Tactical → Strategic:
Expert → Novice:
Novice → Expert:
Formal → Informal:
Informal → Formal:
Long → Summary:
Summary → Long-form:
Before finalizing, check:
Semantic Fidelity (highest priority):
Audience Appropriateness:
Emphasis Alignment:
Medium & Format:
Cultural/Demographic:
Minimum Standard: Use rubric (resources/evaluators/rubric_translation_reframing_audience_shift.json). Average score ≥ 3.5/5 before delivering.
Create translation-reframing-audience-shift.md with:
1. Source Analysis
2. Target Analysis
3. Translated Content
4. Translation Rationale
5. Validation Notes
"So What?" Test (Technical → Business): Every technical detail answers "so what?" - "Migrated to Kubernetes" → "Auto-scale during traffic spikes, 30% cost reduction" | "OAuth 2.0" → "Enterprise SSO, removes adoption barrier"
"How?" Test (Strategic → Tactical): Every goal answers "how?" - "Improve satisfaction" → "Response <2hr, add help center, NPS survey" | "AI-first company" → "Train PMs (Q1), hire 3 ML engineers (Q2), pilot feature (Q3)"
Analogy Bridge (Expert → Novice): Familiar → Unfamiliar - "Git branching" = essay draft versions | "Microservices" = food trucks not one restaurant | "API rate limiting" = nightclub capacity
Inverted Pyramid (Long → Summary): Most important first - Lede (1-2 sentences) → Key details (2-3 bullets) → Supporting (optional depth)
Code-Switching (Cross-Cultural): Replace cultural references - "Home run" (US) → "Big success" (neutral) | "Fire hose" idiom → "Overwhelming info" (literal) | MM/DD/YYYY → YYYY-MM-DD (ISO)
Resources:
Key Principles:
Red Flags:
testing
--- name: advisory-edit description: A strict advisory-only editing discipline for a writer who dictates ("speaks out") essays and wants help WITHOUT having their voice changed. The editor directs structure, flags grammar, and suggests strategic language — but never modifies the writer's text unless the writer explicitly says "apply" / "make that change" / "rewrite this." Produces a line-referenced, suggestion-only critique where every item is marked the writer's call. Four passes: structural, l
testing
Provides the house style for analyst-grade strategist writing — third-person register with sparing first-person, no em dashes, no "not X, not Y, not Z" negation cascades, numbered footnote citations rather than inline source parentheticals, specific opinion-signaling phrases, and topic-forward paragraph structure modeled on voice patterns observed in Damodaran's Musings on Markets and Thompson's Stratechery. Use when consolidating working notes into a finished long-form strategist or analyst report that must read as written by a senior human analyst rather than an AI assistant.
testing
Renders a markdown report to a PDF using pandoc with xelatex (11pt serif body, 1-inch margins, numbered footnotes, formal heading hierarchy). Requires a one-time install of pandoc and a LaTeX engine on the user's machine — basictex on macOS or texlive-xetex on Linux. Does not attempt automatic install. Fails loudly with the exact install commands if pandoc or xelatex is missing on the user's PATH. Use when producing a finished strategist or analyst report PDF from a polished markdown source.
testing
Produces step-by-step computational walkthroughs of vector and matrix operations as a sequence of numbered "frames", showing the explicit state at each step. The text-equivalent of a 3Blue1Brown animation — each frame shows what changed and why, so the learner can re-trace the operation by hand. Use when the learner needs to *see* a computation unfold (eigenvalue computation, attention with 3 tokens, gradient descent step, SVD on a 2×2, layer norm on a 3-vector, softmax of a small input), when an explanation has been given but the learner needs to ground it in a worked example, or when introducing an operation that's intimidating in symbol form but trivial in pencil-and-paper form.