scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-08-28 04:24:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/business-operations/commands/cs-bizops.md
Ben Fairless 02c04e3d32
fix(frontmatter): repair 14 unloadable YAML blocks 
Twelve files had frontmatter that yaml.safe_load rejects, all from the same
cause: an unquoted plain scalar containing ": " inside description. Claude Code
responds by loading the body with empty metadata, so the skill keeps working
via /name but has no description for the model to match against, and the seven
affected agents (where name and description are required) may not load at all.

Eleven are fixed by quoting the existing scalar, leaving the text
byte-identical. design-system carries both ' and " so quoting would defeat the
repo's regex extractors in generate-docs.py and sync-codex-skills.py; its one
colon-space is reworded instead ("Precedence:" -> "Precedence is").

Two agents had no frontmatter at all and were being listed with a placeholder
description; both now declare name and description. tools is deliberately
omitted so they keep inheriting the full set, as before.

Assisted-by: Claude Code:claude-opus-5
2026-08-03 08:55:36 +08:00

1.7 KiB
Raw Blame History

description argument-hint
Top-level Business Operations router. Routes the inquiry to one of six BizOps sub-skills (process, vendor, capacity, comms, knowledge, procurement) and returns a digest. Invokes the business-operations-skills orchestrator (context: fork). <inquiry>

/cs:bizops — Business Operations router

Use the cs-bizops-orchestrator agent + business-operations-skills orchestrator skill to handle this inquiry:

$ARGUMENTS

Routing protocol

  1. Classify the inquiry against the six BizOps lanes:

    • PROCESS — bottleneck, cycle time, handoff, workflow → process-mapper
    • VENDOR — SLA, third-party risk, SaaS audit → vendor-management
    • CAPACITY — headcount, utilization, hiring sequence → capacity-planner
    • COMMS — all-hands, change announcement, internal newsletter → internal-comms
    • KNOWLEDGE — SOP, runbook, onboarding doc → knowledge-ops
    • PROCUREMENT — spend audit, supplier rationalization → procurement-optimizer

  2. If top lane signal score ≥ 2 keyword hits → invoke that sub-skill in forked context.

  3. If single-signal or tie → ask one clarifying question naming the top two candidate lanes.

  4. After sub-skill runs, return ≤ 200-word digest to the parent context.

Output expectations

  • What was analyzed
  • Top 3 findings with severity (CRITICAL/HIGH/MEDIUM)
  • Top 3 next actions with named owners
  • Path to artifact(s) saved to the user's working directory
  • Suggested chain (which sub-skill to invoke next, if any)

Anti-patterns

  • ❌ Running multiple sub-skills to be thorough — pick one, digest, chain on request
  • ❌ Auto-approving an ops change — surface findings, the human decides