research-add-items
Append new items (research objects) to an in-progress research outline's `outline.yaml` — sourced from your direct input, a web-search agent, or both. Use mid-`/research-outline` when you've realised the items list is incomplete (a new competitor surfaced, an important historical entry was missed, a category needs broader coverage) before running `/research-deep`, so the new items are part of the parallel deep pass instead of needing a separate run.
What this skill does
# Research Add Items — Append to the Items List
In-place updates `outline.yaml` with additional research objects.
## Trigger
`/research-add-items`
## Pipeline position
```
/research-outline → ► /research-add-items ◄ → /research-deep → /research-report
```
Reachable any time after `/research-outline` has produced `outline.yaml`, but most useful *before* `/research-deep` so the new items get researched in the same parallel pass.
## Workflow
### Step 1 — Auto-locate outline
`Glob` `*/outline.yaml` from the current working directory. `Read` it to know the existing items (avoid duplicates) and the current `execution` config.
### Step 2 — Gather candidates from two sources
These two sources are gathered sequentially (`AskUserQuestion` blocks waiting on the user; web search can run in the background after). Do them in this order:
1. `AskUserQuestion`: "Which items do you want to add? Any specific names?" — capture whatever the user already has in mind.
2. `AskUserQuestion`: "Should I also run a web-search agent for more candidates?" — if yes, launch a research subagent via the `Task` tool (`subagent_type: general-purpose`, `run_in_background: true`) seeded with the topic, the existing items list, and any items the user named in step 1 (so suggestions don't duplicate).
### Step 3 — Merge, deduplicate, confirm
- Combine the user-supplied items and the subagent's suggestions.
- Deduplicate by case-insensitive name match against the existing `outline.yaml`.
- Show the merged candidate list to the user. `AskUserQuestion` for which to accept.
- For each accepted item, capture: `name` (required), `category` (optional), `description` (optional, short).
### Step 4 — Save update
Append accepted items to `outline.yaml`, preserving existing structure. Save in place.
## Item shape (matches `/research-outline`)
```yaml
items:
- name: <item>
category: <optional>
description: <optional, short>
```
## Output
Updated `{topic}/outline.yaml` — in-place modification, user confirms before save.
## Gotchas
- **Duplicate detection is case-insensitive name match only.** `GPT-4` and `GPT 4` (different by one character) are not detected as duplicates. Eyeball the merged list before saving if you suspect near-duplicates.
- **Items added after `/research-deep` has already run are not auto-researched.** You either need to re-run `/research-deep` (its Step 2 resume check will skip already-completed items and only fan out the new ones), or research the new items manually.
- **The web-search subagent operates outside the conversation context.** Hand it the topic AND the current items list explicitly, so its proposals don't repeat what's already there.
- **`outline.yaml.execution.batch_size`** controls how many deep agents `/research-deep` runs in parallel. If you add many items at once, you may want to bump `batch_size` here too — but that's outside this skill's scope; edit `outline.yaml` directly or re-run `/research-outline`'s Step 4 prompts.
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.