/deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
Claude Code
$ npx -y skills add vshulcz/deja-vu --skill deja-reflect --agent claude-code
Codex
$ npx skills add vshulcz/deja-vu --skill deja-reflect -a codex -y
Cursor
$ npx skills add vshulcz/deja-vu --skill deja-reflect -a cursor -y
Gemini CLI
$ npx skills add vshulcz/deja-vu --skill deja-reflect -a gemini-cli -y
GitHub Copilot
$ npx skills add vshulcz/deja-vu --skill deja-reflect -a github-copilot -y
OpenCode
$ npx skills add vshulcz/deja-vu --skill deja-reflect -a opencode -y
Windsurf
$ npx skills add vshulcz/deja-vu --skill deja-reflect -a windsurf -y
SKILL.md
deja-reflect.SKILL.mdname: deja-reflect
description: End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
metadata:
openclaw:
homepage: https://vshulcz.github.io/deja-vu/
requires:
bins:
- deja
install:
- kind: brew
formula: deja-vu
bins: [deja]
- kind: node
package: "@vshulcz/deja-vu"
bins: [deja]Run an end-of-session reflection over the current task and record only durable, non-obvious project facts in deja-vu.
Workflow
1. **Inspect what was already recorded or hit in this project:**
- Run `deja notes` to check existing promoted decisions so you do not duplicate or contradict an active rule. (If `deja` is not on PATH, run `npx -y @vshulcz/deja-vu ...`.)
- Run `deja friction` to see recurring command failures across sessions.
2. **Distill durable findings from this session:**
- Keep: architectural invariants, required flags/commands that were non-obvious, rejected approaches and why they failed, user-stated project rules.
- Skip: anything already obvious from reading the code, temporary debugging steps, or one-off typos.
3. **Confirm with the user before writing:**
- Present the 1–3 concise one-line facts you propose to store.
- Once confirmed, store each via the `deja` MCP tool (`mode: "remember"`) or in the shell:
deja remember "<concise self-contained decision and why>" --tag <topic>
- If an older note was superseded by today's work, mark it with `deja promote <id> --state superseded --note "<what replaced it>"`.
Read more
name: deja-reflect
description: End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
metadata:
openclaw:
homepage: https://vshulcz.github.io/deja-vu/
requires:
bins:
- deja
install:
- kind: brew
formula: deja-vu
bins: [deja]
- kind: node
package: "@vshulcz/deja-vu"
bins: [deja]Run an end-of-session reflection over the current task and record only durable, non-obvious project facts in deja-vu.
Workflow
1. **Inspect what was already recorded or hit in this project:**
- Run `deja notes` to check existing promoted decisions so you do not duplicate or contradict an active rule. (If `deja` is not on PATH, run `npx -y @vshulcz/deja-vu ...`.)
- Run `deja friction` to see recurring command failures across sessions.
2. **Distill durable findings from this session:**
- Keep: architectural invariants, required flags/commands that were non-obvious, rejected approaches and why they failed, user-stated project rules.
- Skip: anything already obvious from reading the code, temporary debugging steps, or one-off typos.
3. **Confirm with the user before writing:**
- Present the 1–3 concise one-line facts you propose to store.
- Once confirmed, store each via the `deja` MCP tool (`mode: "remember"`) or in the shell:
deja remember "<concise self-contained decision and why>" --tag <topic>
- If an older note was superseded by today's work, mark it with `deja promote <id> --state superseded --note "<what replaced it>"`.
Shared local memory, session history search, cross-agent handoff, and uncommitted code recovery across 46 coding agents — Claude Code, Codex, Cursor, OpenCode, Gemini CLI, OpenClaw & more (CLI & MCP). One Go binary, zero LLM calls.
Other skills on deja-vu.
More skills from other plugins.
agent-cost-report
Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude…
bot-handoff
Keep a durable record of work passed between Bots in the shared Hindsight memory bank. Use when handing work to another Bot, when…
mempalace
Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing…
mempalace
Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing…
Questions about deja-reflect.
- Which coding agents can use deja-reflect?
- deja-reflect installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.

