reference-decode
Decode benchmark videos, contact sheets, frames, or rough ideas into reusable prompt structure. Use this when you need to extract hook essence, viewer question, must-copy visual grammar, and forbidden drift before writing storyboard or generation prompts.
What this skill does
# Reference Decode ## Use When - A benchmark video, contact sheet, frame set, rough idea, or source material needs to become promptable structure. - You need the hook essence, viewer question, visual grammar, and forbidden drift before storyboard or request writing. - A no-reference brief still needs a proxy structure before prompt work. ## Do Not Use When - Do not create the final storyboard grid or provider payload here. - Do not copy faces, exact wardrobe, creator identity, exact location, or exact overlays from benchmark material. ## Core Rule Do not summarize references as "good vibe", "nice pacing", or "strong chemistry". Extract four objects: - `hookEssence` - `viewerQuestion` - `mustCopyVisualGrammar` - `forbiddenDrift` ## Default Workflow 1. Use the smallest sufficient source set: hook-first clip, first 0-5 seconds, hook-first contact sheet, supporting note, or full style board only if needed. 2. Decode the opening mechanism: first clear promise, viewer question, and the exact visual structure that makes the promise legible. 3. Separate structure from identity. Keep camera grammar, shot order, object logic, timing, and relationship logic; do not keep exact identity details. 4. Create a compact decode artifact when it is useful. 5. Print or return the decode block before storyboard or request writing. ## No-Reference Mode When no usable reference exists, operate in proxy mode: - start from the chosen segment pattern - infer the likely viewer question - express must-copy grammar as scene anchors, not imitation notes - express forbidden drift as anti-generic safeguards - state that the output is brief-derived, not observed from footage ## Output Shape The artifact contains `hookEssence`, `viewerQuestion`, `mustCopyVisualGrammar`, and `forbiddenDrift`. ## Stop Conditions - Stop when required user intent, source evidence, or owned input artifacts are missing and guessing would change the result. - If an owned CLI or script command fails, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools. ## Handoff - Grid, beat sheet, or full render request -> `video-request-architect`. - Explicit learn/do-not-copy boundary -> `reference-contract-builder`. - Prompt already drafted -> `prompt-preflight-qa`. ## Public Command Boundary - Choose the smallest matching command or workflow from the user input and run it directly. - If an owned CLI or script command fails, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools. - This public skill is instruction-driven. Produce the artifact described by the workflow directly from the available evidence. - Do not call private provider/runtime paths or unpublished local tools. - If the CLI returns a quote-confirmation challenge, run `postplus quote confirm --json --challenge-file <challenge.json>` and retry with the returned token.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.