research-add-fields
Append new field definitions to an in-progress research outline's `fields.yaml` — either from user-supplied input or from a web-search agent that proposes common dimensions in the domain. Use mid-`/research-outline` when you've realised the schema is missing dimensions (e.g. pricing, performance, ecosystem, governance) before running `/research-deep`, so deep agents fill the new fields on first pass instead of needing a re-run.
What this skill does
# Research Add Fields — Append to the Field Schema
In-place updates `fields.yaml` with additional research dimensions.
## Trigger
`/research-add-fields`
## Pipeline position
```
/research-outline → ► /research-add-fields ◄ → /research-deep → /research-report
```
Reachable any time after `/research-outline` has produced `fields.yaml`, but most useful *before* `/research-deep` so deep agents fill the new fields in their first pass.
## Workflow
### Step 1 — Auto-locate fields file
`Glob` `*/fields.yaml` from the current working directory. `Read` it to know what's already defined — so suggestions don't duplicate existing fields and you can show the user the current categories when asking.
### Step 2 — Pick a supplement source
`AskUserQuestion` with two options:
- **A. Direct input** — user dictates field names, descriptions, and categories.
- **B. Web search** — launch a research subagent via the `Task` tool (`subagent_type: general-purpose`) to propose common fields in the topic's domain.
### Step 3 — Display and confirm
- Show the candidate field list back to the user (whether from A or B).
- `AskUserQuestion` for each candidate: keep / drop / edit.
- For each kept field, capture: `category` (must match an existing `field_categories[].category` or be a new one), `detail_level` (`brief | moderate | detailed`), `required` (default `false`).
### Step 4 — Save update
Append the confirmed fields to `fields.yaml`, preserving existing structure and ordering. Save in place.
## Field shape (matches `/research-outline`)
```yaml
field_categories:
- category: <name>
fields:
- name: <field_name>
description: <what to capture>
detail_level: brief | moderate | detailed
required: false
```
## Output
Updated `{topic}/fields.yaml` — in-place modification, user confirms before save.
## Gotchas
- **Adding `required: true` retroactively breaks already-completed items.** If `/research-deep` already produced JSONs for some items and you add a new required field, those JSONs will fail validation. Either add the field as `required: false`, or plan to re-run `/research-deep` for the affected items.
- **Category names are matched literally.** A new field whose `category` doesn't match an existing `field_categories[].category` creates a new top-level category in the schema. That's fine, but make sure it's intentional — a typo here is a silent split.
- **The web-search subagent in option B operates outside the conversation context.** Hand it the topic and an explicit list of categories that already exist, so its proposals fit the schema rather than colliding with what's there.
- **`fields.yaml` is also consumed by `~/.claude/skills/research-outline/validate_json.py`**. The schema this skill writes must stay compatible with that validator — same `field_categories[].fields[].name` / `required` shape, no exotic YAML constructs.
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.