code-review
Review changed code against project standards. Checks for missing tests, dead code, type…
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
$ npx -y skills add vectorize-io/hindsight --skill memory-retain --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/memory-retainContext preview
The summary Claude sees to decide when to auto-load this skill.
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
name: memory-retain description: Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
Memory is only useful if the next run can find it. Save the outcome and the reason, not a transcript.
1. Decide where it belongs:
2. Write a short, self-contained note that makes sense with no other context: what happened or was decided, who decided it, when, and why. "On 3 Oct the user chose Vendor B over Vendor A because A has no EU data residency" beats "user picked B". 3. Call `retain` with that note as `content`, and `tags` of `source:grok-bot` and `bot:<bot-name>`.
Repo: vectorize-io/hindsight
Review changed code against project standards. Checks for missing tests, dead code, type…
Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub…
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to…
Take a PR from review to merged — run the repo's code-review skill on it in a loop (review,…
Long-term memory for the agent via Hindsight. Use to recall relevant past context before…
Create a new Hindsight-powered subagent with long-term memory. Use when the user wants a…