bossjones
- 39 skills
- 0 followers
- 4 hours ago last updated
- ▌
- ▌ Fastapi Development · bossjonesBuild async APIs with FastAPI, including endpoints, dependency injection, validation, and testing. Use when creating REST APIs, web backends, or microservices.
- ▌ Create New Skills · bossjones bundleCreates new Agent Skills for Claude Code following best practices and documentation. Use when the user wants to create a new skill, extend Claude's capabilities, or package domain expertise into a reusable skill.
- ▌
- ▌ Video Processor · bossjones bundleProcess video files with audio extraction, format conversion (mp4, webm), and Whisper transcription. Use when user mentions video conversion, audio extraction, transcription, mp4, webm, ffmpeg, or whisper transcription.
- ▌ Skill Evals · bossjones bundleRun wshobson PluginEval over this repo's skills and write a `# PluginEval Report` to `docs/evals/<plugin>/<skill>.md`. Use when the user wants to evaluate, score, grade, benchmark, or certify skills; (re)generate or refresh eval reports; check skill quality after editing a SKILL.md; or improve skills based on their eval results. Defaults to `--review` (score/standard depth, report only); `--fix` also edits the weakest skills' SKILL.md in place to raise their scores; `--certify` runs the full deep certification with a badge. Reach for this skill even when the user only says "run the evals", "score these skills", or "refresh the eval reports" without naming PluginEval.
- ▌ Doc Generator · bossjonesGenerate markdown documentation from Python codebases by analyzing source files, extracting docstrings, type hints, and code structure. Use when the user asks to document Python code, create API docs, or generate README files from source code.
- ▌ Version Bump Reviewer · bossjonesReviews uncommitted changes to decide whether a semver bump is required and applies the correct version artifact. Handles plugin skills and components, repo-internal skills, and new marketplace plugins; classifies major, minor, patch, or no-bump changes; uses plugin-eval evidence for skill edits; syncs plugin.json with marketplace.json; updates metadata.version for repo-internal skills; validates initial-publish parity; and creates a conventional commit. Use when feature-bearing files under plugins/ or .claude/skills/ change, a marketplace plugin entry is added, versions may be out of sync, or the user asks to bump, release, introduce, or prepare a skill or plugin for merge. Run after plugin-dev:skill-reviewer.
- ▌ Planf3 · bossjones bundleWrites and maintains implementation plans as self-contained HTML files with synced visual identity, optional AI-generated diagrams, and a full create/update/build lifecycle with phase checkboxes and append-only metadata — saved to specs/. Use as a richer alternative to /agent-harness:plan when the plan benefits from diagrams or needs to be revised and executed over multiple sessions.
- ▌ Example Skill · bossjones bundleExample skill demonstrating proper structure - replace with your skill's purpose
- ▌ Boss Cmux · bossjones bundleDrive cmux — the terminal multiplexer / agent-surface control CLI — from natural language. Use this whenever a prompt asks you to open, inspect, prompt, read, or tear down cmux windows, workspaces, panes, surfaces, or agent sessions. Prefix orchestration prompts with /boss-cmux.
- ▌ Pr Review · bossjones bundleReview a GitHub pull request and emit a schema-validated local review payload — inline comments plus an approve-or-comment decision. Use when asked to review a PR, audit a pull request's changes, or produce review comments without posting them.
- ▌ Stop Slop · bossjones bundleRemove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
- ▌ Fetch Diff · bossjones bundleFetch a GitHub PR diff with old/new line numbers and auto-generated-file masking for code review. Use when you need a pull request's diff annotated with line numbers to place inline review comments, or want the diff filtered to specific file globs.
- ▌ Git Worktree · bossjones bundleCreate an isolated git worktree under .claude/worktrees/<repo>-<name>/ for feature development without switching branches. Use when starting a new feature, fix, or experiment that needs its own working directory — handles repo-prefixed naming, base-ref selection, .worktreeinclude file copying, and language-specific setup pointers.
- ▌ Boss Cmux Team · bossjones bundleSpawn, orient, and drive a multi-agent terminal team in cmux from natural language. Use when a prompt asks you to boot a team of agents (lead + workers) as a cmux workspace, stand up a "full-stack team" / "agent fleet", orchestrate several terminal agents on one feature, or attach to and drive a team that was just spawned. Roles, models, app, and completion sentinel come from a team-config JSON.
- ▌ Harness Doctor · bossjones bundleInspect agent-harness environment readiness and runtime storage without changing files. Use when asked to diagnose agent-harness, check hook prerequisites, find harness logs or data, learn which plugin repository names the harness root, inspect stale logs, .claude/data, or a legacy repository-named harness directory, or run a harness health check.
- ▌ Pyrefly Typing · bossjones bundleAdopt Pyrefly (Meta's Rust-based Python type checker) into a target `uv` Python project as a non-blocking, agent-driven typing feedback loop, alongside whatever type checker it already uses (mypy/pyright/basedpyright/ty) — never replacing it. Use when asked to "adopt pyrefly", "set up pyrefly typing", "add a pyrefly feedback loop", "burn down pyrefly errors", or "wire a pyrefly Stop hook" into a project. This skill configures a *target* repo (pyproject.toml, baseline, task-runner targets, optional Stop hook) — it never touches boss-skills itself.
- ▌ Unicode Hygiene · bossjonesScan skill, plugin, command, agent, and marketplace files for invisible or visually-spoofed Unicode — tag characters (U+E0000–U+E007F), bidirectional overrides (Trojan Source), zero-width / format characters, and mixed-script (homoglyph) install lines. Use before committing or publishing skills/plugins, when reviewing an untrusted SKILL.md / plugin.json / agent / command, or when auditing the marketplace for hidden-instruction supply-chain payloads.
- ▌ Worktree Doctor · bossjones bundleAnalyze a repo and suggest a .worktreeinclude so worktrees inherit env, secret, and local-config files. Use when setting up worktrees in a new repo, before the first /git-worktree, or when a worktree is missing its .env / local settings — scans gitignored files and proposes patterns.
- ▌ Github Pr Review · bossjones bundleUse when reviewing GitHub pull requests with gh CLI - creates pending reviews with code suggestions, batches comments, and chooses appropriate event types (COMMENT/APPROVE/REQUEST_CHANGES)
- ▌ Add Review Comment · bossjones bundlePost a single inline review comment to a GitHub pull request. Use when you need to leave one comment on a specific line or line range of a PR via the GitHub API — supports single-line and multi-line anchors and one-click suggestion blocks.
- ▌ Git Worktree Clean · bossjones bundleClean up stale git worktrees with merged-branch detection and a disk-usage report. Use when feature worktrees under .claude/worktrees/ have accumulated and you want to reclaim space — auto-removes merged worktrees and reviews unmerged ones.
- ▌ Setup Second Brain · bossjones bundleInstall and configure the "second brain" — the obsidian-wiki uv tool plus optional QMD semantic search. Use when setting up a second brain, installing obsidian-wiki, making a machine "second-brain ready", configuring an Obsidian knowledge vault for AI agents, or enabling/configuring QMD semantic search (QMD_WIKI_COLLECTION, QMD_TRANSPORT). Detects what is already present, previews every change, then installs obsidian-wiki[graph,ast] as a uv tool, runs obsidian-wiki setup against the vault, optionally installs QMD via npm, writes QMD variables to the config, and can index the vault. Every config file is backed up before it is written.
- ▌ Git Worktree Remove · bossjones bundleSafely remove a single git worktree with branch cleanup and safety checks. Use when you are done with one feature worktree and want to delete it plus its local and remote branches, with protected-branch, uncommitted-change, and merge-status checks first.
- ▌ Git Worktree Status · bossjones bundleReport the status of background verification jobs (tests, type check, build) in a git worktree. Use when you want a non-blocking PASS/FAIL/RUNNING/NOT_RUN summary of the checks launched by the git-worktree skill, run from inside a worktree directory.
- ▌ Setup Agent Harness · bossjones bundleMake a repo "agent-harness ready" by safely updating .gitignore and .claude/settings.local.json. Use when setting up or onboarding a repo to the agent-harness plugin, ensuring .gitignore covers the plugin-namespaced harness runtime root and optionally configuring the statusLine and an outputStyle in the per-user settings.local.json. Every file is backed up before any change.
- ▌ Twitter To Reel · bossjones bundleConvert Twitter/X posts into Instagram Reels format. Screenshots tweets, crops to show username/caption/media, creates a 9:16 vertical canvas with matching background color, and overlays downloaded video content. Works alongside twitter-media-downloader skill. Use when user wants to repurpose Twitter content for Instagram, TikTok, or other vertical video platforms.
- ▌ Boss Security Review · bossjones bundlePerforms a security review / security audit / vulnerability review of code and writes a structured, severity-graded findings report (default path specs/security-review.md, overridable from the request). Reviews changed code by default; the request can override the target to a named path (e.g. "review src/auth/") or the whole repo. Reviews against a bundled security rubric (and the target repo's .cursor/rules/security-* rules when present) and cites the specific rule each finding triggered. Use whenever the user asks to "run a security review", "do a security audit", "audit this for vulnerabilities", "check for security issues", "review my changes for security", "is this code secure", "find security bugs", or "look for injection / SSRF / path traversal / hardcoded secrets" — including a pre-merge pass on a branch, PR, file, or directory. Prefer this over an ad-hoc review so findings are graded, cite the triggered rule, and land in a re-checkable report.
- ▌ Release Notes Generator · bossjones bundleGenerate release notes in 3 formats (CHANGELOG.md, PR body, Slack announcement) from git commits. Automatically categorizes changes and converts technical language to user-friendly messaging. Use when preparing a release, drafting a changelog or version notes, or writing a what's-new or ship announcement.
- ▌ Fetch Unresolved Comments · bossjones bundleFetch unresolved PR review comments via the GitHub GraphQL API, filtering out already-resolved feedback. Use when you need only the open review threads on a pull request — for example before addressing reviewer feedback or summarizing what still needs attention.
- ▌ Proxmox Infrastructure · bossjones bundleManage Proxmox VE infrastructure — VM/LXC provisioning, cloud-init templates, storage, and networking — via the proxmoxer Python library, Ansible community.general.proxmox modules, and Terraform/OpenTofu Telmate provider. Use when the user wants to provision, inspect, or modify Proxmox VMs, containers, templates, or storage; troubleshoot deployments; or generate IaC for the homelab.
- ▌ Run Skill Eval · bossjonesRuns 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".
- ▌ Twitter Media Downloader · bossjones bundleDownload images and videos from X/Twitter using gallery-dl. Use when user wants to download media from Twitter/X URLs including tweets, user profiles, timelines, or likes. Supports single tweets, entire user media galleries, bookmarks, and lists. Handles authentication via cookies for accessing protected content.
- ▌ Scaffold Skill Eval · bossjones bundleScaffolds 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".
- ▌ Claude Config Validation · bossjones bundleValidates 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 config changes.
- ▌
- ▌
- ▌