reflect

# Reflect Read [runtime](../runtime/SKILL.md) for host-specific tools and paths. Mine the current conversation for durable learnings, then route them into skill edits. ## When to invoke 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. ## Process ### 1. Locate the active transcript The parent finds its own transcript file before fanning out. Use the active workspace's transcript source exposed by the host. Do not glob across `unrelated workspace transcript stores`. That crosses workspace boundaries and reads private chats from unrelated projects. Read the scoped transcript source or exported files from the runtime skill. Match this conversation by its opening user prompt and source ID. If no source resolves, write a tight digest of the session and pass that instead. ### 2. Spawn three reviewers in parallel One message, three delegation calls, each a general-purpose agent, with `model` set as below, read-only investigation with the required MCP tools enabled. Reviewers need MCP access for context lookups (tickets, chat threads, observability traces referenced in the transcript). Each reviewer and the synthesizer name a role line in the `models.md` rule and a default. Set `model` to that line's value, or to the default if the rule or the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the host rejects a model, follow the runtime skill's model fallback rules. | Lens | Role line | Default `model` | Prompt template | |---|---|---|---| | Judgment | `reflect judgment, divergent, synthesizer` | `inherit-parent` | `references/judgment-reviewer.md` | | Tooling | `reflect tooling` | `inherit-parent` | `references/tooling-reviewer.md` | | Divergent | `reflect judgment, divergent, synthesizer` | `inherit-parent` | `references/divergent-reviewer.md` | Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the delegation result. ### 3. Synthesize One delegation call, a general-purpose agent, with `model` from the `reflect judgment, divergent, synthesizer` line (default `inherit-parent`), read-only investigation with the required MCP tools enabled. The synthesizer's quality check includes spot-verifying citations, which can require MCP access. 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. 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. 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 the bundled `create-skill` skill and run its draft / test / iterate loop. - `tune description: <skill path>` (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: <kebab-name>`: 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: `<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.