Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →catlog22/maestro-session-seal
Seal current session with knowledge candidate review and DAG progression
Passed 13 of 18 test cases with the skill, and 3 of 18 without it.
and 17 more in the full report
12 fixed4 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
A session has no verify or review runs in its ledger. During readiness check, what warning code is emitted, and does it block session completion?
| Checked | Without skill | With skill |
|---|---|---|
| emits warning code W002 for missing verify run | Missed | Passed |
| allows session seal to continue without aborting on missing verify gate | Passed | Passed |
The instructions your model reads when the skill loads.
<required_reading>
@/.maestro/workflows/run-mode.md
@/.maestro/workflows/codex-run-mode.md
</required_reading>
If any required file above was not expanded into context by the host, or its content is no longer in context, Read it explicitly before executing any step.
Run completion already stages accepted decisions, locked constraints, and explicit maestro knowledge stage entries. This command reviews those receipts; it does not re-extract the same artifacts or write project knowledge through a second path.
Flags:
| Flag | Effect | Default |
|---|---|---|
--session <id> | Target session (slug or full ID) | active_session_id |
-y / --yes | Auto mode — skip confirmations | false |
--skip-knowledge | Leave candidate backlog pending and continue sealing | false |
Note: maestro-next suggests session-seal when 'Tests green + active session'. This command additionally requires verify/review gates (or W002 if absent). Both conditions should be met for clean seal.
--session flag or active_session_idmaestro session status --session {session_id} --json — verify status is open (a completed/archived Session is terminal)review step first")maestro knowledge review {session_id} --json. Treat its Run ledgers, reconciliation policies, diversified matches, and candidate IDs as authoritative; do not rescan outputs to recreate candidates. Use --refresh only when the review reports missing or stale source receipts.cited, validated, and contradicted are explicit Run relations.test cases passed, vs 3 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.