sovereign-skills

22 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift, single-source-of-truth, skill routing). Works with Claude Code, Codex, and Cursor.

Active — Updated in the last 14 days
Multi-agent — Targets three or more agents

Works with

Claude
Codex
Cursor

View on GitHub

151 GitHub stars (151)

+12 in 30 days

Stars gained per day · daily snapshots since Sep 30

Stars gained between daily snapshots
Period	New stars
Oct 1	0
Oct 2	+1
Oct 3	0
Oct 4	0
Oct 5	0
Oct 6	0
Oct 7	+1
Oct 8	0
Oct 9	0
Oct 10	+1
Oct 11	0
Oct 12	0
Oct 13	0
Oct 14	0
Oct 15	0
Oct 16	0
Oct 17	0
Oct 18	0
Oct 19	+1
Oct 20	0
Oct 21	+5
Oct 22	0
Oct 23	0
Oct 24	+1
Oct 25	0
Oct 26	+1
Oct 27	+1
Oct 28	0
Oct 29	0
Oct 30	0
Oct 31	0
Nov 1	0
Nov 2	0
Nov 3	0
Nov 4	0
Nov 5	+1
Nov 6	+1

22 skills (22 skills found in its SKILL.md files)
24 forks (24 forks)
2d ago last update (Last updated 2d ago)

Install

Skills CLI

npx skills add AlexZio00/sovereign-skills

Asks which skills and agents to install. Just one: npx skills add AlexZio00/sovereign-skills --skill clean-room — add -g for every project.

Claude Code

git clone https://github.com/AlexZio00/sovereign-skillscp -r "sovereign-skills/clean-room" ~/.claude/skills/

Copies the clean-room skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add AlexZio00/sovereign-skills

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

Filter skills

In the author's own words, from each skill's SKILL.md.

clean-room

Use when a task mixes safety-adjacent material (stealth, scraping, privacy, IP, licensing, security) with genuinely safe work, or the moment you notice yourself about to hedge, dilute, silently drop, or brace for a refusal on part of a request. Triggers: 'strip the risky part out', 'just the safe part', 'carve this out', 'clean-room this'.
clean-room/SKILL.md on GitHub (opens in a new tab)
code-autopsy

Quantified code review: 12 questions (design, bugs, security, tests, error handling, observability), severity scoring, a four-axis composite score and a deployment verdict (SHIP IT / FIX FIRST / RISKY / BLOCK). Modes: full, --fast (runtime bugs only, max 8 findings), --quick (lint/type gate), diff. Use when: 'code autopsy', 'review this code', 'review my diff', 'is this safe to ship', 'security r…
code-autopsy/SKILL.md on GitHub (opens in a new tab)
collab-audit

This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating the purpose. Saves to ~/.claude/collab-audits/YYYY-MM-DD.md. Compare mode: /colla…
collab-audit/SKILL.md on GitHub (opens in a new tab)
doc-drift

Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory statements, risky-or-ambiguous wording, and session-only context leaked into skills/agent…
doc-drift/SKILL.md on GitHub (opens in a new tab)
eval-leakage-audit

Audits whether a verification (eval/metric/experiment/holdout) actually secures independent external ground truth, or whether the designer, the model, and the scorer are just confirming each other in a circle — via a 28-pattern taxonomy. Read-only. Use before trusting any 'how we'll know it worked' — A/B tests, holdouts, scores, validation — especially when a result feels too clean or self-confir…
eval-leakage-audit/SKILL.md on GitHub (opens in a new tab)
freeze

Scope lock for current task. Declares editable zone — everything outside is frozen (read-only). Call before starting implementation to prevent scope creep.
freeze/SKILL.md on GitHub (opens in a new tab)
full-audit

Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) -> judgment (false-positive/UNCERTAIN triage) -> fix-vs-addition split, gated by ex…
full-audit/SKILL.md on GitHub (opens in a new tab)
goal-lock

Agent Discipline Engine — lock the goal, run PLAN→DO→VERIFY→FINALIZE→OUTPUT loop, detect success masquerading. Triggers: '/goal-lock', '/goal-lock quick', 'goal lock', 'task harness'.
goal-lock/SKILL.md on GitHub (opens in a new tab)
integration-intake

Gate for deciding whether to adopt an external pattern (skill/agent/rule/plugin/MCP/prompt) into your system. Triggers: '/integration-intake [name]', 'should I integrate this', 'is this worth adopting', or sharing a GitHub repo link and asking what to do with it.
integration-intake/SKILL.md on GitHub (opens in a new tab)
next-action

Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
next-action/SKILL.md on GitHub (opens in a new tab)
pre-push

Pre-push security and quality pipeline: secrets scan, then tests, lint and review. TRIGGER automatically whenever the user requests a git push: 'push my changes', 'push to origin', 'push this', 'push the code', 'commit and push', 'ship it', 'deploy to remote', 'deploy to prod/staging/production', or any git push command. Blocks hardcoded credentials and prompt-injection/exfiltration markers (14 p…
pre-push/SKILL.md on GitHub (opens in a new tab)
project-check

Existing project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only. Use when: '/project-check', 'project health check', 'project audit', 'what\'s missing', 'analyze my project', 'check setup'. Ends with /project-init and /setup recommendations. NOT for new projects (use /project-init); project-check = shallow health scan.
project-check/SKILL.md on GitHub (opens in a new tab)
project-init

Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch. Use when: user says '/project-init', 'new project', 'project creation', 'project setup', 'create project'. NOT for AI agent/harness configuration (use setup for that). Conversational, one question at a time.
project-init/SKILL.md on GitHub (opens in a new tab)
project-overview

Use when the user wants a deterministic cross-project status map generated from registered projects' session handoffs. Triggers: '/project-overview', 'project map', 'overall status'. Reads ~/.claude/projects-registry.md (opt-in list), parses each project's memory/session-handoff-LATEST.md state-snapshot v1 block (ts+ctx only), and rewrites the AUTO:START/AUTO:END region of ~/.claude/OVERVIEW.md.…
project-overview/SKILL.md on GitHub (opens in a new tab)
scope

Scope definition before implementation — two modes. Quick mode (default): IN/OUT/exit criteria brief → BRIEF.md. Full mode (/scope full): L0→L4 layered spec chain → spec.md. Trigger: '/scope', '/brief', '/specify', 'scope this', '스펙 잡아줘', '범위 잡아줘', 'spec 만들어', '스펙 만들어', '기획 정리해줘', 'plan this'. Do NOT trigger for: bug fixes, single-file changes, existing spec, brainstorming.
scope/SKILL.md on GitHub (opens in a new tab)
session-checkpoint

Use when saving session state before context compaction, switching tasks, or ending a session. Runs 5 phases: context extraction → handoff write → memory save → preservation check → compact guidance (plus an optional attestation step).
session-checkpoint/SKILL.md on GitHub (opens in a new tab)
session-start

Load handoff on session start, review lessons, output readiness signal. Triggers: '/session-start', 'start session'. Skip if: first session (no handoff), user requests 'start fresh', or standalone question unrelated to project context.
session-start/SKILL.md on GitHub (opens in a new tab)
setup

Claude Code infrastructure + agent team setup — rules, hooks, memory, routing, and agent installation from a guided interview. Combines infrastructure + agent team into one flow. Not project scaffolding (CLAUDE.md/ROADMAP/.gitignore/.env.example) — use project-init for that. Triggers: /setup, harness setup, set up rules, agent team setup.
setup/SKILL.md on GitHub (opens in a new tab)
skill-ops

Skill ops hub with 4 modes: snapshot/rollback, usage health, invocation frequency, and an operational quality score.
skill-ops/SKILL.md on GitHub (opens in a new tab)
skill-trigger-auditor

Audit whether skills, agents and slash commands route correctly and safely, and whether a trigger regression test is needed. Use before changing routing metadata or widening a description.
skill-trigger-auditor/SKILL.md on GitHub (opens in a new tab)
ssot-audit

Find where one fact, value or decision is duplicated or contradicted across files, name the single source of truth (read-only), then consolidate the copies after user approval.
ssot-audit/SKILL.md on GitHub (opens in a new tab)
stepback

One-shot perspective reset. Scans current work context, generates 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.
stepback/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.

Kodlayıcılar ve Kod Çözücüler

Hash Oluşturucular

Kod Formatlayıcılar

HTML Araçları

JavaScript Araçları

Ağ Araçları

database_tools

Geliştirme Araçları

Çeşitli Araçlar

sovereign-skills