hiruno-content-skills

Use this skill whenever the user wants to make a single-clip video with text overlay and value in the caption. Trigger on phrases like "B-roll post", "single clip with text", "read caption video", "read more in caption", "post with one B-roll", "I just have one clip", "lazy post", "quickest format to make", or whenever the user has a short video clip and wants to publish it without a full script or filming. This is the fastest format to make (~10 minutes) and the highest retention hack of the three formats: the caption takes longer to read than the clip is long, so the clip loops while the viewer reads, spiking average watch time.

Use this skill at the start of any new content project, before any other Hiruno skill runs. It walks the user through a one-time brand setup and writes `.agents/brand-content-context.md`, the single source of truth for brand voice, audience symptoms, content pillars, format library, and the why anchor. Every other content skill in this repo reads that file first. Trigger this skill whenever the user mentions "set up the brand", "brand context", "new client", "onboard a brand", "brand voice", "audience research", "content pillars", "find the niche", or starts a content project for a brand that has no `.agents/brand-content-context.md` yet. Also trigger when the user wants to update an existing brand context with new pains, desires, pillars, or voice notes.

Use this skill whenever the user wants to audit, review, diagnose, or analyse existing content for what's working and what isn't. Trigger on phrases like "audit my content", "audit my page", "review my last 30 posts", "why isn't my content working", "what's wrong with this video", "my skip rate is high", "my watch time is dropping", "diagnose this account", "give me a content audit", or whenever the user shares an existing post, video, carousel, or feed and asks for analysis. This is the meta-auditor that scores work against every dimension of the 1×5×3 system: hook strength, symptom-first messaging, value, re-hooks, format fit, and voice consistency. Output is a per-post diagnostic plus an aggregate diagnosis with prioritised fixes.

Use this skill whenever the user wants to write, plan, or refine a script for a talking-head video. Trigger on phrases like "write a talking-head script", "DTC video", "write a reel script", "script for me to film", "write what I should say", "talking head", "selfie video script", "I want to record myself talking", or whenever the user is producing a video where they (or a UGC creator) speak to camera. Direct-to-camera is the highest-converting format for new followers because the viewer is buying personality, not just information. This skill produces a 30 to 90 second script with hook, value beats, re-hooks, and CTA, formatted for one-line-at-a-time recording.

Use this skill whenever the user wants a deep, hook-specific audit across many pieces of content. Trigger on phrases like "audit my hooks", "score these hooks", "why aren't my hooks working", "skip rate diagnosis", "review my opening lines", "are my hooks pulling their weight", or whenever the user has a batch of existing hooks (10+ posts, an ad set, a feed) and wants to know which type is working, which isn't, and what to fix. This is the hook-only deep dive — different from content-audit, which scores many dimensions. Output is per-hook scores plus aggregate patterns showing which hook type, which symptom, and which structural moves are winning for this brand.