reply
Review p11 document comments and replies, then post useful replies to visible threads that ask questions, are unclear, are indecisive, or need input. Use when Claude Code should answer reviewers on a p11 document.
What this skill does
# p11:reply Use this skill to inspect p11 comments/replies and post replies where a response is useful. ## Target Resolution Resolve the p11 document target in this order: 1. Use the p11 read URL, edit URL, read ID, or edit ID provided by the user. 2. If none is provided, use the most recent p11 document mentioned or created in the current chat conversation. 3. Only if the current chat has no usable p11 target, run `p11 history` and use the most recent relevant entry. Do not use `p11 history` when the current chat already contains a usable p11 target. ## CLI Resolution Prefer the global `p11` CLI. If missing, install `@p11-core/cli` globally. Use `npx -y @p11-core/cli@latest` only when global install is not possible. Never install p11 into the project. Check availability with `command -v p11` and `p11 --help`. Install or upgrade with `npm install -g @p11-core/cli@latest` when the command is missing or any `p11` command prints an update warning. Use `--json` when structured comment fields are useful. ## Review Comments Fetch all comments/replies: ```bash p11 comments <target> ``` Use `--version <number>` only when the user asks for comments on a historical version. Only consider comments/replies that are visible to reviewers. Do not reply to resolved or hidden comments; reviewers will not see those replies in the UI. Review every visible thread before replying. Decide from the comment/reply content, not from an unresolved status field alone. Reply when a visible thread: - asks a question - requests clarification - needs input or a decision - is indecisive - has conflicting replies - is unclear to Claude Code - needs a lightweight acknowledgement before the document can be revised Do not equate an unresolved or visible status with needing a reply. If the thread already gives a clear action, such as "change this to...", "remove this...", "use this wording", or another settled decision, do not reply; those should be handled by `p11:revise`. If no threads need replies, say that clearly and summarize any clear decisions that should be handled by `p11:revise`. When discussing comments with the user, refer to quoted text or thread content instead of line numbers unless the user asks for line numbers. ## Posting Replies Post replies with: ```bash p11 reply <readUrl|readId> <commentId> --name "Claude Code" --body <text> ``` If the user provided only an edit URL or edit ID, use the current chat context, `p11 comments`, or `p11 history` to recover the matching read URL or read ID before replying. Use `--body-file <file>` or `--body-file -` for multi-line replies. Use the reply name `Claude Code` for replies from Claude Code. Keep replies concise and specific. If the comment is unclear, ask one direct clarifying question and name the decision needed to proceed. After posting replies, ask the user to refresh the p11 page to see them.
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.