Menu
Capture learnings from the workflow into reusable documentation. Stage 7 of the development workflow.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | workflows-compound |
| description | Capture learnings from the workflow into reusable documentation. Stage 7 of the development workflow. |
| argument-hint | [optional focus area] |
| user-invocable | true |
Capture learnings from the current workflow: $ARGUMENTS
You are executing Stage 7 (Compound) of the development workflow. Implementation is reviewed and revised. Your job is to extract reusable learnings from this workflow and persist them so future workflows benefit. You are NOT writing code — you are documenting what was learned.
Before starting, verify:
.workflow/state.json exists and currentStage is "compound"stages.review.status is "completed")If pre-conditions are not met, report what's missing and halt.
Read all workflow artifacts:
.workflow/state.json — timeline, iterations, stage notes.workflow/summaries/*.md — what was built.workflow/review-report.md — what was foundgit log --oneline --since="$(jq -r .startedAt .workflow/state.json)" -- .
Identify three categories of learnings:
Solutions — Reusable patterns for solving specific problems:
Discoveries — Things learned about the codebase or domain:
Process — What worked or didn't in the workflow itself:
If a reusable solution was produced, write it to docs/solutions/:
# <Problem Title>
## Problem
[What problem this solves, in 2-3 sentences]
## Solution
[The approach that worked, with code references]
## Context
- Workflow: <id>
- Spec: <path>
- Date: <ISO date>
## Key Decisions
- [Decision 1]: [Why this choice was made]
- [Decision 2]: [Why this choice was made]
## What Didn't Work
- [Approach that was tried and abandoned, with brief explanation]
## Related
- [Links to specs, ADRs, or other solutions]
If significant patterns or discoveries should persist across sessions:
Update workflow state (.workflow/state.json):
stages.compound.status to "completed"stages.compound.completedAt to current ISO timestampstages.compound.artifacts.solution to the solution doc path (if created)currentStage to "reflection"updatedAtPresent the handoff:
COMPOUND COMPLETE
==================
Solutions captured: N
Discoveries: N
Process notes: N
Solution doc: <path or "none — no reusable pattern identified">
Next: Stage 8 - Reflection (/workflow-reflection)
A learning is worth capturing if it meets ANY of these:
A learning is NOT worth capturing if:
A-Mem thought evolution — check which prior thoughts should be updated when a significant new insight arrives. Spawns a lightweight subagent to classify prior thoughts as UPDATE or NO_UPDATE, then applies revisions. Use during long reasoning sessions when you reach a synthesis, make a decision, or discover something that changes earlier assumptions. Triggers on "this changes what I thought earlier", "update prior reasoning", "evolve thoughts", or automatically on conclusion/synthesis thoughts in sessions >10 thoughts.
Cross-session knowledge retrieval from the Thoughtbox knowledge graph. Searches entities, traverses relations, retrieves observations, and synthesizes findings from past sessions. Use when you need to recall prior decisions, check what's already known about a topic, find related insights, or build on past work. Triggers on "what do we know about", "have we seen this before", "recall", "prior decisions about", "knowledge graph", or when starting work that might have prior context.
Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.
Write or improve prompts for Codex using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.
Generate architecture diagrams for a codebase subsystem or module. Explores source files and produces Mermaid diagrams in docs/.
Extract reusable principles and decision frameworks from accumulated experience. Use after significant work sessions, project milestones, or when you notice recurring patterns worth codifying.