reflect

name	reflect
description	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.
disable-model-invocation	true

When to use

• the user says reflect

On-demand loading: Read this file when the task matches the triggers below.

Activation: Use this skill when the user says "reflect" or "/reflect", or after a complex task to mine learnings and route them into skill edits. Do NOT use for trivial, off-topic conversations, or sessions already fully covered by existing skills followed correctly.

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. The system prompt names the active workspace's agent-transcripts/ directory; use that path. Do not glob across ~/.cursor/projects/*/. That crosses workspace boundaries and reads private chats from unrelated projects.

ls -t <agent-transcripts>/*.jsonl <agent-transcripts>/*/*.jsonl <agent-transcripts>/*/subagents/*.jsonl 2>/dev/null | head -10

Three transcript layouts: legacy flat (.jsonl), current nested ( /.jsonl), and subagent ( /subagents/.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

One message, three Task calls, subagent_type: generalPurpose, explicit model: on each, agent mode (readonly: false). Reviewers need MCP access for context lookups (tickets, chat threads, observability traces referenced in the transcript); readonly strips MCPs. The prompt forbids file writes; the parent applies edits.

Lens	model	Prompt template
Judgment	claude-opus-4-8-thinking-xhigh	references/judgment-reviewer.md
Tooling	composer-2.5-fast	references/tooling-reviewer.md
Divergent	claude-opus-4-8-thinking-xhigh	references/divergent-reviewer.md

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

3. Synthesize

One Task call, subagent_type: generalPurpose, model: claude-opus-4-8-thinking-xhigh, agent mode (readonly: false). The synthesizer's quality check includes spot-verifying citations, which can require MCP access; readonly strips MCPs. 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): hand to Cursor's built-in create-skill skill and run its draft / test / iterate loop.
• tune description: (the skill exists but didn't trigger when it should have): hand to create-skill and run its description-optimization loop.
• new skill via create-skill: : hand creation to create-skill. Do not invent the shape ad hoc.

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: . What changed, one line each.
• New skills created: . One line each (rare).
• Backlog filed to the devex tracker: ( ). One line each.
• Dropped: one line per rejected finding + reason from the synthesizer.

Related skills

• what-did-i-get-done: recap of shipped commits over a custom time range; prefer it when the goal is a status update, not mining learnings
• weekly-review: fixed weekly recap of shipped work classified by bugfix / tech debt / net-new; prefer it for retros and planning summaries
• workflow-from-chats: mines multiple past chats for durable preferences; prefer it for cross-session preference extraction rather than one transcript's learnings