ericrisco/rsc-harness / skills/shortform-ideation
shortform-ideation
VerifiedUse when a Reels/TikTok/Shorts account needs its next video ideas scored into a ranked backlog, grounded in its own performance log plus dated trending sounds, each bet logged so its outcome feeds the next batch. NOT scripting a chosen idea (that is `video-shorts`), NOT pillars or cadence (that is `shortform-strategy`), NOT packaging a finished cut (that is `shortform-packaging`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.1 KB |
| evals/README.md | markdown | 1.5 KB |
| evals/cases.yaml | config | 3.9 KB |
| references/experiment-ledger.md | markdown | 2.9 KB |
| references/trend-sources.md | markdown | 3.7 KB |
| scripts/verify.shexecutable | script | 6.4 KB |
evals/cases.yaml
View on GitHubskill: shortform-ideation
# Prompts that MUST load `shortform-ideation`. The skill owns the IDEA LOOP for a
# Reels/TikTok/Shorts account: ground in the account's own perf log, fold in dated
# trending signals (no scraping), generate + score + rank a backlog, and log each
# bet as a hypothesis with result fields. It does NOT script/edit one video
# (video-shorts), set pillars/cadence (shortform-strategy), package a finished cut
# (shortform-packaging), do YouTube ideation (youtube-ideation), run a cross-channel
# calendar (content-engine), or build dashboards (analytics).
should_trigger:
- prompt: "Give me 10 Reels ideas for next week for our coffee brand."
why: "Core ask — generate a ranked batch of short-form ideas is the skill's primary deliverable."
- prompt: "We have 12 ideas — which 3 do we shoot first?"
why: "Prioritization/scoring of an idea set is core; the skill ranks into a backlog rather than dumping."
- prompt: "Fold this week's trending TikTok sounds into our idea list."
why: "Trend-grounded ideation — capturing dated trend signals and turning them into scored ideas is Phase 2→3."
- prompt: "Why did the videos we bet on last month flop?"
why: "Non-obvious — sounds like analytics, but reviewing the outcome ledger that ties each bet to its measured result is THIS skill's loop, not generic reporting."
- prompt: "Idéame Reels para esta semana basándote en lo que ya nos funcionó."
why: "Spanish for 'come up with Reels for this week based on what already worked for us' — grounded-in-own-log ideation, the Phase-1+Phase-3 signature."
- prompt: "Prioritza idees de vídeo curt per aquesta setmana i digue'm quina gravem primer."
why: "Catalan for 'prioritize short-video ideas for this week and tell me which to film first' — generation + prioritization, core loop."
should_not_trigger:
- prompt: "Write the shot-by-shot script and edit sheet for this Reel idea."
route_to: video-shorts
why: "Writing spoken lines and beat timecodes crosses out of ideation into the craft of one short."
- prompt: "What should our posting cadence and content pillars be?"
route_to: shortform-strategy
why: "Account-level positioning, pillars, and cadence are consumed by this skill, not authored by it."
- prompt: "Write the caption and pick the hashtags for this finished Reel."
route_to: shortform-packaging
why: "Caption/cover/hashtag-set for an already-shot cut is packaging; ideation only suggests a hashtag as a trend signal."
- prompt: "Give me YouTube video ideas with thumbnail-first packaging."
route_to: youtube-ideation
why: "YouTube's packaging-led, slower-decay idea pipeline is a different skill; this one is Reels/TikTok/Shorts-native."
- prompt: "Build us a metrics dashboard for our social performance."
route_to: analytics
why: "Generic reporting/dashboards live in analytics; this skill only reads the perf log to ground and score ideas."
capability:
- scenario: "An account has a 2-month performance log in 02-DOCS where hook patterns A and B won (>60% 3s-hold) and topic C flopped twice. The user asks for next week's idea batch and to fold in this week's trending sounds."
must_include:
- "Reads/uses the 02-DOCS performance log to ground ideas (cites winning hooks A/B and the dead topic C; never re-pitches topic C)"
- "Captures at least one trend signal WITH a first-seen date and WITHOUT any scraping command (manual/assisted capture or sanctioned API)"
- "Produces a ranked backlog table with the required columns (id, idea, hook line, trend signal + date, format, target length, score, status)"
- "Scores each idea by hook strength and shareability/save (hook weighted highest), not by topic interest alone"
- "Writes at least one advanced idea as a dated hypothesis under 02-DOCS/shortform/experiments/ with result fields left pending"
- "Does NOT write full scripts or beat timecodes; explicitly hands the chosen idea off to video-shorts"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |