Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sediman-agent/reflect
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
Passed 6 of 16 test cases with the skill, and 3 of 16 without it.
and 5 more in the full report
7 fixed3 passed either way14 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
An accepted finding requires adding a comprehensive 25-line troubleshooting table and edge-case section to `skills/deploy/SKILL.md`. Should the parent process edit this file directly or delegate it?
| Checked | Without skill | With skill |
|---|---|---|
| Delegates multi-line substantive skill additions to the create-skill skill | 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 parent finds its own transcript file before fanning out. The system prompt names the active workspace's agent-transcripts/ directory; use that path. Do not glob across ~/.cursor/projects/*/. That crosses workspace boundaries and reads private chats from unrelated projects.
ls -t <agent-transcripts>/*.jsonl <agent-transcripts>/*/*.jsonl <agent-transcripts>/*/subagents/*.jsonl 2>/dev/null | head -10
Three transcript layouts: legacy flat (<id>.jsonl), current nested (<id>/<id>.jsonl), and subagent (<parent>/subagents/<child>.jsonl).
For each candidate, read the first JSONL line and check that message.content[0].text contains the conversation's opening user prompt. Take the matching path. If no path resolves, write a tight digest of the session and pass that instead.
One message, three Task calls, subagent_type: generalPurpose, explicit model: on each, agent mode (readonly: false). Reviewers need MCP access for context lookups (tickets, chat threads, observability traces referenced in the transcript); readonly strips MCPs. The prompt forbids file writes; the parent applies edits.
| Lens | model | Prompt template |
|---|---|---|
| Judgment | claude-opus-4-8-thinking-xhigh | references/judgment-reviewer.md |
| Tooling | composer-2.5-fast | references/tooling-reviewer.md |
| Divergent | claude-opus-4-8-thinking-xhigh | references/divergent-reviewer.md |
Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the Task response body.
test cases passed, vs 3 / 16 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.