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.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
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.
Use the active environment's transcript or conversation-history interface to identify this conversation. Read only its evidence. If a complete transcript is unavailable, pass a tight digest of the accessible session instead. State its coverage limits and do not invent missing turns or present the digest as a complete transcript. Keep any intermediate digests and review artifacts under .agents-state.
Delegate to three reviewers with independent judgment, tooling and divergent lenses. Follow the delegation instructions in AGENTS.md. Run them in parallel where capacity permits; if capacity is limited, batch the work without dropping a lens. Give them the session evidence and read access to the referenced context sources. They return findings without modifying files, skills or external records.
| Lens | Prompt template |
|---|---|
| Judgment | references/judgment-reviewer.md |
| Tooling | references/tooling-reviewer.md |
| Divergent | references/divergent-reviewer.md |
Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in their response bodies. Pass along any evidence-coverage limits.
Delegate to a separate synthesizer following AGENTS.md. It may spot-verify citations using available read-only context tools. Pass references/synthesizer.md verbatim, with each reviewer's full output inlined where marked, plus any evidence-coverage limits. It returns an Accepted / Rejected / Backlog list without modifying files or external records.
Move any Accepted item that a Haskell type, owning API, lint rule, script, metadata flag, or runtime check would enforce more reliably to Backlog. See the encode-lessons-in-structure principle skill.
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 future runs that use those skills. 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:
tune description: <skill path> (the skill exists but didn't trigger when it should have): use the available skill-authoring capability to improve the description and validate its triggering behavior with the facilities it provides.new skill: <kebab-name>: use the available skill-authoring capability. Do not invent the shape ad hoc.If your environment ships a SKILL.md validator, run it on every touched skill before declaring done. Report any unavailable or unsupported checks; do not claim they passed.
Short list, no preamble:
<skill path>. What changed, one line each.<skill path>. One line each (rare).<issue title> (<tags>). One line each.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
The English summary is being prepared. Showing the original description.
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
The English summary is being prepared. Showing the original description.
Inspect or supervise a PR or stack through review and CI to merge-ready, using current GitHub evidence and the requested mode.
The English summary is being prepared. Showing the original description.
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you benchmark or report a measured speedup or regression, including complete framework flows and compilation of projects that consume the framework.
The English summary is being prepared. Showing the original description.
Restate the last message in plain human language, with no jargon.
The English summary is being prepared. Showing the original description.
Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.
The English summary is being prepared. Showing the original description.