Claude-Codex Skills Marketplace
A compact marketplace of standalone engineering skills for Claude Code and Codex covering review, audit, optimization, testing, product discovery, architecture, and safe publishing.
- Source repo
- levnikolaevich/claude-code-skills
- Stars
- ★ 596
- Last updated
- 6d ago
- License
- MIT
- Primary language
- Shell
- FA score
- 60/100 · Some gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformCodex · Claude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A team lead validates an implementation plan against repository evidence with ln-11-plan-reviewer before letting an agent execute it.
- Not a fit if
- Teams needing a standalone runtime or MCP server; it only runs inside Claude Code or Codex
- Teams wanting benchmarked proof of skill quality; static checks do not prove task performance
- Users needing a deterministic workflow engine or mandatory skill chain; the lifecycle is user-coordinated
- Website
- levnikolaevich.com ↗ set on GitHub
- Maintenance
- Commits in the last 30 dayslast commit 2026-11-11latest release v2026.10.18 (2026-10-18)+0.9 ★/day over 7 days
- Source review
- 60/100 · Some gaps
What does this agent do, and when should you use it?
This repository is a compact plugin marketplace providing 24 standalone engineering skills for the Claude Code and Codex hosts, organized into seven suites: a Review Suite (plan and delivery review), a Codebase Audit Suite (documentation, code health, test suite, architecture, and persistence auditors), an Optimization Suite (performance, dependency upgrades, modernization, benchmark comparison, surgical changes), a Testing Suite, a Product Discovery Suite, a Maintainer Suite, and an Architecture Suite. Each skill is a plugin directory with a SKILL.md containing domain checklists, evidence requirements, and a final self-check; skills have a 200-line ceiling and load references only for the relevant workflow branch. The repo ships a portable Agent Plugins v1 manifest, host-specific catalogs for Claude Code (.claude-plugin/marketplace.) and Codex (.agents/plugins/marketplace.), and a static catalog site. It deliberately contains no MCP servers, orchestration hierarchy, or evaluation harness, and users install only the suites they need.
Skills run as instructions inside the host (Claude Code or Codex): Plan Reviewer validates an implementation plan against repository evidence before execution; Delivery Reviewer reviews delivery acceptance, regressions, and release risks; the five auditors assess documentation trust, cross-cutting code health, test value and isolation, system boundaries and dependency topology, and query/transaction consistency; Performance Optimizer profiles and experiments to keep only measured improvements, while Benchmark Comparator compares alternatives under a frozen, reproducible experiment contract; the Architecture Suite (ln-71 through ln-76) produces baselines, current-state documents, target design proposals, decision records, diagrams, and migration plans from repository evidence; and the Maintainer Suite validates, commits, pushes, and remotely verifies repository changes, then publishes GitHub releases and Discussions announcements. Skills are invoked by namespaced names, e.g. /review-suite:ln-12-delivery-reviewer.
- A team lead validates an implementation plan against repository evidence with ln-11-plan-reviewer before letting an agent execute it.
- An engineer inheriting a legacy codebase runs the audit suite (ln-21 to ln-25) to assess documentation, code health, tests, architecture, and persistence.
- A performance-sensitive project uses ln-31-performance-optimizer and ln-34-benchmark-comparator for reproducible experiments, keeping only measured wins.
- A team upgrading dependencies without a big-bang rewrite uses ln-32-dependency-upgrader for reversible, verified batches.
- An architect uses the architecture suite to generate current-state documents, decision records, and migration plans from existing repo evidence.
- A skill-repo maintainer uses the maintainer suite (ln-61 to ln-64) to review skill content and publish GitHub releases and Discussions announcements.
How do you install or deploy this agent?
In Claude Code, add the marketplace and install only the suites you need:
/plugin marketplace add levnikolaevich/claude-code-skills
/plugin install review-suite@levnikolaevich-skills-marketplace
/plugin install codebase-audit-suite@levnikolaevich-skills-marketplace
/plugin install optimization-suite@levnikolaevich-skills-marketplace
/plugin install testing-suite@levnikolaevich-skills-marketplace
/plugin install product-discovery-suite@levnikolaevich-skills-marketplace
/plugin install maintainer-suite@levnikolaevich-skills-marketplace
/plugin install architecture-suite@levnikolaevich-skills-marketplace
/reload-pluginsIn Codex:
codex plugin marketplace add levnikolaevich/claude-code-skills
codex plugin add review-suite@levnikolaevich-skills-marketplace(repeat with the other suite names.)
For local development, load one plugin directly: claude --plugin-dir ./plugins/review-suiteHow do you use this agent?
After installation, invoke a skill by its namespaced name, e.g. /review-suite:ln-12-delivery-reviewer for delivery review, /codebase-audit-suite:ln-22-codebase-auditor for a codebase health audit, or /architecture-suite:ln-76-architecture-migration-planner for a migration plan. Each skill loads its skill-local references only for the relevant workflow branch and produces reports in a consistent order: result, scope, evidence, verification, completion. No MCP server or shared runtime is required.
What are this agent's strengths and limitations?
- Works with both Claude Code and Codex hosts and follows the portable Agent Plugins v1 standard, with one canonical copy of each skill (skills/<name>/SKILL.md).
- Every skill carries explicit evidence checks, applicability reasons, and a final self-check; reports follow a uniform structure (result, scope, evidence, verification, completion).
- Seven independently installable suites let you adopt only what you need; the repo is intentionally minimal with no MCP or orchestration dependencies.
- Includes a static validation script, scripts/validate-repository.ps1, covering structure, skill contracts, catalogs, and documentation coverage.
- Depends on host CLIs (Claude Code or Codex); it cannot run outside those environments and offers no MCP or standalone runtime path.
- The README states static validation establishes format and consistency only and does not certify task performance, so real skill quality must be verified by the user.
- No independent evaluation harness exists to quantify skill outcomes, and additional repository guidance (AGENTS.md) was not available for deeper review.
- Contributors must learn the numbering scheme (1x–7x), SKILL_TEMPLATE.md authoring format, and AGENTS.md validation rules before adding or editing skills.
How does this agent compare with similar options?
The README positions the repo as a compatible implementation of Claude Code's native plugin mechanism and the OpenAI plugin guide, aligned with the Agent Plugins v1, Agent Skills, and Claude Code skill/plugin specifications; no third-party competitors are named in the source.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Claude-Codex Skills Marketplace This agent | 60 · Some gaps | Agent plugin / skillFree + model costs | ★ 596 | 6d ago | Shell | Codex · Claude Code |
| Compound Engineering | 75 · Good | Agent plugin / skill | ★ 26k | today | TypeScript | Codex · Claude Code |
| Maestro Orchestration Platform | 64 · Some gaps | Agent plugin / skillFree + model costs | ★ 490 | 28d ago | JavaScript | Codex · Claude Code |
| multi | 56 · Major gaps | — | ★ 24 | today | Shell | Codex · Claude Code · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
AGENTS.md limits review, planning, and investigation to read-only work and requires user authorization for implementation, publication, and deployment, supporting the least-privilege, confirmation, and external-effects scores. It separates preparation, publication, deployment, and health outcomes and calls for safe recovery. The sample does not describe runtime data flows, sensitive-data handling, or dependency vulnerability response. Provenance consists of an owner field and license attribution; publisher identity is unverified and does not establish verified authorship or maintenance.
The sampled architecture skills share an execution contract that requires observed outcome evidence, preserves gaps, and distinguishes unknown from proven; their workflow boundaries broadly match the README. Tool routing offers preferred capabilities and fallbacks, with BLOCKED or UNVERIFIED outcomes for missing evidence. The sample does not establish dependency availability guarantees or detailed per-tool failure messages, so those areas receive partial credit.
The README maps a broad range of tasks to plugins and expected results, covering discovery, architecture, implementation, review, delivery, and operations. Skills state their boundaries, permitted artifacts, and relationships to adjacent workflows. Only a small subset of skill bodies is included, so trigger behavior and fit beyond Claude Code and Codex have limited evidence.
The README organizes the catalog by task and lifecycle and provides installation and invocation examples for both hosts; skills use numbered, descriptive names. The MIT license text is complete. The sample has no FAQ, consolidated limitations, version history, or clear maintenance owner and update responsibility. Installation steps are actionable but provide limited detail on platform and version differences.
The product packages standalone skills as workflows with stated scope, checks, and evidence reporting, and the catalog helps users choose by desired outcome. The sample does not show concrete final outputs for most skills, observed user benefits, or execution cost data, so it supports a structured value proposition but not stronger usability or cost-benefit claims.
README descriptions can be compared with the sampled architecture skill bodies; those bodies require observed evidence, source paths, and limitations, and label unknown claims as UNKNOWN or UNVERIFIED. The CI workflow shows behavioral-evaluation configuration and provenance-recording steps, but no results for this revision are supplied. Cross-source support and fact-versus-inference practices are specified, though the sample provides incomplete corroboration.
- This assessment uses only the supplied static sample; skills were not run, and evaluation results and publisher identity were not independently verified.
- Many safeguards appear as workflow instructions in the skills and AGENTS.md. The sample does not establish runtime adherence and does not include every skill file.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
What's New in v2026.10.18 - Architecture-correct implementation: scoped changes include necessary refactoring, structural root-cause fixes and all affected consumers. Minimize system complexity and lifecycle risk rather than changed lines. - Executable engineering standards: the new Quality Gate Engineer (46) configures and verifies lint, type, architecture and other checks, including acceptance, rejection and command failure propagation. …View on GitHub ↗ -
Release notes excerpt
What's New in v2026.10.05 - Skills organized around delivery outcomes: product discovery, architecture, delivery planning, implementation, quality assurance, delivery, operations, and skill maintenance. Each skill remains independently usable. - New capabilities: product requirements and interaction design; architecture baselines, documentation, proposals, decisions, diagrams, and migration planning; deployment engineering, incident investigation, and product outcome evaluation. …View on GitHub ↗ -
Release notes excerpt
What's New in v2026.07.12 Claude-Codex Skills, rebuilt for current models Earlier coding models needed a large orchestration and evaluation framework to follow complex workflows reliably. Current Claude and Codex models work better with focused procedural guidance. The repository now contains 18 standalone skills in six small plugins. Each skill owns one bounded outcome and carries only the domain rules, tool-routing decisions, safety gates, evidence requirements, and residual-risk checks worth bringing into context. Six focused plugins …View on GitHub ↗
FAQ
Does it cost anything or need extra APIs?
Do I need all seven suites?
How are skills invoked?
Does it need an MCP server or a complex runtime?
How do I verify skills work after installing?
Is Claude-Codex Skills Marketplace open source?
Is Claude-Codex Skills Marketplace safe to use?
Is Claude-Codex Skills Marketplace still maintained?
Who makes Claude-Codex Skills Marketplace?
What is Claude-Codex Skills Marketplace's official website?
Thanks — we use this to improve the page.