Stats
Actions
Tags
From agentops
Distill context (research, recon, learnings) into evidence-anchored rules routed to automation shapes. Use when a finished artifact should become skills, gates, or beads.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentops:operationalizeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Loop position:** move 7 (capture + ratchet) of the [operating loop](../../docs/architecture/operating-loop.md) — routes promoted learnings to their weakest durable enforcement (skill, gate, or bead).
Loop position: move 7 (capture + ratchet) of the operating loop — routes promoted learnings to their weakest durable enforcement (skill, gate, or bead).
Rich context dies in the artifact that gathered it. A deep-research report, a codebase-recon sweep, or a painful learning is read once, agreed with, and never changes behavior again. This skill is the bridge: distill the artifact into a handful of evidence-anchored rules, then route each rule to the automation shape that will actually fire next time — skill, workflow, hook, gate, beads, or playbook.
Use when: "I gathered rich context — operationalize it." The input is a finished artifact; the output is rules with anchors and a handoff per rule.
Name the source artifacts in place — absolute or repo-relative paths plus a one-line provenance note each (who produced it, when, method). Confirm each source has citable anchors (section IDs, finding IDs, line ranges); if not, add anchor IDs to your notes about the source, never by editing the source.
Checkpoint: every source is a named path with a provenance line. No corpus dirs were created.
Extract candidate rules in the canonical form — "When X, do Y because Z" — where Z cites at least one anchor. Work source by source, then reconcile:
Checkpoint: every rule line carries ≥1 anchor; every conflict became a DISPUTED entry, not a blended rule.
Hand each rule to /automation-shape-routing and extend its decision with this target table:
| Route | Pick when the rule… | Emit target |
|---|---|---|
| skill | needs judgment at execution time | /skill-builder |
| workflow | is a deterministic multi-step sequence | /workflow-builder |
| hook | must fire mechanically on a runtime event | /cc-hooks |
| gate | should check outputs — start warn-only | a validation gate spec (warn-only first) |
| beads | is unsettled work or a DISPUTED investigation | /beads-workflow |
| playbook | guides a human/operator decision, not an agent | .agents/playbooks/ entry |
Checkpoint: every rule has exactly one route; every DISPUTED entry routed to beads.
Write the rule packet (Output Specification below), then create one handoff stub per routed rule: the rule text, its anchors, the chosen route, and the target skill invocation. The downstream builder owns the artifact; this skill owns the rule and its evidence trail.
For each rule, run the counter-example check: actively search the sources (and your own experience) for one case where following the rule would be wrong. A found counter-example narrows the rule's "When X" or demotes it to DISPUTED. Then request a /validate verdict on the packet before handing off — verify before any downstream builder consumes it.
Input: fixtures/research-excerpt.md — a fake deep-research excerpt on worker-lane retry behavior, anchors RX-1…RX-5.
Distilled packet:
Note what did NOT happen: rules 1–3 were not averaged into "rotate fairly quickly"; RX-3 (re-dispatch to a warm lane) was held back at Step 5 because its own source records a 9% duplicate-work counter-example.
Format: markdown rule packet — sources-in-place list, numbered rules in
"When X, do Y because Z" form with anchors, DISPUTED section, route table, and
the validate verdict reference.
Path: written to .agents/operationalize/YYYY-MM-DD-<slug>.md; handoff
stubs accompany it as a ## Handoffs section (one block per routed rule).
Exit signal: packet path + per-rule route summary reported to the caller.
npx claudepluginhub boshu2/agentops --plugin agentopsScans installed skills to extract cross-cutting principles and distills them into rules by appending, revising, or creating rule files. Useful for periodic rules maintenance after skill changes.
Scans installed skills to extract principles shared across 2+ skills and distills them into rules by appending, revising, or creating rule files.
Walks existing company artifacts (Slack, Notion, GDocs, markdown vaults) and emits draft rules, skills, and CLAUDE.md for onboarding to ai-brain-starter.