/capture
Capture a session summary — what was done, what decisions were made, and what to do next.
$ npx -y skills add sharpdeveye/maestro --skill capture --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/capture
Context preview
The summary Claude sees to decide when to auto-load this skill.
Capture a session summary — what was done, what decisions were made, and what to do next.
SKILL.md
capture.SKILL.mdname: capture
description: "Capture a session summary — what was done, what decisions were made, and what to do next."
argument-hint: "[session topic]"
category: utility
version: 2.0.0
user-invocable: true
MANDATORY PREPARATION
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.
---
Capture the current session's work into a persistent summary. This creates a record that survives session boundaries — future commands can reference what happened here.
What to Capture
Read the conversation history and identify:
1. **Commands run** — which Maestro commands were invoked and in what order 2. **Decisions made** — architectural choices, trade-offs accepted, patterns adopted 3. **Files changed** — what was created, modified, or deleted 4. **Issues found** — bugs, gaps, or risks identified 5. **Next steps** — what should happen next (be specific)
Output Format
Generate a session summary file at `.maestro/sessions/{date}_{topic}.md`:
# Session: {topic}
Date: {YYYY-MM-DD}
## Commands Run
- /diagnose → Score: 18/25
- /fortify → Added retry logic to API handlers
- /evaluate → Verified with 3 test scenarios
## Decisions
- Chose retry-with-backoff over circuit breaker (simpler, sufficient for current load)
- Kept synchronous error handling (async not justified yet)
## Files Changed
- `src/api/handler.ts` — added retry wrapper
- `src/middleware/auth.ts` — added input validation
- `tests/api.test.ts` — new test file
## Open Issues
- Rate limiting not yet implemented (deferred to next session)
## Next Steps
1. Run `/guard` to add rate limiting
2. Run `/evaluate` with adversarial test casesAlso append a decision entry to `.maestro/decisions.jsonl` recording this capture.
Session Capture Checklist
- [ ] All commands from this session listed
- [ ] Key decisions documented with rationale
- [ ] Files changed listed with brief descriptions
- [ ] Open issues captured (nothing lost)
- [ ] Next steps are specific and actionable
- [ ] Summary saved to `.maestro/sessions/`
Recommended Next Step
After capturing, your next session should start with `/recap` to restore context, then proceed with the next steps listed above.
**NEVER**:
- Store raw prompts or full LLM outputs in the session file
- Overwrite an existing session file — create a new one
- Skip the "Next Steps" section — this is what makes capture valuable
- Capture without reading the conversation history first
- Auto-capture without the user invoking this command
Read more
name: capture description: "Capture a session summary — what was done, what decisions were made, and what to do next." argument-hint: "[session topic]" category: utility version: 2.0.0 user-invocable: true
MANDATORY PREPARATION
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.
---
Capture the current session's work into a persistent summary. This creates a record that survives session boundaries — future commands can reference what happened here.
What to Capture
Read the conversation history and identify:
1. **Commands run** — which Maestro commands were invoked and in what order 2. **Decisions made** — architectural choices, trade-offs accepted, patterns adopted 3. **Files changed** — what was created, modified, or deleted 4. **Issues found** — bugs, gaps, or risks identified 5. **Next steps** — what should happen next (be specific)
Output Format
Generate a session summary file at `.maestro/sessions/{date}_{topic}.md`:
# Session: {topic}
Date: {YYYY-MM-DD}
## Commands Run
- /diagnose → Score: 18/25
- /fortify → Added retry logic to API handlers
- /evaluate → Verified with 3 test scenarios
## Decisions
- Chose retry-with-backoff over circuit breaker (simpler, sufficient for current load)
- Kept synchronous error handling (async not justified yet)
## Files Changed
- `src/api/handler.ts` — added retry wrapper
- `src/middleware/auth.ts` — added input validation
- `tests/api.test.ts` — new test file
## Open Issues
- Rate limiting not yet implemented (deferred to next session)
## Next Steps
1. Run `/guard` to add rate limiting
2. Run `/evaluate` with adversarial test casesAlso append a decision entry to `.maestro/decisions.jsonl` recording this capture.
Session Capture Checklist
- [ ] All commands from this session listed
- [ ] Key decisions documented with rationale
- [ ] Files changed listed with brief descriptions
- [ ] Open issues captured (nothing lost)
- [ ] Next steps are specific and actionable
- [ ] Summary saved to `.maestro/sessions/`
Recommended Next Step
After capturing, your next session should start with `/recap` to restore context, then proceed with the next steps listed above.
**NEVER**:
- Store raw prompts or full LLM outputs in the session file
- Overwrite an existing session file — create a new one
- Skip the "Next Steps" section — this is what makes capture valuable
- Capture without reading the conversation history first
- Auto-capture without the user invoking this command
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
Other skills on maestro.
- /accelerate
Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.
Open skill - /adapt-workflow
Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.
Open skill - /agent-workflow
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.
Open skill - /amplify
Use when the workflow works but needs to handle more complex cases or produce higher-quality output through better tools, context, prompts, or models.
Open skill - /calibrate
Use when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.
Open skill - /chain
Use when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.
Open skill

