skills/forensic-speech-structure/SKILL.md
Structure persuasive speeches and formal arguments in forensic, legal, policy, and competitive debate styles. Use when the user needs to prepare talks, opening or closing arguments, policy pitches, public explanations, debate speeches, or mentions 'forensic speech', 'formal argument', 'persuasive speech structure', 'debate speech', 'opening statement', 'closing argument'. Turns structured claims into audience-tuned persuasive delivery.
npx skillsauth add curiositech/windags-skills forensic-speech-structureInstall 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.
Format Selection Tree: Choose structure based on audience and time constraints:
IF legal/judicial context:
├─ IF <10 minutes → Classical 5-part (abbreviated)
└─ IF >10 minutes → Classical 5-part (full)
IF policy/legislative context:
├─ IF formal body → Congressional format
└─ IF advocacy → Policy debate format
IF public/corporate presentation:
├─ IF <15 minutes → TED-style structure
├─ IF hostile audience → Classical (heavy refutatio)
└─ IF neutral/friendly → TED-style or Congressional
IF competitive debate:
├─ IF policy debate → Plan/Inherency/Harms/Solvency
└─ IF parliamentary → Classical 5-part
Argument Ordering Decision:
Time Allocation by Format:
1. Exordium Overload
2. Evidence Dumping
3. Strawman Refutation
4. Fizzle Finish
5. Format Mismatch
Example 1: Legal Closing (200 words)
[EXORDIUM] "Members of the jury, three weeks ago you promised to follow the evidence wherever it leads. Today, it leads to one conclusion: reasonable doubt."
[NARRATIO] Timeline: incident at 9:47pm → police arrival 10:15pm → witness statements collected 11pm-1am.
[CONFIRMATIO] First, the alibi: restaurant receipt timestamped 9:52pm, five miles away. Physical impossibility to travel that distance in 5 minutes during rush traffic. Second, witness credibility: Ms. Johnson changed her story three times between initial statement and trial testimony—first "maybe saw someone," then "definitely the defendant," now "absolutely certain." This progression suggests influence, not memory.
[REFUTATIO] The prosecution says restaurant receipts can be faked. But they provided no evidence of forgery, no motive for the restaurant to lie, no explanation for how my client could fake a receipt showing him ordering food at the exact moment of the crime.
[PERORATIO] Reasonable doubt isn't just possible here—it's unavoidable. The evidence doesn't whisper doubt; it shouts it. Your oath demands you follow that evidence. Find my client not guilty.
Expert catches: Primacy/recency in confirmatio (strongest argument last), refutatio addresses prosecution's likely response, peroratio echoes opening oath language. Novice misses: Would dump all evidence equally, wouldn't anticipate strongest objection.
Example 2: Policy Pitch (150 words)
[PROBLEM] Remote work policies are failing 40% of employees who report isolation and productivity drops. Current hybrid solutions address logistics but ignore human connection needs.
[SOLUTION] Implement "squad-based" remote work: permanent 4-person teams with daily virtual coworking sessions, quarterly in-person intensives, and shared project ownership.
[BENEFITS] Pilot data from three departments shows 23% productivity increase, 67% reduction in reported isolation, 45% improvement in project completion rates. Cost: $2400/employee annually vs. $18,000 for full office return.
[ADDRESSING CONCERNS] "This sounds complicated"—actually simpler than current ad-hoc arrangements. Everyone knows their squad, daily touchpoint, quarterly dates. "What about bigger meetings?"—squads send representatives, just like current team leads model.
[CALL TO ACTION] Approve the six-month pilot for marketing and engineering. If results match our pilot data, we'll have solved remote work's biggest weakness while keeping its biggest advantages.
Expert catches: Concrete data points, addresses obvious objection, specific ask. Novice misses: Would provide vague benefits, wouldn't anticipate implementation concerns.
Do NOT use this skill for:
presentation-structure insteadinstructional-design insteadceremonial-speech insteadsocratic-dialogue insteadargumentative-writing insteadDelegate when:
toulmin-argument-analysis firstlogical-fallacy-detector before structuringsteel-man-argumentaudience-analysis for complex stakeholder mappingdata-ai
license: Apache-2.0 NOT for unrelated tasks outside this domain.
development
Use when designing caching strategies (cache-aside, write-through, write-behind), implementing distributed locks, building rate limiters, leaderboards, real-time streams (XADD/consumer groups), pub/sub, or tuning eviction policies. Triggers: thundering-herd on cache miss, dogpile on key expiry, Redlock vs SET-NX-PX choice, sliding-window rate limiter, hot-key on a single cluster slot, big-key blowup, MULTI/EXEC across slots, KEYS in production. NOT for Redis Cluster operations/admin (different domain), embedded KV (SQLite, leveldb), in-process LRU caches, or Memcached.
tools
Drawing the `'use client'` boundary correctly in React Server Components apps (Next.js App Router, RSC frameworks) — leaf-pushing, slot composition, serialization rules, and environment poisoning prevention. Grounded in react.dev and Next.js 16 docs.
development
Use when designing rate limiting for an API, choosing between token bucket / sliding window / leaky bucket / fixed window, implementing it in Redis, deciding edge (Cloudflare/Upstash) vs origin enforcement, sizing per-user vs per-IP vs per-endpoint quotas, returning the right 429 response with Retry-After, or fixing the boundary-burst bug in fixed-window limiters. Triggers: 429 too many requests, INCR + EXPIRE, ZADD + ZREMRANGEBYSCORE + ZCARD, X-RateLimit-Remaining header, Cloudflare WAF rate limiting rules, Upstash @upstash/ratelimit, leaky bucket shaping vs policing, distributed rate limiter consistency. NOT for DDoS mitigation specifically (different scale), CAPTCHA / bot management, full WAF design, or per-user quota billing.