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 4
claude-skills/c-level-agents
History
Exact
Claude 7405298b4b
fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 
- #954: strip non-spec source/attribution keys from all 39 plugin.json
  manifests so Claude Code's validator accepts them; metadata preserved in
  new .claude-plugin/authoring-notes.json sidecars; check_plugin_json.py now
  hard-fails manifests carrying those keys and sanity-checks the sidecar;
  CLAUDE.md ClawHub schema section updated to the new rule.
- #949: move the c-level-agents plugin out of c-level-advisor/ to a
  top-level directory so the two marketplace sources no longer overlap;
  updated marketplace.json source, homepage, descriptions, all
  cross-references, docs, harness manifest, mirror-tree symlinks/indexes,
  and rebased the moved files' relative links; domain counters trued up
  (18 -> 19 domains).
- #933: replace dead links to the gitignored maintainer-local megaprompts/
  tree with annotated plain-text references (44 files: SKILL.md, READMEs,
  agents, commands).
- #931: DynamoDB on-demand pricing updated to post-Nov-2024 rates
  ($0.625/M writes, $0.125/M strongly consistent reads).
- #969: skill_security_auditor.py and the three dossier scripts reconfigure
  stdout/stderr to UTF-8 (errors=replace) so legacy Windows codepages no
  longer crash at print time; PYTHONUTF8=1 documented.
- #968: Windows Notes section in INSTALLATION.md + README pointer for the
  core.symlinks mirror-tree checkout caveat.
- #924/#885 residuals: hook commands quote "${CLAUDE_PLUGIN_ROOT}" paths in
  all plugin hooks.json/settings.json (space-safe roots); removed the stale
  pre-rename status/review mirror symlinks and index entries left over from
  the memory-status/memory-review rename.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Qgc6RYXWJPr5oW9DHU7zR4
2026-08-21 05:47:37 +00:00
..
.claude-plugin fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
agents fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
references fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
skills fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00
README.md fix: resolve the actionable reported issues (#954, #949, #933, #931, #969, #968, #924, #885) 2026-08-21 05:47:37 +00:00

README.md

c-level-agents — Founder-Mode Executive Team

A virtual C-suite for Claude Code. Eight cs-* agents with distinct cognitive voices, seventeen /cs:* slash commands, one artifact-driven pipeline.

This plugin is the surface layer on top of the 28 c-level skills already in this repo. The skills provide frameworks and Python tools; this plugin adds:

  1. Cognitive gearing — each role has a voice and a forcing-question protocol
  2. Slash-command invocation — /cs:cfo-review, /cs:boardroom, /cs:founder-mode
  3. Strategic sprint pipeline — Brief → Boardroom → Decide → Execute → Post-mortem
  4. Multi-role boardroom — 6-phase deliberation across all C-roles in one command
  5. Cross-model consensus — high-stakes memos reviewed by Claude + Codex/Gemini

Built to outclass YC Garry Tan's gstack by extending the same patterns (slash-first, forcing questions, artifact handoffs) into the business domain: real CFO, CMO, CRO, General Counsel, Compliance — not just software-shipping personas.

Quick Start

/cs:onboard                          # 6-question founder interview → company-context.md
/cs:office-hours <topic>             # YC-style 6-question interrogation
/cs:founder-mode <question>          # auto-routes to the right C-role
/cs:cfo-review <plan>                # numerate skeptic stress-tests unit economics
/cs:boardroom <brief>                # full panel deliberation, 6 phases
/cs:decide <memo>                    # logs decision to two-layer memory

Agent Roster

Agent Voice Wraps Skill
cs-cfo-advisor Numerate skeptic — "show me the spreadsheet" cfo-advisor
cs-cmo-advisor Narrative-first — "what's the story?" cmo-advisor
cs-cro-advisor Pipeline-paranoid — "where's the coverage?" cro-advisor
cs-cpo-advisor JTBD-driven — "what job hired this?" cpo-advisor
cs-coo-advisor Execution OS — "what's the cadence?" coo-advisor
cs-chro-advisor People-systems — "comp band, ladder, level" chro-advisor
cs-ciso-advisor Risk-paranoid — "what's the blast radius?" ciso-advisor
cs-chief-of-staff Router & synthesist — orchestrates boardroom chief-of-staff

Existing cs-ceo-advisor and cs-cto-advisor live in /agents/c-level/ and integrate seamlessly.

Slash Command Map

Forcing-question office hours (8) — interrogate before advising

  • /cs:office-hours — 6-question YC-style intake
  • /cs:cfo-review /cs:cmo-review /cs:cpo-review /cs:cro-review
  • /cs:cto-review /cs:ciso-review /cs:gc-review

Strategic sprint pipeline (5) — Think → Decide → Ship for business

  • /cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortem

Meta + safety (4)

  • /cs:founder-mode — auto-routes to the right C-role
  • /cs:onboard — founder interview, populates ~/.claude/company-context.md
  • /cs:cross-eval — multi-model consensus (Claude + Codex/Gemini, graceful degradation)
  • /cs:freeze — locks a strategic decision for cooldown period

Design Principles

  • Voice is bookended, analysis is neutral. Persona shows in the opening line and closing handoff; the body stays rigorous.
  • Artifacts over chat. Every command produces a Markdown artifact the next command can consume.
  • Two-layer memory. Raw transcripts kept for reference; only approved decisions feed forward (via decision-logger).
  • Phase 2 isolation. In /cs:boardroom, each role thinks independently before cross-examination.
  • Graceful degradation. /cs:cross-eval falls back to Claude-only if no other models are configured.

References

What's Different vs gstack

gstack c-level-agents
Roles ~6 software-shipping personas 10 real C-suite roles + General Counsel lane
Domain Code shipping only Business + compliance + GTM + finance + product
Frameworks Scope cut, sprint pipeline RICE, JTBD, OKR, Wardley, ADKAR, 8-dim org health
Memory Postgres + pgvector (separate repo) Markdown via llm-wiki bridge (stdlib-only)
Voice Default Claude voice Per-role cognitive style
Compliance None ra-qm-team integration (ISO/MDR/FDA/GDPR)
Boardroom Sequential review chain 6-phase deliberation with isolation

Version: 2.9.0 Status: Production Ready License: MIT