Skip to content

ericrisco/rsc-harness / skills/shortform-packaging

shortform-packaging

Verified

Use when a vertical short is shot or scripted and you need the upload-form copy and cover that win the feed — the hook line, the first-frame on-screen text, the search-led caption, a tight hashtag set, and the cover frame; it learns from what performed via the 02-DOCS log. NOT inventing the idea (that is `shortform-ideation`), NOT scripting or directing the cuts (that is `video-shorts`), NOT executing the edit (that is `shortform-editing`), NOT scheduling the post (that is `social-publisher`).

FileKindSize
SKILL.mdskill md14.1 KB
evals/README.mdmarkdown653 B
evals/cases.yamlconfig3.1 KB
references/package-templates.mdmarkdown5.4 KB
scripts/verify.shexecutablescript7.3 KB

evals/cases.yaml

View on GitHub
skill: shortform-packaging

should_trigger:
  - prompt: "Write the hook, caption and hashtags for this finished Reel."
    why: Core ask — three of the five upload-form artifacts for a finished short.
  - prompt: "Pick the cover frame and the text that goes on it for my TikTok."
    why: The cover artifact specifically — frame choice plus overlay, owned here.
  - prompt: "My shorts get views but nobody shares them — fix the packaging."
    why: Non-obvious — a shares complaint with no copy keyword; diagnosis maps to send-bait caption and a sendable hook, not the edit.
  - prompt: "Is 20 hashtags too many for a Reel?"
    why: Non-obvious — tests the Instagram 5-tag hard cap and the 3-5 best-practice rule.
  - prompt: "Log how my last 5 shorts performed and apply it to the next batch."
    why: The learning loop — read the 02-DOCS feedback log on retention/sends and carry winners forward.
  - prompt: "Rewrite this caption so it ranks in TikTok search."
    why: Caption as a search-ranking field — keyword-led first sentence, owned here.
  - prompt: "Escríbeme el gancho i el pie de foto per a aquest Reel i dona'm els hashtags."
    why: Spanish/Catalan — full upload-form copy ask (hook, caption, hashtags).

should_not_trigger:
  - prompt: "Come up with an idea for a short about productivity."
    route_to: shortform-ideation
    why: The idea/angle, which packaging consumes but never invents.
  - prompt: "Write the full script and plan the cuts for this 30s TikTok."
    route_to: video-shorts
    why: The spoken script and edit direction (the narrative layer), not the upload copy.
  - prompt: "Burn in the captions and add the B-roll for this clip."
    route_to: shortform-editing
    why: Execution of the edit, not the words and cover that wrap it.
  - prompt: "Schedule this Reel to post Tuesday 6pm across IG and TikTok."
    route_to: social-publisher
    why: When and where to post, not the copy or cover.
  - prompt: "Write the title and description for my long-form YouTube video."
    route_to: youtube-packaging
    why: Long-form metadata, not a vertical short's package.

capability:
  - scenario: >
      Given a finished 25s faceless productivity TikTok and a 02-DOCS feedback log whose
      last winner was a number-led on-screen hook, produce the full package.
    must_include:
      - Reads the 02-DOCS feedback log / brand voice BEFORE writing, and carries the number-led winner forward.
      - Emits a SET of >=2 hook + on-screen-text variants, each 4-7 words.
      - On-screen text restates the hook (the silent twin) and stays in the safe zones.
      - Caption first sentence is keyword-led and <=~150 chars, not a teaser like "wait for it".
      - Exactly 3-5 hashtags, topic-signal not a discovery dump.
      - A cover frame plus a <=6-word overlay that sits inside the 1:1 centre square (the band that survives the 3:4 grid, 4:5 feed, and 9:16 tab crops) and matches the hook.
      - A feedback-entry stub keyed on intro_retention / sends_per_reach / saves — not likes.
      - Routes nothing it does not own (no scripting, editing, scheduling, or idea invention).
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall