cmd-code-what
Catch the user up on what the agent has been doing in the current session with 3-5 ultra-tight bullet points. Use when the user invokes /cmd-what, asks "what are you doing", "what did you do", "catch me up", "status", "where are we", or otherwise needs a fast situational summary of in-flight agent work.
What this skill does
# What <!-- omit in toc -->
Give the user a high-signal, low-noise snapshot of what's happened in this session so they can re-enter the loop without scrolling back.
## Output format
Reply with **3-5 bullet points only**. No preamble, no closing summary, no headers, no follow-up questions. Each bullet must be:
```
- **1-3 word label**: explanation in less than 120 characters
```
Hard rules:
- **3-5 bullets, no more, no less in spirit** (4 is the sweet spot)
- **Label**: 1-3 words, bolded, title-case or kebab-case, names a concrete thing (file, action, decision, blocker)
- **Explanation**: a single clause, **< 120 characters including the label**, present tense or past tense — never future tense ("will", "going to")
- No nested bullets, no code fences, no links, no emoji unless one is genuinely load-bearing
- Skip anything the user already knows from the last 1-2 turns — focus on what they'd miss if they just walked back to the terminal
## What to include (in priority order)
1. **Current focus** — what file/task is actively being worked on right now
2. **Most recent concrete change** — what just got written, edited, run, or decided
3. **Blocker or open question** — anything waiting on the user, or that's stuck
4. **Next step** — the very next action the agent intends to take, if obvious
5. **Notable side effects** — files created, branches touched, processes started, only if relevant
## What to leave out
- Restating the original user request verbatim
- Tool-call narration ("I ran ls, then grep, then…")
- Anything that happened more than ~10 turns ago unless it's still load-bearing
- Hedging, qualifiers, or meta-commentary about the summary itself
## Example
User: `/cmd-what`
Good response:
```
- **Editing**: refactoring `auth/session.py` to drop the legacy cookie path
- **Tests**: 14/16 passing, 2 failing on token refresh edge case
- **Blocked**: need to know if expired refresh tokens should silently re-auth or 401
- **Next**: wire the chosen behavior into `refresh_token()` once you decide
```
Bad response (too verbose, narrates tool calls, future-tense, missing labels):
```
- I started by reading the auth module and then I grepped for cookie usage
- I'm planning to refactor the session handling but first I want to check with you
- The tests will probably need updates too
```
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.