AlexZio00/sovereign-skills
138 stars · Last commit 2026-09-25
20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift). Works with Claude Code, Codex, and Cursor.
README preview
🌐 **English** | [한국어](docs/README.ko.md) | [日本語](docs/README.ja.md) | [中文](docs/README.zh.md) | [Español](docs/README.es.md) # sovereign-skills v6.5.13 20 skills for the full Claude Code project lifecycle — from setup to daily workflow to code review to session management to governance. Each skill is useful standalone; the full sequence covers everything. > **What changed in v6.5.13:** Refinement release — no skills added or removed; a delta port covering 19 of the 20 skills, including several bug fixes that also existed in the public copy. `pre-push` → v3.11.0 no longer skips the secret scan when staging is empty but unpushed commits exist, keeps its test/lint gates working when shell state is lost between calls, and adds a counted same-line allow marker; `full-audit` → v1.4 adds opt-in canary mixing (a clean file and a planted-defect file slipped into review bundles to measure false positives and recall); `integration-intake` splits adoption into enforcement and execution surfaces; `goal-lock` adds judgment-reversal discipline; the frontmatter key is now the documented `user-invocable` in all 20 skills. Full list in [CHANGELOG.md](CHANGELOG.md). --- ## Quick Start **New project (15 min):** ``` /project-init → CLAUDE.md + ROADMAP + .gitignore + .env.example /setup → rules/ + hooks + memory/ + agent routing + team then daily: /session-start at the start of every session /scope before each feature (define IN/OUT/exit criteria) /freeze before implementation (declare editable zone)