memory-update
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".
What this skill does
Scan session history, surface save-worthy moments, propose → confirm → write. Never fabricate — every proposal must cite a transcript turn.
## Scope
Creates or revises memory files in the agent's memory directory. Does not delete, merge-stale, or audit existing files (that is `memory-clean`). Does not redact or sanitize (that is `memory-sanitize`).
## Path resolution
```sh
SKILL_SCRIPTS="${MEMORY_UPDATE_SKILL_SCRIPTS:-$HOME/.claude/claude/skills/memory-update/scripts}"
MEMORY_DIR=$("$SKILL_SCRIPTS/resolve-paths.sh" memory_dir)
SESSION_HISTORY_GLOB=$("$SKILL_SCRIPTS/resolve-paths.sh" session_history_glob)
```
Abort on non-zero exit. Override `MEMORY_UPDATE_SKILL_SCRIPTS` if installed outside `$HOME/.claude`. Override `MEMORY_DIR` / `SESSION_HISTORY_GLOB` env vars to target a non-Claude-Code agent's layout.
## Memory types and required sections
Read `references/MEMORY-FRONTMATTER.md` for the full schema. Key rules:
| type | Required extra sections |
|---|---|
| `feedback` | `**Why:**` and `**How to apply:**` |
| `project` | `**Why:**` and `**How to apply:**` |
| `user` | none beyond frontmatter |
| `reference` | none beyond frontmatter |
Filename: `<type>_<slug>.md`. Slug: lowercase, hyphens only, ≤ 40 chars.
## Workflow
### 1. Resolve paths (above)
### 2. Scan session history for proposals
Run `scripts/scan-session.sh "$SESSION_HISTORY_GLOB"` → JSON array:
```json
[{ "type": "feedback", "slug": "prefer-foo", "evidence_turn_ids": ["uuid-123"],
"draft_body": "...", "draft_index_entry": "- [Title](file.md) — hook" }, ...]
```
Read `references/SIGNAL-HEURISTICS.md` to understand which turns qualify. If the user triggered the skill with an explicit instruction ("remember that X"), synthesize a proposal from that instruction directly instead of scanning.
### 3. Present proposals and wait for confirmation
Render each proposal as:
```
Proposal N — type: feedback
Evidence: turn uuid-123 ("the user said 'stop doing X'")
Draft:
---
name: …
description: …
type: feedback
---
Rule text. **Why:** … **How to apply:** …
Index entry: - [Title](file.md) — hook (N chars)
Accept / Reject / Edit?
```
Wait for explicit user response per proposal. Never write without confirmation.
### 4. Check for near-duplicates before writing
```sh
rg -l -F "<key phrase from draft>" "$MEMORY_DIR"
```
`rg` works on any directory regardless of git worktree boundaries. If a hit exists, show the existing file's content and ask whether to merge into it or create new.
### 5. Write
- Write `"$MEMORY_DIR/<type>_<slug>.md"` with frontmatter + body.
- Append (or update) one-line entry in `"$MEMORY_DIR/MEMORY.md"` (≤ 150 chars).
### 6. Verify
Read back each written file; confirm frontmatter parses as YAML (key: value lines present, no tab-indentation errors). Report which files were written and their line counts.
## Anti-patterns (never do)
- Fabricate a memory without citing a transcript turn or explicit user statement.
- Write without per-proposal user confirmation.
- Store code patterns, fix recipes, git history, or ephemeral task state.
- Create MEMORY.md entries exceeding 150 chars.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($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.