remember
Esta skill debe usarse cuando el usuario pide "recuerda que", "guarda esto", "anota esto", "no olvides que", "remember this", "save this", "store this", "keep in mind", "where should I save", "donde guardo esto", o menciona querer persistir informacion del proyecto. Proporciona clasificacion automatica al destino correcto de memoria de Claude Code segun la naturaleza del contenido.
What this skill does
# Remember Given a piece of information, classify its nature and write it to the correct Claude Code memory location for the current project. ## Scope Project-level only. The five valid destinations are: - `CLAUDE.local.md` — local environment, never versioned - `CLAUDE.md` — always-loaded project context, versioned - `.claude/rules/` — on-demand conventions (path-scoped or always-on), versioned - `.claude/skills/` — reproducible flows Claude can execute, versioned - `Memory` — project context not derivable from code, machine-local User-global destinations (`~/.claude/CLAUDE.md`, `~/.claude/rules/`) are out of scope. ## Reference files (read on demand) - `references/storage-decision-guide.md` — full spec for each destination: when to use, when not to, write format, and a concrete example. Read when the classification table below doesn't resolve the case. ## Decision sequence Apply these questions in order. Stop at the first `yes`. | Question | Destination | |---|---| | Is it a secret, credential, or API key? | **Refuse** — warn the user; none of these systems are appropriate | | Does it only apply on your local machine (localhost URLs, local paths, personal dev overrides)? | `CLAUDE.local.md` | | Is it project orientation Claude needs before opening any file (overview, structure, build/run commands)? | `CLAUDE.md` | | Does it apply only to certain file types or directories in the project? | `.claude/rules/` with `paths` frontmatter | | Is it a cross-cutting coding standard for the whole project (naming, error handling, control flow)? | `.claude/rules/` without frontmatter | | Is it a step-by-step procedure or workflow that Claude should execute reproducibly? | `.claude/skills/` | | Is it project context not derivable from the code (infra, stakeholders, historical decisions, external constraints)? | `Memory` (topic file under `~/.claude/projects/<project>/memory/`) | If the information fits two buckets equally, use `AskUserQuestion` to clarify before writing. ## Workflow ### Step 1: Classify Apply the decision sequence above. Use `$ARGUMENTS` as the information to store if provided; otherwise use the user's last message. Check for secrets first: URLs with credentials, tokens, passwords, private keys. If found, stop and warn — do not write. If the information applies to all of the user's projects (not just this one), it belongs in `~/.claude/CLAUDE.md` or `~/.claude/rules/`. This skill does not write to user-global destinations — tell the user and stop. ### Step 2: Resolve ambiguity Proceed without asking for clear cases. Ask only when: - The information could plausibly go to two different destinations and the choice changes how it behaves (e.g., "applies to all TypeScript" vs "applies to all code in the project"). - The destination file is near its size limit and writing would make it worse (CLAUDE.md approaching 200 lines). ### Step 3: Write For each destination, see `references/storage-decision-guide.md` for the exact write format. Abbreviated rules: - **CLAUDE.local.md**: verify `CLAUDE.local.md` is listed in `.gitignore` before writing; if not, warn the user and stop. Append at end; create file if absent. - **CLAUDE.md**: insert under the most relevant existing section; never create a new top-level section unless no section fits. If the file is at or above 180 lines, suggest running `rulify` first and stop. - **.claude/rules/ (path-scoped)**: check for an existing rule whose `paths` covers the same scope; merge into it if found, otherwise create a new file under `.claude/rules/<category>/<topic>.md` with `paths` frontmatter. - **.claude/rules/ (always-on)**: check for an existing rule covering the same standard; merge if found. Create new file without any frontmatter if no match. Never start the file with `---` — that converts it to a path-scoped rule with no triggers and it will never load. - **`.claude/skills/`**: check for an existing skill covering the same flow; merge into it if found. Otherwise create `.claude/skills/<skill-name>/SKILL.md`. See `references/storage-decision-guide.md` for format details. - **Memory**: write to a topic file (`~/.claude/projects/<project>/memory/<topic>.md`) using three-field frontmatter (`name`, `description`, `metadata.type`) plus body. Add or update the pointer line in `MEMORY.md`. If the new information contradicts existing content in the target file, overwrite the stale entry rather than appending. Report the replacement in Step 4. ### Step 4: Report One sentence: what was saved, where, and the deciding criterion. Example: `Saved to .claude/rules/code-standards/naming.md (always-on) — cross-cutting naming convention that applies to all project code.`
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.