skills/communication-storytelling/SKILL.md
Transforms analysis, data, and complex information into clear, persuasive narratives tailored to specific audiences — executives, customers, investors, or non-technical stakeholders. Provides story structures (Hero's Journey, Problem-Solution-Benefit, Situation-Complication-Resolution) and audience adaptation techniques. Use when presenting findings, explaining technical concepts to non-technical audiences, writing announcements, or when user mentions "write this for", "explain to", "present findings", "make this compelling", or "audience is".
npx skillsauth add lyndonkl/claude communication-storytellingInstall 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.
This skill crafts compelling stories using a structured framework: (1) Headline — single clear statement capturing the essence, (2) Key Points — 3-5 supporting ideas with logical flow, (3) Proof — evidence, data, examples that substantiate, (4) Call-to-Action — what audience should think, feel, or do.
Quick example:
Bad (data dump): "Our Q2 revenue was $2.3M, up from $1.8M in Q1. Customer count went from 450 to 520. Churn decreased from 5% to 3.2%. NPS improved from 42 to 58. We launched 3 new features..."
Good (storytelling): "We've reached product-market fit. Three signals prove it: (1) Revenue grew 28% while sales capacity stayed flat—customers are pulling product from us, not the other way around. (2) Churn dropped 36% as we focused on power users, with our top segment now at 1% monthly churn. (3) NPS jumped 16 points to 58, with customers specifically praising the three features we bet on. Recommendation: Double down on power user segment with premium tier."
Copy this checklist and track your progress:
Communication Storytelling Progress:
- [ ] Step 1: Gather inputs and clarify audience
- [ ] Step 2: Choose appropriate narrative structure
- [ ] Step 3: Craft the narrative
- [ ] Step 4: Validate quality and clarity
- [ ] Step 5: Deliver and adapt
Step 1: Gather inputs and clarify audience
Ask user for the message (analysis, data, information to communicate), audience (who will receive this), purpose (inform, persuade, inspire, build trust), context (situation, stakes, constraints), and tone (formal, casual, urgent, celebratory). Understanding audience deeply is critical—their expertise level, concerns, decision authority, and time constraints shape everything. See resources/template.md for input questions.
Step 2: Choose appropriate narrative structure
For standard communications (announcements, updates, presentations) → Use resources/template.md quick template. For complex multi-stakeholder communications requiring different versions → Study resources/methodology.md for audience segmentation and narrative adaptation techniques. To see what good looks like → Review resources/examples/.
Step 3: Craft the narrative
Create communication-storytelling.md with: (1) Compelling headline that captures essence in one sentence, (2) 3-5 key points arranged in logical flow (chronological, problem-solution, importance-ranked), (3) Concrete proof for each point (data, examples, quotes, stories), (4) Clear call-to-action stating what audience should do next. Use storytelling techniques: specificity over generality, show don't tell, human stories over abstract concepts, tension/resolution arcs. See Story Structure for narrative patterns.
Step 4: Validate quality and clarity
Self-assess using resources/evaluators/rubric_communication_storytelling.json. Check: headline is clear and compelling, key points are distinct and well-supported, proof is concrete and relevant, flow is logical, tone matches audience, jargon is appropriate for expertise level, call-to-action is clear and achievable, length matches time constraints. Read aloud to test clarity. Test with "so what?" question—does each point answer why audience should care? Minimum standard: Average score ≥ 3.5 before delivering.
Step 5: Deliver and adapt
Present the completed communication-storytelling.md file. Highlight how narrative addresses audience's key concerns. Note storytelling techniques used (data humanized, tension-resolution, specificity). If user has feedback or needs adaptations for different audiences, use resources/methodology.md for multi-version strategy.
When to use: Major changes, pivots, overcoming challenges
Structure:
Example: "We were growing 20% YoY, but churning 10% monthly—unsustainable. Data showed we were solving the wrong problem for the wrong users. We tested 5 hypotheses over 3 months, failing at 4. The one that worked: focusing on power users willing to pay 5x more. Churn dropped to 2%, growth hit 40% YoY. Now we're betting everything on premium tier."
When to use: Recommendations, proposals, project updates
Structure:
Example: "We lose 30% of signups at checkout—$2M ARR left on table. Root cause: we ask for credit card before users see value. Proposal: 14-day trial, no card required, with onboarding emails showing ROI. Comparable companies saw 60% conversion lift. Expected impact: +$1.2M ARR with 4-week implementation."
When to use: Product launches, feature announcements, process improvements
Structure:
Example: "Before: Sales team spends 10 hours/week manually exporting data, cleaning it in spreadsheets, and copy-pasting into slide decks—error-prone and soul-crushing. After: One-click report generation with live data, auto-refreshing dashboards, 30 minutes per week. Bridge: We built sales analytics v2.0, launching Monday with training sessions."
When to use: Executive communications, board updates, investor relations
Structure:
Example: "Situation: We budgeted $5M for customer acquisition in 2024. Complication: iOS 17 privacy changes killed our primary ad channel—50% drop in conversion overnight. Resolution: Shifting $2M to content marketing (3-month ROI), $1M to partnerships (immediate distribution), keeping $2M in ads for testing new channels. Risk: content takes time to scale, but partnerships derisk timeline."
Data-Heavy Communications:
Technical → Non-Technical:
Change Management:
Crisis Communications:
Do:
Don't:
Red Flags:
Resources:
When to use which resource:
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.