Reflect
Mine the current conversation for durable learnings, then route them into skill edits.
Invoke when the user says "reflect" or "/reflect". Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.
1. Locate the active transcript
Before fanning out, find this conversation's transcript under ~/.claude/projects/<slug>/, where <slug> is the workspace's absolute path with every / and . turned into - (so /home/you/proj becomes -home-you-proj). Do not glob across ~/.claude/projects/*/. That crosses workspace boundaries and reads private chats from unrelated projects.
bashls -t ~/.claude/projects/<slug>/*.jsonl ~/.claude/projects/<slug>/*/subagents/*.jsonl 2>/dev/null | head -10
That covers the session (<id>.jsonl) and subagent (<parent>/subagents/agent-<child>.jsonl) layouts. For each candidate, read the first JSONL line. Take the file whose message.content[0].text contains the conversation's opening user prompt. If none matches, pass a tight digest of the session instead.
2. Spawn three reviewers in parallel
One message, three Agent tool calls, subagent_type: "general-purpose". Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references, and the general-purpose agent keeps it.
Each reviewer and the synthesizer name a role from the model table in the poteto-mode skill.
| Lens | Role | model | Prompt template |
|---|---|---|---|
| Judgment | reflect judgment, divergent, synthesizer | inherit the parent (omit) | references/judgment-reviewer.md |
| Tooling | reflect tooling | sonnet | references/tooling-reviewer.md |
| Divergent | reflect judgment, divergent, synthesizer | inherit the parent (omit) | references/divergent-reviewer.md |
Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in their final report.
3. Synthesize
One Agent tool call, subagent_type: "general-purpose", no model (the reflect judgment, divergent, synthesizer role inherits the parent). It spot-verifies citations through MCP. Pass references/synthesizer.md verbatim, with each reviewer's full output inlined where marked. It returns an Accepted / Rejected / Backlog list.
4. Structural enforcement check
Move any Accepted item that a lint rule, script, metadata flag, or runtime check would enforce more reliably to Backlog. See the encode-lessons-in-structure principle skill.
5. Apply
Present the synthesizer's full Accepted / Rejected / Backlog output and wait for explicit approval before applying any Accepted edit. The user picks the subset and may redirect routings. Skill changes affect every future agent in the org. Do not auto-apply.
File each Backlog item to your team's devex or backlog tracker without waiting. Only the Accepted list waits for approval.
Follow each approved row's Routing exactly:
- Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): the parent does it directly.
- Substantive existing-skill edit (a new section, a new pattern table, more than ~10 lines): hand to the
skill-creatorskill and run its draft / test / iterate loop. tune description: <skill path>(the skill exists but didn't trigger when it should have): hand toskill-creatorand run its description-optimization loop.new skill via skill-creator: <kebab-name>: hand creation toskill-creator. Do not invent the shape ad hoc.
If your environment ships a SKILL.md validator, run it on every touched skill before declaring done.
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.
