Explore skills

Generates a week-by-week narrative digest of a project's Claude-mem timeline, splitting it into ISO-week files and using subagents to produce weekly chapters. Ideal for "weekly digests" or "narrative chapters" of a project's history.

Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More.

Converts a single document into a kawaii NotebookLM slide-deck PDF. It's used to generate shareable narrative slides from a single file, responding to commands like wowerpoint this, make a deck about <file>, or turn this report into slides.

Maps a codebase into feature-grouped flowcharts, identifies duplicated concerns across features, and proposes a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor, emitting a proposed unified flowchart plus per-system /make-plan prompts.

Generates a Journey Into [Project] narrative report analyzing a project's entire development history from claude-mem's timeline. Use it when asked for a timeline report, project history analysis, development journey, or full project report.

Create a detailed, phased implementation plan including documentation discovery. Use this when asked to plan a feature, task, or multi-step implementation, especially before executing with 'do'.

Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.

This skill explains how claude-mem captures observations, when memory injection occurs, and where its data is stored.

Audits a design against Dieter Rams' ten "Good design is..." principles, then provides a /make-plan prompt for a new design, refinement, or redesign. Use when the user requests a design audit, review, or critique that should lead to a plan.

Token-optimized structural code search using tree-sitter AST parsing. Use this instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.

Persistent Context Across Sessions for Every Agent – This feature captures all agent activity during sessions, compresses it with AI, and re-injects relevant context into future interactions. It supports Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode, and more.

Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or "get up to speed".