# Reflect

> Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

- Skill: `jtaroreh/reflect` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add jtaroreh/reflect`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jtaroreh/reflect/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: jtaroreh (https://skillmd.com/u/jtaroreh)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/jtaroreh/reflect

---


# Reflect

Mine the current conversation for durable learnings, then route them into skill edits.

## When to invoke

- The user said "reflect" or "/reflect".
- A complex task (5+ tool calls) just landed cleanly and the recipe is worth keeping.
- The agent hit dead ends, found the working path, and the path generalizes.
- The user corrected the agent's approach mid-task.
- A non-trivial workflow emerged that isn't captured anywhere.

Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.

## Process

### 1. Locate the active transcript

The parent finds its own transcript file before fanning out. Antigravity IDE chats live under `~/.gemini/antigravity-ide/brain/<conversation-id>/`. Prefer `.system_generated/logs/transcript.jsonl` or `transcript_full.jsonl`. The current session's `transcriptPath` is authoritative. Do not glob across `~/.cursor/projects/*/`.

```bash
ls -t ~/.gemini/antigravity-ide/brain/*/.system_generated/logs/transcript.jsonl ~/.gemini/antigravity/brain/*/.system_generated/logs/transcript.jsonl 2>/dev/null | head -10
```

Three transcript layouts: legacy flat (`<id>.jsonl`), current nested (`<id>/<id>.jsonl`), and subagent (`<parent>/subagents/<child>.jsonl`).

For each candidate, read the first JSONL line and check that `message.content[0].text` contains the conversation's opening user prompt. Take the matching path. If no path resolves, write a tight digest of the session and pass that instead.

### 2. Spawn three reviewers in parallel

Spawn three subagents in a single `invoke_subagent` turn, `TypeName: "self"` (or `"poteto-agent"`), explicit `Model: "pro"`, `Workspace: "inherit"`. Reviewers need MCP access for context lookups (tickets, chat threads, observability traces referenced in the transcript). The prompt forbids file writes; the parent applies edits.

| Lens | `Model` | Prompt template |
|---|---|---|
| Judgment | your configured reflect-judgment model (default `pro`) | `references/judgment-reviewer.md` |
| Tooling | your configured reflect-tooling model (default `pro`) | `references/tooling-reviewer.md` |
| Divergent | your configured reflect-judgment model (default `pro`) | `references/divergent-reviewer.md` |

Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in their subagent response body.

### 3. Synthesize

Spawn one subagent via `invoke_subagent`: `TypeName: "self"` (or `"poteto-agent"`), `Role: "Reflect Synthesizer"`, using your configured reflect-judgment model (default `pro`), `Workspace: "inherit"`. The synthesizer's quality check includes spot-verifying citations. Use `references/synthesizer.md` verbatim, with each reviewer's full output inlined where marked. The synthesizer returns a structured Accepted / Rejected / Backlog list.

### 4. Structural enforcement check

Sanity-check the synthesizer's Accepted list. For any item that would be enforced more reliably by a lint rule, script, metadata flag, or runtime check, move it from Accepted to Backlog. The synthesizer already applies this criterion; this is a final pass before edits land. See the **encode-lessons-in-structure** principle skill.

### 5. Apply

Before applying any Accepted edit, present the synthesizer's full Accepted/Rejected/Backlog output to the user and wait for explicit approval. The user picks which subset to apply and may redirect routings. Skill changes affect every future agent in the org; do not auto-apply.

Backlog items file to whatever devex / backlog tracker your team uses automatically. Those are tracker submissions, not skill edits. Only the Accepted list waits for approval.

For each approved Accepted item, follow the Routing field exactly:

- Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): parent does directly.
- Substantive existing-skill edit (a new section, a new pattern table, more than ~10 lines): draft the new section following the unslop skill and validate frontmatter/links.
- `tune description: <skill path>` (the skill exists but didn't trigger when it should have): update the YAML frontmatter `description` scalar with precise trigger keywords.
- `new skill: <kebab-name>`: create a new skill directory under `.agents/skills/<kebab-name>/SKILL.md` (or in this plugin) with valid YAML frontmatter.

If your environment ships a SKILL.md validator, run it on every touched skill before declaring done. Skip this step if it doesn't.

### 6. Summarize for the user

Short list, no preamble:

- Edits applied: `<skill path>`. What changed, one line each.
- New skills created: `<skill path>`. One line each (rare).
- Backlog filed to the devex tracker: `<issue title>` (`<tags>`). One line each.
- Dropped: one line per rejected finding + reason from the synthesizer.