mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-08-28 04:24:58 +00:00
7947638b31
Two new top-level domain folders expanding the repo from 313 → 319 production
skills across 14 domains. Path-B 11-file contract per skill, stdlib-only Python
tools, Matt Pocock grill-with-docs discipline baked into every SKILL.md.
## New domains
- business-operations/ — internal-ops skills for BizOps leads, COO direct
reports, vendor management, IT ops. Sprint 1 ships 3 skills:
- business-operations-skills (orchestrator, context: fork)
- process-mapper (BPMN + bottleneck + cycle-time, 4 industry profiles,
Lean/TOC canon)
- vendor-management (scorecard + SLA + 3rd-party risk, 4 industry profiles,
Shared Assessments SIG-Lite, NIST SP 800-161, ISO/IEC 27036)
- commercial/ — per-deal-and-packaging skills. Sprint 1 ships 3 skills:
- commercial-skills (orchestrator, context: fork)
- pricing-strategist (5-model picker, Van Westendorp PSM with OPP/IDP/PMC/PME,
packaging with 7 anti-pattern detectors, Ramanujam/Skok/Tunguz canon)
- deal-desk (5-dim scorer, discount approval router, 10-pattern terms redliner,
never auto-approves — every verdict names the human approver)
## Chaining via context: fork
Both domain orchestrators set context: fork in frontmatter so heavy ingestion
(vendor catalogs, RFP docs, process transcripts) stays out of the parent
session. Sub-skills opt into fork only when they ingest large artifacts
(vendor-management does, pricing-strategist and deal-desk do not).
## Matt Pocock grill discipline
Every Sprint 1 SKILL.md ships a "Forcing-question library" section: 5-7
questions, walked one at a time by the orchestrator (or /cs:grill-bizops,
/cs:grill-commercial), each with a recommended answer + canon citation.
Discipline derived from engineering/grill-me + engineering/grill-with-docs
(Matt Pocock, MIT).
## Hard rules per domain
- BizOps: every output is a recommendation, never an auto-decision.
- Commercial: pricing outputs model+range (never a single number); deal outputs
route to a named human approver (never auto-approve); forecasts surface the
conversion assumption explicitly.
## Agents + commands
- cs-bizops-orchestrator agent ("Where does the work spend most of its time
waiting?")
- cs-commercial-orchestrator agent ("What's the margin on this deal at full
discount?")
- 8 new slash commands: /cs:bizops, /cs:commercial, /cs:grill-bizops,
/cs:grill-commercial, /cs:process-map, /cs:vendor-review, /cs:pricing-strategy,
/cs:deal-review
## Verification
- All 12 new Python tools (4 skills × 3 each) pass --help and --sample
smoke tests, exit 0
- Stdlib-only across the board
- 12 reference docs each cite ≥ 7 authoritative sources
- Marketplace registry: 57 → 59 plugins
## Sprint 2 (not in this PR)
- BizOps: capacity-planner, internal-comms, knowledge-ops, procurement-optimizer
- Commercial: partnerships-architect, channel-economics, commercial-policy,
rfp-responder, commercial-forecaster
## Files
50 new files: 6 SKILL.md (2 orchestrators + 4 leaf) + 12 Python tools + 12
references + 4 asset templates + 2 plugin.json + 2 CLAUDE.md + 2 README.md +
2 cs-* agents + 8 slash commands + 1 master plan doc + marketplace.json +
root CLAUDE.md update.
Master plan: documentation/implementation/bizops-commercial-expansion-plan.md
https://claude.ai/code/session_015bBb4HzWCf5HH5QK2TGtnW
|
||
|---|---|---|
| .. | ||
| delivery | ||
| implementation | ||
| GIST_CONTENT.md | ||
| GROWTH_STRATEGY.md | ||
| PYTHON_TOOLS_AUDIT.md | ||
| TEST_COVERAGE_ANALYSIS.md | ||
| WORKFLOW.md | ||