accelerate
Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token…
Quick summary of the last session — commands run, files changed, and what to do next.
$ npx -y skills add sharpdeveye/maestro --skill recap --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/recapContext preview
The summary Claude sees to decide when to auto-load this skill.
Quick summary of the last session — commands run, files changed, and what to do next.
name: recap description: "Quick summary of the last session — commands run, files changed, and what to do next." argument-hint: "[optional: session file]" category: utility version: 2.0.0 user-invocable: true
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.
---
Get back up to speed fast. Recap reads the most recent session file and recent decisions to tell you where you left off and what to do next.
1. **`.maestro/sessions/`** — read the most recent session file (by filename date) 2. **`.maestro/decisions.jsonl`** — read the last 5 decisions
If no session files exist, read the last 10 decisions and summarize those instead.
If no data exists at all, respond: *"No session history found. Run `/capture` at the end of your next session to start tracking."*
┌─────────────────────────────────────┐ │ LAST SESSION RECAP │ ├─────────────────────────────────────┤ │ Date: YYYY-MM-DD │ │ Commands: /diagnose → /fortify (2) │ │ Files: 3 changed, 1 created │ │ Outcome: Completed │ ├─────────────────────────────────────┤ │ PICK UP HERE: │ │ 1. Run /guard — rate limiting │ │ 2. Run /evaluate — adversarial tests│ └─────────────────────────────────────┘
After recapping, run the first command listed in "Pick Up Here" to continue where you left off.
**NEVER**:
Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.
Repo: sharpdeveye/maestro
Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token…
Use when porting a workflow to a different AI provider, deployment environment, model tier,…
Use when any Maestro command is invoked — provides foundational workflow design principles…
Use when the workflow works but needs to handle more complex cases or produce higher-quality…
Use when workflow components are inconsistent, naming conventions vary, or a new team…
Capture a session summary — what was done, what decisions were made, and what to do next.