pitch-htt
Create a positioning campaign -- guided interview builds campaign.json, strategy brief, and deliverables tailored to your audience, medium, and stakes. Use when user says 'pitch', 'I need to convince', 'position this', 'make them care'.
What this skill does
<purpose>
Main workflow for heres-the-thing. Guided interview that builds a campaign: gathers subject, audience, goals, context, and precedent, then generates a strategy brief and deliverables based on the decision framework.
If `--resume` or an existing campaign-id is passed, loads the existing campaign and skips to prep level assessment (delegates to `/heres-the-thing:prep-htt` logic).
</purpose>
<steps>
<step id="load-config" number="1">
<description>Load Configuration</description>
<load-config>
Resolve the user's home directory (run `echo $HOME` via Bash). Use this absolute path for all file operations below -- never pass `~` to the Read tool.
1. Read `<home>/.things/config.json`
<if condition="config-missing">Tell the user: "Run `/things:setup-things` first." Then stop.</if>
2. Check that `<home>/.things/heres-the-thing/` exists
<if condition="htt-missing">Tell the user: "Run `/heres-the-thing:setup-htt` first." Then stop.</if>
3. Read `<home>/.things/heres-the-thing/deliverable-types/index.json`
4. Read `<home>/.things/shared/professional-profile.json` (for self-assessment defaults)
5. <if condition="resume-flag-or-campaign-id">
Read the existing campaign.json and skip to Step 8 (Generate).
</if>
</load-config>
</step>
<step id="gather-subject" number="2">
<description>Step 1: What Are You Positioning?</description>
Use AskUserQuestion:
What are you positioning? This can be anything -- a tool you built, someone else's idea, a proposal, a promotion, a policy change, a request for resources, or something that doesn't exist yet.
<phase name="subject-source" number="1">
How do you want to describe it?
<options>
- Describe it now (free text)
- Pull from an i-did-a-thing log
- Reference a URL, file, or existing campaign
- Describe something that doesn't exist yet (idea, aspiration)
</options>
<if condition="pull-from-idat">
Search `<home>/.things/i-did-a-thing/index.json` for recent entries. Present top 10 by date. Let user select one.
Extract title, description, tags, and store as `source_refs` entry with type `idat_log`.
</if>
<if condition="reference-url">
Ask for the URL or file path. Store as `source_refs` entry with type `url`.
</if>
</phase>
<phase name="subject-type" number="2">
What kind of thing is this?
Use AskUserQuestion (free text accepted):
<options>
- project -- Something you built or are building
- idea -- A concept or proposal
- request -- Asking for resources, approval, or support
- tool -- A specific tool, library, or system
</options>
<rule>Accept any string -- these are suggestions, not an enum.</rule>
</phase>
<phase name="subject-familiarity" number="3">
How well do you understand what you'll be communicating about?
Use AskUserQuestion:
<options>
- expert -- I know this deeply, could answer any question
- i_built_it -- I created it and know it well
- familiar -- I understand the basics but may have gaps
- new_to_me -- I'm still learning about this
</options>
<if condition="new_to_me-or-familiar">
Flag: Subject research tasks will be included in the strategy brief. Confidence flags will mark assumptions that need verification.
</if>
</phase>
</step>
<step id="gather-goals" number="3">
<description>Step 2: Who / Why / Where / When (Per Goal)</description>
<constraint>A campaign can have multiple goals. Start with the first one, then ask if they want to add more.</constraint>
For each goal, use AskUserQuestion to gather:
<phase name="goal-basics" number="1">
1. **Goal description**: What outcome are you trying to achieve?
2. **Goal type**:
<options>
- short_term -- A specific near-term outcome
- long_term -- A broader objective that may require multiple steps
</options>
3. **Target date**: When does this need to happen? (date or relative like "next Friday", "end of Q2")
4. **Stakes**:
<options>
- low -- Nice to have, won't hurt if it doesn't land
- medium -- Important but recoverable
- high -- Critical outcome, significant consequences
</options>
</phase>
<phase name="goal-audience" number="2">
**Audience**: Who are you trying to reach?
Use AskUserQuestion:
<options>
- A specific person (I'll name them)
- An audience segment I've already defined
- A new audience I'll describe now
</options>
<if condition="specific-person">
Ask for their name. Check `<home>/.things/shared/people/` for an existing profile.
<if condition="person-exists">Load their profile.</if>
<if condition="person-not-found">
Ask the user: "No profile found for <name>. I'll create one. What's their role/title?"
Create a minimal profile in `<home>/.things/shared/people/<slug>/profile.md` and `index.json`.
</if>
Then ask:
- **Receptiveness**: How receptive is this person to what you're proposing?
<options>
- champion -- They're already on your side
- enthusiastic -- Open and supportive
- neutral -- Will evaluate on merits
- skeptical -- Needs convincing
- hostile -- Actively against it
</options>
- **Familiarity**: How well do you know this person?
<options>
- well_known -- Worked together extensively
- moderate -- Some interaction
- low -- Barely know them
- unknown -- Never met
</options>
- **Familiarity notes** (free text, optional): Anything else about your relationship or their preferences?
</if>
<if condition="existing-segment">
List available segments from `<home>/.things/heres-the-thing/audiences/`. Let user select.
Ask for receptiveness override (or use baseline).
</if>
<if condition="new-audience">
Gather basic audience info inline (name, key concerns, decision criteria). Store in campaign only (not as a reusable segment).
</if>
<rule>A goal can have multiple audience entries (e.g., presenting to a group).</rule>
Ask: "Is there anyone else in this audience for this goal?"
</phase>
<phase name="goal-medium" number="3">
**Medium**: How will you deliver this?
Use AskUserQuestion (free text accepted):
<options>
- meeting_1on1 -- One-on-one meeting
- meeting_group -- Group meeting or presentation
- email -- Written email
- proposal -- Formal written proposal
- talk -- Presentation or talk
- cold_outreach -- Cold email or message
- slack -- Slack message or thread
</options>
<rule>Accept any string -- these are suggestions, not an enum.</rule>
**Delivery length** (if applicable): How long do you have? (e.g., "30 min", "1 page", "5 min lightning talk")
</phase>
<phase name="goal-deliverables" number="4">
Based on the decision framework (see Step 7), the system will auto-select deliverables. But ask:
Are there specific deliverables you want for this goal beyond the auto-selected ones?
Show available types from the deliverable type registry.
</phase>
<phase name="more-goals" number="5">
Use AskUserQuestion:
Do you want to add another goal for this campaign?
<options>
- Yes -- add another goal
- No -- that's all
</options>
<if condition="add-another">Loop back to the start of this step.</if>
<rule>If a user defines both short-term and long-term goals, prompt them to link them: "Does <short-term-goal> roll up to <long-term-goal>?" Set `parent_goal` accordingly.</rule>
</phase>
</step>
<step id="gather-context" number="4">
<description>Step 3: Context</description>
Use AskUserQuestion:
1. **Situational context**: What's the landscape? What's happening that makes this timely? (free text)
2. **Precedent**: Is there anything relevant from your past thaRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".