{
"markdown": "# TechWolf AI-First Toolkit\n\n     \n\nOpen-source agent skills from [TechWolf](https://techwolf.ai)'s [AI-First Bootcamp](https://ai-first.techwolf.ai), for Claude Code, Codex, and Google Antigravity.\n\n\n\n**New here?** Add the marketplace, then install any plugin below. Full commands in [Quick start](#quick-start).\n\n```bash\nclaude plugin marketplace add techwolf-ai/ai-first-toolkit\n```\n\n## Plugins at a glance\n\n8 plugins, 28 skills. One install command each.\n\n| Plugin | What it does | Install |\n|--------|--------------|---------|\n| **ai-firstify** | Audit, re-engineer, or bootstrap any codebase to 9 AI-first design principles | `claude plugin install ai-firstify@techwolf-ai-first` |\n| **content-studio** | Thought-leadership pipeline (LinkedIn, blog, opinion) with a visual editor | `claude plugin install content-studio@techwolf-ai-first` |\n| **people-management** | AI-augmented management: 1:1 prep, meeting prep, triage, performance cycles | `claude plugin install people-management@techwolf-ai-first` |\n| **knowledge-base** | Evidence-backed KB; every answer cites literal quotes from your files | `claude plugin install knowledge-base@techwolf-ai-first` |\n| **ai-adoption** | Claude history analytics: token-doctor and task-profile | `claude plugin install ai-adoption@techwolf-ai-first` |\n| **session-tools** | Session continuity: find past sessions, write handoff notes, craft /goal prompts | `claude plugin install session-tools@techwolf-ai-first` |\n| **techwolf-brand-kit** | Official TechWolf logo assets (SVG + PNG) for AI-generated outputs | `claude plugin install techwolf-brand-kit@techwolf-ai-first` |\n| **tool-build-kit** | Build an MCP server and bundle your tools into a shareable plugin, end to end | `claude plugin install tool-build-kit@techwolf-ai-first` |\n\n\nNot using Claude Code? Every skill follows the [agentskills.io](https://agentskills.io) spec and installs into Codex or Google Antigravity via [`./install.sh`](#codex). One caveat on per-platform support:\n\n- **Cross-platform (all skills except below):** ai-firstify, content-studio, knowledge-base, people-management, techwolf-brand-kit, tool-build-kit, and the `handoff` and `goal-prompt` skills in session-tools. These operate on your project files and prompts, so they work the same on Claude Code, Codex, and Antigravity.\n- **Host-aware (ai-adoption and session-tools):** token-doctor, task-profile, and session-search read agent **session history** off disk, which is per-platform. Each script detects the host (via the `platform` field `install.sh` stamps into each installed skill; override with `AI_FIRST_PLATFORM=claude|codex|antigravity`) and routes or degrades rather than scanning the wrong path. Support today:\n\n | Skill | Plugin | Claude Code / Cowork | Codex (`~/.codex/sessions`) | Antigravity |\n |---|---|---|---|---|\n | session-search | session-tools | yes | yes | no (degrades) |\n | token-doctor | ai-adoption | yes | yes (cost via OpenAI rates) | no (degrades) |\n | task-profile | ai-adoption | yes | yes | no (degrades) |\n\n **Antigravity** is unsupported for session analysis on purpose: the IDE stores conversations AEAD-encrypted at rest (`~/.gemini/antigravity/conversations/*.pb`), and the unencrypted CLI store carries no parseable turn/token content. Where a skill can't honestly read a platform's data it prints a clear \"not available on \\\" message and exits, never empty or misleading output.\n\n## What's inside\n\n### ai-firstify: AI-First Skill\n\nAudit, re-engineer, or bootstrap any codebase to align with 9 AI-first design principles and 7 design patterns. Three modes:\n\n- **Audit**: deep analysis across 7 dimensions with a scored report\n- **Re-engineer**: actively restructures your project to be AI-first\n- **Bootstrap**: guides new project setup with discovery questions\n\n### content-studio: Thought Leadership Pipeline\n\nFull content pipeline for LinkedIn posts, blog posts, and opinion pieces. Includes 8 specialized skills, a visual Kanban editor, and hooks that auto-start the companion app.\n\n- **Write**: LinkedIn posts, blog posts, opinion pieces with voice-matched style\n- **Brainstorm**: generate ideas from URLs, files, or recent posts\n- **Analyze**: engagement pattern analysis across published content\n- **Setup**: interactive onboarding that learns your voice and creates a personalized content repo\n\n### people-management: AI-Augmented Management\n\nAI-augmented tooling for people managers. Surfaces the right context at the right time, before meetings, during 1:1 prep, when triaging messages, or reviewing performance. Adapts to any org's frameworks and values.\n\n- **Setup**: interactive onboarding (10 phases) that discovers your team, frameworks, values, and ways of working\n- **8 skills**: meeting prep, 1:1 prep, triage, customer status, priority planner, team health, performance cycle\n- **Framework-agnostic**: configures to your org's performance dimensions, rating scale, management competencies, and values\n\n### knowledge-base: Evidence-Backed Knowledge Base\n\nBuild and query a structured knowledge base where every answer cites literal quotes from your KB files. Prevents hallucinations by grounding all responses in documented facts.\n\n- **Setup**: interactive onboarding that defines categories (flat or nested), scaffolds the KB structure, and populates from your existing sources (Notion, Slack, Confluence, local files)\n- **KB Answer**: answer questions with evidence-backed citations from your KB\n- **KB Import**: import knowledge from documents (Markdown, PDF, plain text) into structured entries, single-document or bulk-from-folder\n- **KB Refresh**: add new sources or re-scrape existing ones to keep the KB current\n- **KB Search**: `kb-search.py` keyword-ranked lookup across title, tags, description, and body, with category and tag filters\n\n### ai-adoption: Claude History Analytics\n\nTwo skills for analyzing your Claude Code + Cowork session history. Local-only, no API calls.\n\n> **Host-aware (reads session history off disk).** Both skills work on Claude Code / Cowork **and Codex** (`~/.codex/sessions`); token-doctor prices Codex usage with OpenAI rates. Antigravity session analysis is unsupported (encrypted IDE store). Each script detects the host and degrades with a clear message rather than scanning the wrong path. See [Not using Claude Code?](#not-using-claude-code).\n\n- **token-doctor**: diagnoses where your token spend goes (length distribution, marathon share, cache rebuilds, per-project health) and writes a doctor-style terminal report. Opt-in deep dive fans out parallel Haiku subagents over hotspot sessions for habit-level recommendations.\n- **task-profile**: mines sessions into a role-level map of what you actually do with AI, ranked by frequency and friction. Emits a shareable CSV, an interactive HTML explorer, AI-first coaching cards, and up to five skill proposals.\n\n### session-tools: Session Continuity\n\nThree skills for finding past sessions, preserving the current one, and launching autonomous runs.\n\n- **session-search**: finds a specific past session by title, working directory, time range, or free-text content across every transcript on disk. Works on Claude Code / Cowork and Codex; Antigravity degrades with a clear message.\n- **handoff**: writes a tight `HANDOFF.md` resume note at the current working directory so a fresh session can continue without replaying the conversation. No platform dependency; works on Claude Code, Cowork, and Codex.\n- **goal-prompt**: turns a task, plan, or feature request into a ready-to-paste `/goal` command: one measurable end state, a demonstrable proof, and the constraints that must not drift. Targets Claude Code's `/goal` autonomous mode.\n\n### techwolf-brand-kit: Brand Assets\n\nOfficial TechWolf brand assets for AI-generated outputs. Ensures agents use the correct logo files instead of guessing or approximating.\n\n- **TechWolf Logo**: 4 variants (dark, white, mono-dark, mono-white) in SVG and PNG\n- **currentColor SVG**: inline variant that inherits color from parent CSS for themed contexts\n\n### tool-build-kit: Build and Ship Tools\n\nEnd-to-end guide for building an MCP server and bundling your tools into a shareable plugin, from first questions to published distribution. Two sibling skills; each asks who the work is for before building anything, then tailors every phase to that answer.\n\n- **build-mcp**: five phases (analyze, build, deploy, scale, distribute). Establishes audience (personal / org / public) and runtime (local stdio / hosted HTTP) with `AskUserQuestion` before writing a line of code. Builds on the Anthropic `mcp-builder` skill for implementation depth and adds the scope-and-distribution decision flow it lacks. Branch table drives deploy and distribute across five targets; 6 reference files loaded on demand (transports, local deploy, marketplace distribution, scaling, Python and TypeScript quickstarts).\n- **build-plugin**: four phases (analyze, assemble, ship, maintain). Bundles many tools (skills, hooks, agents, MCP servers) into one installable plugin and ships it via a marketplace. Establishes audience and git host with `AskUserQuestion`, then a branch table maps each phase across Just-me / Team-org-GitHub / Team-org-GitLab / Public. Picks up where build-mcp's distribute phase leaves off; 4 reference files loaded on demand (assemble, marketplace, team enablement, maintain).\n\n## Quick start\n\n### Claude Code\n\n```bash\nclaude plugin marketplace add techwolf-ai/ai-first-toolkit\nclaude plugin install ai-firstify@techwolf-ai-first\nclaude plugin install content-studio@techwolf-ai-first\nclaude plugin install people-management@techwolf-ai-first\nclaude plugin install knowledge-base@techwolf-ai-first\nclaude plugin install ai-adoption@techwolf-ai-first\nclaude plugin install session-tools@techwolf-ai-first\nclaude plugin install techwolf-brand-kit@techwolf-ai-first\nclaude plugin install tool-build-kit@techwolf-ai-first\n```\n\n### Codex\n\nSkills follow the [agentskills.io](https://agentskills.io) spec:\n\n```bash\n./install.sh\n./install.sh ai-firstify\n./install.sh content-studio\n./install.sh people-management\n./install.sh knowledge-base\n./install.sh ai-adoption\n./install.sh session-tools\n./install.sh techwolf-brand-kit\n./install.sh tool-build-kit\n```\n\n\nMore install commands
\n\n```bash\n./install.sh list\n./install.sh verify\n./install.sh update ai-firstify\n./install.sh uninstall ai-firstify\n./install.sh --target ~/custom/\n```\n\n**What the installer does:**\n- Installs each skill under `~/.codex/skills//`\n- Adds per-skill metadata for traceability back to the source plugin and version\n- Verifies required files are present after install\n- Copies plugin guidance into `~/.codex/skills/.techwolf-ai-first/plugins//AGENTS.md`\n\n \n\n### Google Antigravity\n\nThe same skills install into Antigravity, which keeps one self-contained dir per plugin under `~/.gemini/config/plugins/`. Pass `--ide antigravity`:\n\n```bash\n./install.sh install --ide antigravity # all plugins\n./install.sh install ai-firstify --ide antigravity # one plugin\n./install.sh install session-tools --ide antigravity # handoff works; session-search degrades\n./install.sh list --ide antigravity\n./install.sh uninstall ai-firstify --ide antigravity\n```\n\nEach plugin installs as `~/.gemini/config/plugins//` with a `plugin.json`, an `installed_version.json`, and a `skills/` directory, the same shape Antigravity uses for its own plugins. For repo-side discovery as a marketplace, Antigravity reads [`.agents/plugins/marketplace.json`](.agents/plugins/marketplace.json) (the vendor-neutral `.agents/` standard), and each plugin carries an Antigravity `plugin.json` marker at `plugins//plugin.json`. Skills are the same `SKILL.md` files used by Claude Code and Codex, no per-target rewrite.\n\n## Repository structure\n\n```\nai-first-toolkit/\n├── .claude-plugin/\n│ └── marketplace.json # Claude Code marketplace manifest\n├── .agents/\n│ └── plugins/\n│ └── marketplace.json # Antigravity / vendor-neutral marketplace manifest\n├── plugins/\n│ ├── ai-firstify/ # Auditor & re-engineer (1 skill, 9 reference docs)\n│ ├── content-studio/ # Content pipeline (8 skills, visual editor, hooks)\n│ ├── people-management/ # Management tooling (8 skills, 5 reference docs)\n│ ├── knowledge-base/ # Evidence-backed KB (4 skills, templates, index + verify scripts)\n│ ├── ai-adoption/ # Claude history analytics (2 skills: token-doctor, task-profile)\n│ ├── session-tools/ # Session continuity (3 skills: session-search, handoff, goal-prompt)\n│ ├── techwolf-brand-kit/ # Brand assets (logo variants in SVG + PNG)\n│ └── tool-build-kit/ # MCP + plugin builder (2 skills: build-mcp, build-plugin)\n├── install.sh # Codex + Antigravity skill installer\n└── README.md\n```\n\nEach plugin lives in `plugins//` with a `.claude-plugin/` manifest, an Antigravity `plugin.json` marker, and a `skills/` directory of `SKILL.md` files shared across all targets. See individual plugin READMEs for details:\n\n- [ai-firstify README](plugins/ai-firstify/README.md)\n- [content-studio README](plugins/content-studio/README.md)\n- [people-management README](plugins/people-management/README.md)\n- [knowledge-base README](plugins/knowledge-base/README.md)\n- [ai-adoption README](plugins/ai-adoption/README.md)\n- [session-tools README](plugins/session-tools/README.md)\n- [techwolf-brand-kit README](plugins/techwolf-brand-kit/README.md)\n- [tool-build-kit README](plugins/tool-build-kit/README.md)\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## License\n\n[MIT](LICENSE). See [CHANGELOG.md](CHANGELOG.md) for release history.\n",
"bytes": 14317,
"sha": "c8b209bf2783bdc9e1e471ad47186281cc9b0ddf472600befc4e2199c5a35d32",
"repo_slug": "techwolf-ai/ai-first-toolkit",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/plg_techwolf_ai_ai_first_toolkit_ai_firstify_413f2f16/readme"
}