create-type-htt
Create custom deliverable types with templates, tool requirements, and instructions for the deliverable agent. Use when user says 'create deliverable type', 'add a type', 'custom deliverable'.
What this skill does
<purpose>
Create custom deliverable types that extend heres-the-thing beyond the builtin types. Each type defines a template, output format, required tools/MCP servers/external binaries, and instructions for the deliverable agent.
Custom types are registered in `~/.things/heres-the-thing/deliverable-types/index.json` and can be included in any campaign goal's `deliverables` list.
</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. Read `<home>/.things/heres-the-thing/deliverable-types/index.json`
<if condition="types-missing">Tell the user: "Run `/heres-the-thing:setup-htt` first." Then stop.</if>
</load-config>
</step>
<step id="gather-type-info" number="2">
<description>Gather Type Information</description>
Use AskUserQuestion to gather:
1. **Name**: What should this deliverable type be called? (e.g., "Executive One-Pager", "Stakeholder Update Email", "Decision Matrix")
2. **Description**: What does this deliverable produce? What's it for?
3. **Output format**: What format should the output be in?
<options>
- md (Markdown)
- pdf (PDF -- requires external tool)
- html (HTML)
</options>
4. **Template**: Do you have a template for this type?
<options>
- Yes -- I'll provide template content
- No -- the instructions are enough
</options>
<if condition="has-template">
Ask the user to provide the template content. This can be a markdown structure, HTML template, etc.
</if>
5. **Instructions**: How should the deliverable agent use the strategy brief and campaign context to produce this deliverable? Be specific about structure, tone, length, and any special considerations.
6. **Required tools**: Which Claude Code tools does this type need?
- Write (always included)
- Bash (specify commands, e.g., `Bash(wkhtmltopdf)`)
- Any others
7. **Required MCP servers**: Does this type need any MCP servers? (e.g., for Google Docs integration)
8. **Required external binaries**: Does this type need any external programs installed? (e.g., `wkhtmltopdf`, `pandoc`)
</step>
<step id="validate-requirements" number="3">
<description>Validate Requirements</description>
<if condition="has-external-requirements">
For each declared external binary:
```bash
which <binary> 2>/dev/null && echo "found" || echo "missing"
```
<if condition="binary-missing">
Warn the user: "<binary> is not installed. This deliverable type will fail if used without it. Install it first, or continue anyway?"
</if>
</if>
<if condition="has-mcp-requirements">
Note: MCP server availability cannot be validated at registration time. The deliverable agent will check at runtime.
</if>
</step>
<step id="generate-id" number="4">
<description>Generate Type ID</description>
Generate a type ID from the name: lowercase, underscores, no special characters. (e.g., "Executive One-Pager" → `exec_one_pager`)
<check name="no-duplicate">Check that this ID doesn't already exist in the type registry.</check>
<if condition="duplicate">Ask the user to choose a different name or confirm overwrite.</if>
</step>
<step id="write-template" number="5">
<description>Write Template File</description>
<if condition="has-template">
<output-path>`<home>/.things/heres-the-thing/deliverable-types/<type-id>.md`</output-path>
Write the template content provided by the user.
</if>
</step>
<step id="register-type" number="6">
<description>Register Type</description>
Read `<home>/.things/heres-the-thing/deliverable-types/index.json`.
Add the new type:
```json
{
"<type-id>": {
"id": "<type-id>",
"name": "<name>",
"description": "<description>",
"builtin": false,
"template": "<type-id>.md or null",
"output_format": "<format>",
"requires": {
"tools": ["Write", "<additional tools>"],
"mcp_servers": ["<servers or empty>"],
"external": ["<binaries or empty>"]
},
"instructions": "<instructions>"
}
}
```
Write the updated index.json.
</step>
<step id="confirm" number="7">
<description>Confirm</description>
<completion-message>
Custom deliverable type registered:
- ID: `<type-id>`
- Name: <name>
- Output: <format>
- Template: <yes/no>
- Requirements: <tools>, <mcp_servers>, <externals>
Use it in campaigns by adding `"<type-id>"` to a goal's `deliverables` list.
</completion-message>
</step>
</steps>
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.