Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →elianiva/reflect
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
Passed 8 of 15 test cases with the skill, and 6 of 15 without it.
and 3 more in the full report
5 fixed9 passed either way11 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the reflection workflow, which agent is responsible for making approved skill file edits to the codebase?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies that the parent agent applies skill file edits. | Missed | Passed |
The instructions your model reads when the skill loads.
Mine the current conversation for durable learnings, then route them into skill edits.
Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.
The active transcript is $PI_SESSION_FILE. Use it directly when present. To choose an earlier transcript for this working directory, call pstack_sessions with action: "list" and read only a returned path. Never glob Pi's global session directory. If no session file resolves, write a tight digest of the current session and pass that instead.
One parallel subagent call with three tasks, each using agent: "poteto-agent", role: "reflect judgment, divergent, synthesizer", and a prompt that forbids file writes. Reviewers may use MCPs available to their Pi child process for cited context lookups. The parent applies edits.
| Lens | model | Prompt template |
|---|---|---|
| Judgment | your configured reflect-judgment model (default inherit-parent) | references/judgment-reviewer.md |
| Tooling | your configured reflect-tooling model (default inherit-parent) | references/tooling-reviewer.md |
| Divergent | your configured reflect-judgment model (default inherit-parent) | references/divergent-reviewer.md |
Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the subagent result.
One subagent call using agent: "poteto-agent" and role: "reflect judgment, divergent, synthesizer". The synthesizer may use MCPs available to its Pi child process to spot-check citations. Use references/synthesizer.md verbatim, with each reviewer's full output inlined where marked. The synthesizer returns a structured Accepted / Rejected / Backlog list.
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.
test cases passed, vs 6 / 15 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.