claude

boss-experimental

Experimental, not-ready-for-prime-time Claude Code tooling. First tenant: a genericized skillgrade-based skill-eval system plus config-validation, a knowledge-architecture doctrine, and a set of dev-workflow agents. Self-contained and parallel to the repo's existing plugin-eval stack.

1 on GitHubby Malcolm Jonesv0.2.1MITupdated 7 days agoboss-experimental
/

Plugin boss-experimental from marketplace boss-skills in bossjones/boss-skills. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (7)

  • claude-config-validation

    Validates a project's Claude Code configuration (CLAUDE.md, agents, skills, rules, commands) against knowledge-architecture doctrine. Use when asked to "validate CLAUDE.md", "check my .claude config", "audit agent/skill/rule placement", "lint the knowledge architecture", or before merging Claude con

  • my-skill

    A skill that references a nonexistent command

  • example-skill

    Example skill for testing

  • big-skill

    A skill that is way too large

  • bad-skill

    A skill with inline code blocks

  • run-skill-eval

    Runs a Claude Code skill's eval suite — executes each eval.yaml task against its fixtures, scores with graders, reports pass/fail. Use when asked to "run skill evals", "run the eval suite", "score a skill against its fixtures", or "check if a skill passes its evals".

  • scaffold-skill-eval

    Scaffolds a complete, runnable eval suite (fixtures, grader scripts, eval.yaml, runner) for a Claude Code skill. Use when asked to "scaffold an eval", "generate an eval suite for a skill", "create test fixtures and graders for a skill", or "add skillgrade tests".

Subagents (8)

  • architect

    Use when planning a new feature or significant change that needs a technical requirements document before implementation begins

  • coder

    Use when implementing features or fixing bugs in this project's production code

  • config-reviewer

    Reviews Claude Code project configurations against the knowledge architecture. Reports findings — never modifies files.

  • learner

    Use after a workflow completes to update CLAUDE.md, agents, and skills based on what was learned

  • pr-submission

    Use when creating branches, committing changes, pushing, or opening pull requests

  • reviewer

    Use when reviewing code changes for quality, security, architecture, and convention compliance

  • test-writer

    Use when writing unit, integration, or E2E test files

  • tester

    Use when executing build, lint, and test suites and reporting structured results

View source on GitHub

More from bossjones/boss-skills

All 8 plugins →

agent-harness

claude

Agent harness tooling for Claude Code: subagents, commands, skills, and scripts that build and operate agentic dev workflows.

21 skills · 16 commands · 4 agents

1

meta-docs

claudecodex

Documentation quality, anti-slop rewriting, multi-language humanization, and adversarial verification skills and subagents.

3 skills · 1 agent

1

python-dev

claude

Python development tooling for Claude Code: debug GitHub Actions CI failures end-to-end and ship changes via conventional-commit PRs. Assumes a uv-based project with ruff, ty, deptry, pre-commit, and mkdocs.

2 commands

1

twitter-tools

claude

Twitter/X social media tools for downloading media and converting tweets to Instagram Reels format. Includes gallery-dl integration for media downloads and video composition tools for vertical content creation.

2 skills

1

basedpyright-lsp

claude

LSP plugin wiring up basedpyright-langserver for Python real-time diagnostics, hover docs, go-to-definition, and find-references in Claude Code. Requires basedpyright installed separately (`uv tool install basedpyright` or `pip install basedpyright`).

LSP

1

github-pr-review

claude

Professional GitHub PR reviews with pending reviews, code suggestions, and a user-approval workflow via the gh CLI.

1 skill

1

Similar plugins

ruflo-rure

claude

Statically analyze a local JS/Electron app you're authorized to study, with file+line evidence, and build an original reimplementation of what you find. Experimental. Phase 1: JS/Electron static analysis. Phase 2: native ELF/PE/Mach-O container inspection. Phase 3: .NET assembly metadata. Phase 4: EVM bytecode inventory. Phase 5: CUDA fatbin, cubin and PTX inventory. Parses, never executes. Dynamic analysis is a future phase, not yet implemented.

1 skill · 1 command · 1 agent

ruvnet/ruflo 81,589

growthbook

claude

A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.

4 skills

anthropics/claude-plugins-official 47,076

llm-finetuning

claudecodex

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

wshobson/agents 42,461

GrowthBook

claude

A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.

4 skills

anthropics/knowledge-work-plugins 35,601

engineering-advanced-skills

claude

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

alirezarezvani/claude-skills 29,725

promptfoo

claudecodex

Connect providers and targets, write eval suites, and set up or run red team scans with promptfoo

4 skills

promptfoo/promptfoo 27,115

Maintain boss-experimental?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins8 plugins