Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/reconcile
Use this skill when the user wants to reconcile learnings into rules, run /reconcile, propose rules from learnings, turn learnings into .claude/rules/ entries, or review what rules would be generated from current session learnings. On-demand version of session-end Phase 3.6.8.
Passed 17 of 19 test cases with the skill, and 5 of 19 without it.
and 15 more in the full report
15 fixed5 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
When `.orchestrator/config.json` lacks a explicit `reconcile` section, what default parameters must be used for the confidence threshold, minimum rule duration, insight character limit, and proposal volume ceiling?
| Checked | Without skill | With skill |
|---|---|---|
| Applies a confidence floor default of 0.5 | Missed | Passed |
| Applies a minimum rule duration default of 7 days | Passed | Passed |
| Applies a maximum proposals limit default of 10 | Passed | Passed |
The instructions your model reads when the skill loads.
Platform Note: State files use the platform's native directory:
.claude/(Claude Code),.codex/(Codex CLI), or.cursor/(Cursor IDE). Shared metrics live in.orchestrator/metrics/. Seeskills/_shared/platform-tools.md.
On-demand version of the session-end Phase 3.6.8 reconciliation flow. Turns eligible learnings
from .orchestrator/metrics/learnings.jsonl into proposed .claude/rules/<slug>.md entries,
presenting each batch of 4 to the coordinator via AUQ multiSelect for operator approval before
any file is written. Advisory-only — rules are NEVER auto-applied.
emitter.mjs) throws
on any eligible learning that would produce an alwaysApply: true rule — the engine
structurally cannot emit always-on rules. This invariant is enforced upstream, not by
this skill..claude/rules/. runReconcile computes proposals and records
them in the idempotency sidecar only. The only module that writes .claude/rules/ is
writer.mjs, and only AFTER the operator approves proposals via AUQ.mergeCandidates — nothing else writes it.
.orchestrator/runtime/reconcile-candidates.jsonl is a mutable work-queue whose only
sanctioned writer is mergeCandidates (scripts/lib/reconcile/idempotency.mjs); it is
not a scratch pad, and no report, analysis run, or agent may append to it by hand. A
hand-written record there corrupts downstream readers — the session-start reconcile nudge
banner derives "last run" from created_at, so a foreign-shaped record makes a non-empty
store report no reconcile run on record. Candidate analyses and dry-run reports write
their findings to docs/reconcile/<date>-<topic>.md, never into the store. (Since
2026-07-31 a read-side shape guard drops records lacking learning_key/created_at and
mergeCandidates reports the count as skipped — that guard is a backstop, not a licence.)reconcile.enabled gates the AUTOMATIC session-end phase only. /reconcile is an
on-demand command and runs regardless of reconcile.enabled. It still honours
rule-expiry-days and confidence-floor from the reconcile config block.test cases passed, vs 5 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.