AlexZio00/sovereign-skills
140 stars · Last commit 2026-10-09
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 v6.5.14 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 v6.5.14:** Refinement release — no skills added or removed. Bug fixes that also existed in the public copy: `session-start` no longer stops the whole run on a first session without a handoff; `pre-push` stops when the secret scanner is missing; eleven test files that let `pytest` collect 0 tests (a silent pass) now run; `eval-leakage-audit` blocks Bash so the read-only skill cannot write; `setup` backs up files before Replace; `project-init`, `collab-audit`, `scope` and `skill-ops` had rules that contradicted themselves. New: `pre-push` blocks newly committed database files, `scope` gets `coverage_check.py` (requirement ↔ task check), `collab-audit` gets `extract_session_meta.py`, `eval-leakage-audit` grows to 28 patterns, `goal-lock` records a pre-existing-failure baseline, and `integration-intake` adds supply-chain checks. See [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)