Menu
Extract and save learnings from a completed knowledge work session. Saves to docs/knowledge/ so future plans automatically find them.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Brain dump and compile knowledge before structuring a plan. Use when starting any non-trivial knowledge work — after a meeting, when tackling a new problem, or when you need to pull together what you know before planning.
Gut-check what you know and don't know before proceeding. Use at any point to assess confidence, surface gaps, and decide whether to proceed or dig deeper.
Research past work and structure a knowledge work plan. Use when starting strategy docs, campaign plans, content briefs, research synthesis, or operational playbooks.
Multi-reviewer quality check for knowledge work. Runs strategic alignment and data accuracy reviewers on plans, briefs, and strategy docs.
Execute a knowledge work plan. Break it into tasks, do the work, and track what happened. Use after planning to actually produce the deliverables.
| name | kw:compound |
| description | Extract and save learnings from a completed knowledge work session. Saves to docs/knowledge/ so future plans automatically find them. |
Close the loop. Extract what you learned and save it where future work will find it.
After completing a plan, campaign, analysis, or strategy session
"Compound this session", "Save what we learned", "What should we remember?"
After a data correction, process fix, or strategic insight
At the end of any meaningful work session
Scan the current session for compoundable insights. Look for:
| Type | Signals |
|---|---|
| Insight | "We discovered...", surprising finding, counter-intuitive result |
| Playbook | Repeatable process that worked, step-by-step that others could follow |
| Correction | Wrong assumption fixed, data source clarified, definition updated |
| Pattern | Something that keeps recurring, systemic observation |
Extract 1-3 learnings max. Quality over quantity. If nothing is worth saving, say so:
"Nothing from this session seems worth saving as a standalone learning. The work is captured in the plan/deliverables."
For each learning, draft:
**Learning:** [One sentence — what we now know]
**Type:** [insight | playbook | correction | pattern]
**Why it matters:** [One sentence — how this changes future work]
Present the drafted learnings and ask:
"Found [N] learnings worth saving. Review and approve?"
Show each learning with its classification. User can:
Approve as-is
Edit the wording
Skip individual learnings
Add learnings you missed
Do not save anything without approval.
For each approved learning, search existing knowledge:
Grep: [key phrases] in docs/knowledge/
Grep: [key phrases] in docs/solutions/
If a similar learning already exists:
Show the existing entry
Ask: "Update existing or save as new?"
If updating, edit the existing file
After identifying what to save, launch the stale knowledge checker:
Launch Task agent: compound-knowledge:research:stale-knowledge-checker
If stale entries are found, present them to the user:
"This new learning may conflict with existing knowledge:
- [existing file] says [X], but the new learning says [Y]
- Recommendation: [Update / Remove / Keep both]
Want me to update the old entry?"
<critical_requirement> Agents return TEXT only. They must NOT write or delete files. Only the orchestrating compound skill writes files — both new learnings and updates to stale entries. </critical_requirement>
Write each learning to docs/knowledge/:
Filename: docs/knowledge/{descriptive-slug}.md
Create the directory if it doesn't exist: mkdir -p docs/knowledge/
File format:
---
type: [insight | playbook | correction | pattern]
tags: [relevant keywords for future search]
confidence: [high | medium | low]
created: [today's date]
source: [brief description of what triggered this]
---
# [Learning Title]
[2-4 sentences explaining the learning. Be specific enough that someone reading this in 3 months understands what happened and why it matters.]
## Context
[What you were doing when you discovered this.]
## Implication
[How this should change future work. Be concrete: "When doing X, always check Y first."]
## Compounded
**Saved:**
- docs/knowledge/{filename}.md
**This learning will be surfaced by /kw:plan** when future work touches:
- [list the tags that would trigger retrieval]
Use AskUserQuestion:
Question: "Learnings saved. What next?"
Options:
/kw:plan — Start a new planning cycle (the learnings will be found)1-3 learnings max per session. If you're saving 5 things, you're not filtering enough.
Approval required. Never auto-save. The user decides what's worth remembering.
Be specific. "Use the right data source" is useless. "Revenue metrics come from [specific dashboard], not [other source] which overcounts by ~$X" is useful.
Duplicates are waste. Always check before creating. Update existing entries when possible.
Confidence matters. Mark low if based on one data point. Mark high if verified across multiple sessions or with data.
Tags are for retrieval. Choose tags that /kw:plan's grep search would match on. Think: "What future question would this answer?"
When invoked with disable-model-invocation context (e.g., from an orchestrator or automation):