Skip to content

Jrecos/omp-pstack / skills/reflect

reflect

Verified

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.

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, the parent resolves this conversation's JSONL transcript in the current session directory. Pass its absolute path to every reviewer. Do not glob across other sessions or workspaces. That reads private chats unrelated to this session. If no path resolves, pass a tight digest of the session instead.

2. Spawn three reviewers in parallel

Spawn three reviewers in one native task batch. Resolve each descriptor through pstack_agent and pass only its returned agent. The returned model is metadata, not a native task field. Use kind: "general" because reviewers need MCP access for tickets, chat threads, and traces. The readonly kind strips MCPs. The prompt forbids file writes. The parent applies edits.

Each reviewer and the synthesizer use the configured role in rules/pstack-models.md, managed by pstack_models through /setup-pstack. If a role is unset or its model is unavailable, run /setup-pstack. Never substitute another model. inherit-parent and auto resolve to the live parent model through the returned agent.

Lenspstack_agent rolePrompt template
Judgmentreflect judgment, divergent, synthesizerreferences/judgment-reviewer.md
Toolingreflect toolingreferences/tooling-reviewer.md
Divergentreflect judgment, divergent, synthesizerreferences/divergent-reviewer.md

Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the task result.

3. Synthesize

Resolve pstack_agent with role: "reflect judgment, divergent, synthesizer" and kind: "general". Dispatch one native task with the returned agent. The synthesizer's citation spot-checks can need MCP access, which readonly strips. Pass references/synthesizer.md verbatim, with each reviewer's full output filled in. 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.

Never edit an installed plugin copy or a skill under plugins/cache/. Before approval, resolve and show the source checkout and skill path. For package-owned skills, edit that source checkout after approval. For project or personal skills, use their existing .agents/skills/ or .omp/skills/ source according to skills/poteto-mode/references/omp-create-skill.md. Do not copy a package skill into a shadowing local override. Never open a PR or push.

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 packaged OMP skill-authoring guidance (skills/poteto-mode/references/omp-create-skill.md) and run its draft / test / iterate loop.
  • tune description: <skill path> (the skill exists but didn't trigger when it should have): hand to that guidance and run its description-optimization loop.
  • new skill via create-skill: <kebab-name>: hand creation to that guidance. 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.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall