code-review
Review changed code against project standards. Checks for missing tests, dead code, type safety, lint issues, and coding…
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)
Claude Code
$ npx -y skills add vectorize-io/hindsight --skill hindsight-local --agent claude-code
Codex
$ npx skills add vectorize-io/hindsight --skill hindsight-local -a codex -y
Cursor
$ npx skills add vectorize-io/hindsight --skill hindsight-local -a cursor -y
Gemini CLI
$ npx skills add vectorize-io/hindsight --skill hindsight-local -a gemini-cli -y
GitHub Copilot
$ npx skills add vectorize-io/hindsight --skill hindsight-local -a github-copilot -y
OpenCode
$ npx skills add vectorize-io/hindsight --skill hindsight-local -a opencode -y
Windsurf
$ npx skills add vectorize-io/hindsight --skill hindsight-local -a windsurf -y
name: hindsight-local description: Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)
You have persistent memory via the `hindsight-embed` CLI. **Proactively store learnings and recall context** to provide better assistance.
Before using memory commands, verify Hindsight is configured:
uvx hindsight-embed daemon status
**If this fails or shows "not configured"**, run the interactive setup:
uvx hindsight-embed configure
This will prompt for an LLM provider and API key. After setup, the commands below will work.
When you call `retain`, Hindsight does **not** store the string as-is. The server runs an internal pipeline that:
1. **Extracts structured facts** from the content using an LLM 2. **Identifies entities** (people, tools, concepts) and links related facts 3. **Builds temporal and causal relationships** between facts 4. **Generates embeddings** for semantic search
This means you should pass **rich, full-context content** — the server is better at extracting what matters than a pre-summarized string. Your job is to decide **when** to store, not **what** to extract.
Use `memory retain` to store what you learn. Pass the full context — raw observations, session notes, conversation excerpts, or detailed descriptions:
uvx hindsight-embed memory retain default "User is working on a TypeScript project. They enabled strict mode and prefer explicit type annotations over inference." uvx hindsight-embed memory retain default "Ran the test suite with NODE_ENV=test. Tests pass. Without NODE_ENV=test, the suite fails with a missing config error." --context procedures uvx hindsight-embed memory retain default "Build failed on Node 18 with error 'ERR_UNSUPPORTED_ESM_URL_SCHEME'. Switched to Node 20 and build succeeded." --context learnings
You can also pass a raw conversation transcript with timestamps:
uvx hindsight-embed memory retain default "[2026-03-16T10:12:03] User: The auth tests keep failing on CI but pass locally. Any idea? [2026-03-16T10:12:45] Assistant: Let me check the CI logs. Looks like the tests are running without the TEST_DATABASE_URL env var set — they fall back to the production DB URL and hit a connection timeout. [2026-03-16T10:13:20] User: Ah right, I never added that to the CI secrets. Adding it now. [2026-03-16T10:15:02] User: That fixed it. All green now." --context learnings
Use `memory recall` BEFORE starting tasks to get relevant context:
uvx hindsight-embed memory recall default "user preferences for this project" uvx hindsight-embed memory recall default "what issues have we encountered before"
Use `memory reflect` to synthesize context:
uvx hindsight-embed memory reflect default "How should I approach this task based on past experience?"
**Always store** after you learn something valuable:
**Always recall** before:
1. **Store immediately**: When you discover something, store it right away 2. **Pass rich context**: Include full observations, not pre-summarized strings — the server extracts facts automatically 3. **Include outcomes**: Store what happened AND why, including failures and workarounds 4. **Recall first**: Always check for relevant context before starting work 5. **Use `--context` for metadata**: The `--context` flag labels the type of memory (e.g., `procedures`, `learnings`, `preferences`), not a replacement for full content
Review changed code against project standards. Checks for missing tests, dead code, type safety, lint issues, and coding…
Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub README, PR, issue or blog post. Use…
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version,…
Take a PR from review to merged — run the repo's code-review skill on it in a loop (review, fix, re-review) until nothing is left…
Triage a GitHub issue or a reported problem — check it is real and not by design (code, git history, PRs, Hindsight memory), find…
Long-term memory for the agent via Hindsight. Use to recall relevant past context before answering, retain durable facts as you…
Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude…
Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing…
Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing…