@mikulgohil/ai-kit 1.8.0 → 1.8.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +207 -141
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -1,46 +1,36 @@
1
- # AI Kit
1
+ <p align="center">
2
+ <strong style="font-size: 2em;">AI Kit</strong>
3
+ </p>
4
+
5
+ <h3 align="center">Make AI coding assistants actually useful.</h3>
6
+
7
+ <p align="center">
8
+ One command. Project-aware AI from the first conversation.
9
+ </p>
10
+
11
+ <p align="center">
12
+ <a href="https://www.npmjs.com/package/@mikulgohil/ai-kit"><img src="https://img.shields.io/npm/v/@mikulgohil/ai-kit.svg?style=flat-square&color=blue" alt="npm version" /></a>
13
+ <a href="https://www.npmjs.com/package/@mikulgohil/ai-kit"><img src="https://img.shields.io/npm/dm/@mikulgohil/ai-kit.svg?style=flat-square&color=green" alt="npm downloads" /></a>
14
+ <a href="https://github.com/mikulgohil/ai-kit/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/@mikulgohil/ai-kit.svg?style=flat-square" alt="license" /></a>
15
+ <a href="https://github.com/mikulgohil/ai-kit"><img src="https://img.shields.io/github/stars/mikulgohil/ai-kit?style=flat-square&color=yellow" alt="GitHub stars" /></a>
16
+ </p>
17
+
18
+ <p align="center">
19
+ <a href="https://ai-kit.mikul.me">Documentation</a> &nbsp;&middot;&nbsp;
20
+ <a href="https://ai-kit.mikul.me/getting-started">Getting Started</a> &nbsp;&middot;&nbsp;
21
+ <a href="https://ai-kit.mikul.me/cli-reference">CLI Reference</a> &nbsp;&middot;&nbsp;
22
+ <a href="https://ai-kit.mikul.me/slash-commands">Skills</a> &nbsp;&middot;&nbsp;
23
+ <a href="https://ai-kit.mikul.me/agents">Agents</a> &nbsp;&middot;&nbsp;
24
+ <a href="https://ai-kit.mikul.me/changelog">Changelog</a>
25
+ </p>
2
26
 
3
- **Make AI coding assistants actually useful.**
4
- One command. Project-aware AI from the first conversation.
5
-
6
- [![npm version](https://img.shields.io/npm/v/@mikulgohil/ai-kit.svg)](https://www.npmjs.com/package/@mikulgohil/ai-kit)
7
- [![npm downloads](https://img.shields.io/npm/dm/@mikulgohil/ai-kit.svg)](https://www.npmjs.com/package/@mikulgohil/ai-kit)
8
- [![license](https://img.shields.io/npm/l/@mikulgohil/ai-kit.svg)](https://github.com/mikulgohil/ai-kit/blob/main/LICENSE)
9
-
10
- > **[Read the full documentation](https://ai-kit.mikul.me)** | [Getting Started](https://ai-kit.mikul.me/getting-started) | [CLI Reference](https://ai-kit.mikul.me/cli-reference) | [Skills & Commands](https://ai-kit.mikul.me/slash-commands) | [Hooks](https://ai-kit.mikul.me/hooks) | [Agents](https://ai-kit.mikul.me/agents) | [Changelog](https://ai-kit.mikul.me/changelog)
27
+ ---
11
28
 
12
29
  ```bash
13
30
  npx @mikulgohil/ai-kit init
14
31
  ```
15
32
 
16
- ---
17
-
18
- ## Problems AI Kit Solves
19
-
20
- Every team using AI coding assistants hits these problems. AI Kit solves each one.
21
-
22
- | # | Problem | How AI Kit Solves It |
23
- |---|---------|---------------------|
24
- | 1 | **AI forgets everything each session** — Every new chat starts from zero. No memory of project rules, patterns, or past decisions. | Generates a persistent `CLAUDE.md` with project rules, conventions, and stack details. The AI knows your project from the first prompt, every time. |
25
- | 2 | **AI generates wrong framework patterns** — Writes Pages Router code when you use App Router. Uses CSS when you use Tailwind. Creates default exports when your project uses named exports. | Auto-detects your exact stack (framework, router, CMS, styling, TypeScript config) and generates rules specific to your setup. The AI can't use the wrong patterns. |
26
- | 3 | **Developers write bad prompts** — Vague or incorrect prompts lead to wrong code, wasted time, and rework. Junior developers waste the most time. | Ships **46 pre-built skills** so developers don't write prompts from scratch — just run `/review`, `/security-check`, `/new-component`, `/refactor`, etc. |
27
- | 4 | **Same mistakes happen repeatedly** — No system to track what went wrong, so the team keeps hitting the same build failures and lint errors. | Generates a **mistakes log** (`docs/mistakes-log.md`) with **auto-capture hook** that logs every build/lint failure automatically. The AI references it to avoid repeating them. |
28
- | 5 | **Every developer gets different AI behavior** — No consistency in how the team uses AI tools, leading to inconsistent code quality and style. | One `ai-kit init` command generates the same rules for the entire team — everyone's AI follows identical project standards. Commit the generated files to the repo. |
29
- | 6 | **No quality checks on AI-generated code** — AI output goes straight to PR without type checking, linting, or security review. | Automated **hooks** run formatting, type-checking, linting, and git safety checks in real-time as the AI writes code. **Quality gate** runs everything before merge. |
30
- | 7 | **AI generates insecure code** — No guardrails for secrets exposure, XSS, SQL injection, or other vulnerabilities. AI doesn't scan its own output. | Built-in **security audit** scans for exposed secrets, OWASP risks, and misconfigurations. **Security review agent** catches issues at development time, not production. |
31
- | 8 | **AI can't handle multi-file reasoning** — Changes to one component break related files. AI loses context across linked models and shared types. | **10 specialized agents** with focused expertise — planner, code-reviewer, build-resolver, doc-updater, refactor-cleaner — each maintains context for their domain. |
32
- | 9 | **No decision trail** — Nobody remembers why a technical decision was made 3 months ago. Knowledge walks out the door when developers leave. | Auto-scaffolds a **decisions log** (`docs/decisions-log.md`) to capture what was decided, why, and by whom — fully searchable and traceable. |
33
- | 10 | **Onboarding takes too long** — New developers spend days understanding the project and its AI setup before they can contribute. | AI Kit generates developer guides and project-aware configurations — new team members get productive AI assistance from day one with zero manual setup. |
34
- | 11 | **Context gets repeated every conversation** — You explain the same conventions in every session: import order, naming, component structure, testing patterns. | All conventions are encoded in the generated rules file. The AI reads them automatically at session start. You explain once, it remembers forever. |
35
- | 12 | **AI doesn't improve over time** — The AI makes the same wrong suggestions regardless of past feedback, team patterns, or previous failures. | The system **learns as you use it** — mistakes log, decisions log, and updated rules mean the AI gets smarter with every session. Mistakes auto-capture builds the log organically. |
36
- | 13 | **Complex tasks need multiple manual AI passes** — Developers manually coordinate review + test + docs updates across separate conversations. | **Multi-agent orchestration** runs multiple specialized agents in parallel — review, test, document, and refactor in one command with `/orchestrate`. |
37
- | 14 | **Switching AI tools means starting over** — Moving from Cursor to Claude Code (or vice versa) loses all configuration and project context. | Generates configs for **5+ AI tools** (Claude Code, Cursor, Windsurf, Aider, Cline) from a single source — switch tools without losing project knowledge. |
38
- | 15 | **AI creates components without tests, docs, or types** — Every AI-generated file needs manual follow-up to add what was missed. | Skills like `/new-component` enforce a structured workflow: asks 10 questions, reads existing patterns, generates component + types + tests + docs together. |
39
- | 16 | **No visibility into AI usage costs** — Management has no idea how many tokens the team is consuming or which projects cost the most. | Built-in **token tracking** provides daily/weekly/monthly usage summaries, per-project cost breakdown, budget alerts, and ROI estimates. |
40
- | 17 | **Cursor copies entire modules instead of targeted edits** — AI bloats the repo with unnecessary file duplication, especially in CMS and monorepo setups. | Generated rules include explicit instructions for editing patterns — update in place, respect package boundaries, follow existing structure. Rules prevent over-generation. |
41
- | 18 | **No component-level AI awareness** — AI doesn't know which components have tests, stories, Sitecore integration, or documentation gaps. | **Component scanner** discovers all React components and generates `.ai.md` docs with health scores, props tables, Sitecore field mappings, and dependency trees. |
42
- | 19 | **Setup is manual and error-prone** — Configuring AI assistants requires deep knowledge of each tool's config format. Most teams skip it entirely. | **Zero manual configuration** — one command auto-detects your stack and generates everything. Update with one command when the project evolves. |
43
- | 20 | **AI hallucinates framework-specific APIs** — Generates incorrect hook usage, wrong data fetching patterns, or non-existent component APIs for your framework version. | Stack-specific template fragments include exact API patterns for your detected framework version (e.g., Next.js 15 App Router patterns, Sitecore Content SDK v2 patterns). |
33
+ > **48 pre-built skills** &nbsp;·&nbsp; **16 specialized agents** &nbsp;·&nbsp; **5+ AI tools supported** &nbsp;·&nbsp; **30-second setup**
44
34
 
45
35
  ---
46
36
 
@@ -64,13 +54,13 @@ npx @mikulgohil/ai-kit health
64
54
  |---|---|
65
55
  | `CLAUDE.md` | Project-aware rules for Claude Code — your stack, conventions, and patterns |
66
56
  | `.cursorrules` + `.cursor/rules/*.mdc` | Same rules formatted for Cursor AI with scoped file matching |
67
- | 46 Skills | Auto-discovered workflows — `/review`, `/new-component`, `/security-check`, `/pre-pr`, and 42 more |
68
- | 10 Agents | Specialized AI assistants — planner, reviewer, security, E2E, build-resolver, ci-debugger, and more |
69
- | 3 Context Modes | Switch between dev (build fast), review (check quality), and research (understand code) |
70
- | Automated Hooks | Auto-format, TypeScript checks, console.log warnings, mistakes auto-capture, git safety |
71
- | 6 Guides | Developer playbooks for prompts, tokens, hooks, agents, Figma workflow |
72
- | Doc Scaffolds | Mistakes log, decisions log, time log — structured knowledge tracking |
73
- | Component Docs | Auto-generated `.ai.md` per component with health scores and Sitecore integration |
57
+ | **48 Skills** | Auto-discovered workflows — `/review`, `/new-component`, `/security-check`, `/pre-pr`, and more |
58
+ | **16 Agents** | Specialized AI assistants — planner, reviewer, security, architect, build-resolver, and more |
59
+ | **3 Context Modes** | Switch between dev (build fast), review (check quality), and research (understand code) |
60
+ | **Automated Hooks** | Auto-format, TypeScript checks, console.log warnings, mistakes auto-capture, git safety |
61
+ | **6 Guides** | Developer playbooks for prompts, tokens, hooks, agents, Figma workflow |
62
+ | **Doc Scaffolds** | Mistakes log, decisions log, time log — structured knowledge tracking |
63
+ | **Component Docs** | Auto-generated `.ai.md` per component with health scores and Sitecore integration |
74
64
 
75
65
  ---
76
66
 
@@ -89,45 +79,71 @@ Scans your `package.json`, config files, and directory structure to detect your
89
79
  | Turborepo monorepo | Workspace conventions, cross-package imports |
90
80
  | Figma + design tokens | Token mapping, design-to-code workflow |
91
81
 
92
- ### 46 Pre-Built Skills
82
+ <br />
83
+
84
+ ### 48 Pre-Built Skills
93
85
 
94
86
  Structured AI workflows applied automatically — the AI recognizes what you're doing and loads the right skill:
95
87
 
96
88
  | Category | Skills |
97
89
  |---|---|
98
- | Getting Started | `prompt-help`, `understand` |
99
- | Building | `new-component`, `new-page`, `api-route`, `error-boundary`, `extract-hook`, `figma-to-code`, `design-tokens`, `schema-gen`, `storybook-gen`, `scaffold-spec` |
100
- | Quality & Review | `review`, `pre-pr`, `test`, `accessibility-audit`, `security-check`, `responsive-check`, `type-fix`, `perf-audit`, `bundle-check`, `i18n-check`, `test-gaps` |
101
- | Maintenance | `fix-bug`, `refactor`, `optimize`, `migrate`, `dep-check`, `sitecore-debug`, `upgrade` |
102
- | Workflow | `document`, `commit-msg`, `env-setup`, `changelog`, `release`, `pr-description`, `standup`, `learn-from-pr`, `release-notes` |
103
- | Session | `save-session`, `resume-session`, `checkpoint` |
104
- | Orchestration | `orchestrate`, `quality-gate`, `harness-audit` |
90
+ | **Getting Started** | `prompt-help`, `understand` |
91
+ | **Building** | `new-component`, `new-page`, `api-route`, `error-boundary`, `extract-hook`, `figma-to-code`, `design-tokens`, `schema-gen`, `storybook-gen`, `scaffold-spec` |
92
+ | **Quality & Review** | `review`, `pre-pr`, `test`, `accessibility-audit`, `security-check`, `responsive-check`, `type-fix`, `perf-audit`, `bundle-check`, `i18n-check`, `test-gaps` |
93
+ | **Maintenance** | `fix-bug`, `refactor`, `optimize`, `migrate`, `dep-check`, `sitecore-debug`, `upgrade` |
94
+ | **Workflow** | `document`, `commit-msg`, `env-setup`, `changelog`, `release`, `pr-description`, `standup`, `learn-from-pr`, `release-notes` |
95
+ | **Session** | `save-session`, `resume-session`, `checkpoint` |
96
+ | **Orchestration** | `orchestrate`, `quality-gate`, `harness-audit` |
105
97
 
106
- ### 10 Specialized Agents
98
+ <br />
107
99
 
108
- | Agent | Purpose | Conditional |
109
- |---|---|---|
110
- | `planner` | Break features into implementation plans | No |
111
- | `code-reviewer` | Deep quality and security review | No |
112
- | `security-reviewer` | OWASP Top 10, XSS, CSRF, secrets detection | No |
113
- | `build-resolver` | Diagnose and fix build/type errors | No |
114
- | `doc-updater` | Keep documentation in sync with code | No |
115
- | `refactor-cleaner` | Find and remove dead code | No |
116
- | `tdd-guide` | Test-driven development guidance and workflow | No |
117
- | `ci-debugger` | CI/CD failure debugger — analyzes logs and suggests fixes | No |
118
- | `e2e-runner` | Playwright tests with Page Object Model | Yes — Playwright only |
119
- | `sitecore-specialist` | Sitecore XM Cloud patterns and debugging | Yes — Sitecore only |
100
+ ### 16 Specialized Agents
101
+
102
+ | Agent | Purpose |
103
+ |---|---|
104
+ | `@planner` | Break features into implementation plans with dependencies and risk assessment |
105
+ | `@code-reviewer` | Deep quality review — patterns, performance, types, and conventions |
106
+ | `@security-reviewer` | OWASP Top 10, XSS, CSRF, secrets detection, and auth flow analysis |
107
+ | `@build-resolver` | Diagnose and fix build errors, type conflicts, and dependency issues |
108
+ | `@doc-updater` | Keep documentation in sync with code changes automatically |
109
+ | `@refactor-cleaner` | Find and remove dead code, unused imports, and unnecessary complexity |
110
+ | `@tdd-guide` | Test-driven development workflow — red, green, refactor with guidance |
111
+ | `@ci-debugger` | Analyze CI/CD failures, parse logs, and suggest targeted fixes |
112
+ | `@e2e-runner` | Playwright tests with Page Object Model and smart selectors |
113
+ | `@sitecore-specialist` | XM Cloud patterns, Content SDK v2, Experience Edge, and field helpers |
114
+ | `@architect` | SSR/SSG/ISR strategy, component hierarchy, data flow, and rendering patterns |
115
+ | `@data-scientist` | ML pipelines, model evaluation, data analysis, and experiment tracking |
116
+ | `@performance-profiler` | Core Web Vitals, bundle analysis, runtime profiling, and rendering optimization |
117
+ | `@migration-specialist` | Framework upgrades, breaking change detection, codemods, and incremental adoption |
118
+ | `@dependency-auditor` | Vulnerability scanning, outdated packages, license compliance, and bundle impact |
119
+ | `@api-designer` | REST/GraphQL API design, schema validation, versioning, and error handling |
120
+
121
+ <br />
120
122
 
121
123
  ### Automated Quality Hooks
122
124
 
123
125
  | Profile | What Runs Automatically |
124
126
  |---|---|
125
- | Minimal | Auto-format + git push safety |
126
- | Standard | + TypeScript type-check + console.log warnings + mistakes auto-capture + bundle impact warning |
127
- | Strict | + ESLint check + stop-time console.log audit + pre-commit AI review + bundle impact warning |
127
+ | **Minimal** | Auto-format + git push safety |
128
+ | **Standard** | + TypeScript type-check + console.log warnings + mistakes auto-capture + bundle impact warning |
129
+ | **Strict** | + ESLint check + stop-time console.log audit + pre-commit AI review + bundle impact warning |
128
130
 
129
131
  **Mistakes auto-capture** — When a build/lint command fails, the hook logs the error to `docs/mistakes-log.md` with timestamp and error preview. The mistakes log builds itself over time.
130
132
 
133
+ <br />
134
+
135
+ ### Multi-Tool Support
136
+
137
+ | Tool | Output |
138
+ |---|---|
139
+ | **Claude Code** | `CLAUDE.md` + skills + agents + contexts + hooks |
140
+ | **Cursor** | `.cursorrules` + `.cursor/rules/*.mdc` + skills |
141
+ | **Windsurf** | `.windsurfrules` (via `ai-kit export`) |
142
+ | **Aider** | `.aider.conf.yml` (via `ai-kit export`) |
143
+ | **Cline** | `.clinerules` (via `ai-kit export`) |
144
+
145
+ <br />
146
+
131
147
  ### Component Scanner & Docs
132
148
 
133
149
  Discovers all React components and generates `.ai.md` documentation:
@@ -136,6 +152,8 @@ Discovers all React components and generates `.ai.md` documentation:
136
152
  - Sitecore details: datasource fields, rendering params, placeholders, GraphQL queries
137
153
  - Smart merge — updates auto-generated sections while preserving manual edits
138
154
 
155
+ <br />
156
+
139
157
  ### Project Health Dashboard
140
158
 
141
159
  ```bash
@@ -144,6 +162,8 @@ npx @mikulgohil/ai-kit health
144
162
 
145
163
  One-glance view across 5 sections: setup integrity, security, stack detection, tools/MCP, and documentation. Outputs an A-F grade with actionable recommendations.
146
164
 
165
+ <br />
166
+
147
167
  ### Token Tracking & Cost Estimates
148
168
 
149
169
  ```bash
@@ -152,16 +172,6 @@ npx @mikulgohil/ai-kit tokens
152
172
 
153
173
  Period summaries, budget progress with alerts, per-project cost breakdown, week-over-week trends, model recommendations (Sonnet vs Opus), and ROI estimates.
154
174
 
155
- ### Multi-Tool Support
156
-
157
- | Tool | Output |
158
- |---|---|
159
- | Claude Code | `CLAUDE.md` + skills + agents + contexts + hooks |
160
- | Cursor | `.cursorrules` + `.cursor/rules/*.mdc` + skills |
161
- | Windsurf | `.windsurfrules` (via `ai-kit export`) |
162
- | Aider | `.aider.conf.yml` (via `ai-kit export`) |
163
- | Cline | `.clinerules` (via `ai-kit export`) |
164
-
165
175
  ---
166
176
 
167
177
  ## CLI Commands
@@ -171,48 +181,83 @@ Period summaries, budget progress with alerts, per-project cost breakdown, week-
171
181
  | `ai-kit init [path]` | Scan project and generate all configs |
172
182
  | `ai-kit update [path]` | Re-scan and update generated files (safe merge) |
173
183
  | `ai-kit reset [path]` | Remove all AI Kit generated files |
174
- | `ai-kit health [path]` | One-glance project health dashboard |
184
+ | `ai-kit health [path]` | One-glance A-F project health dashboard |
175
185
  | `ai-kit audit [path]` | Security and configuration health audit |
176
- | `ai-kit doctor [path]` | Diagnose setup issues |
186
+ | `ai-kit doctor [path]` | Diagnose setup issues and misconfigurations |
177
187
  | `ai-kit diff [path]` | Preview what would change on update (dry run) |
178
188
  | `ai-kit tokens` | Token usage summary and cost estimates |
179
- | `ai-kit stats [path]` | Project complexity metrics |
189
+ | `ai-kit stats [path]` | Project complexity metrics and analysis |
180
190
  | `ai-kit export [path]` | Export rules to Windsurf, Aider, Cline |
181
191
  | `ai-kit patterns [path]` | Generate pattern library from recurring code patterns |
182
192
  | `ai-kit dead-code [path]` | Find unused components and dead code |
183
193
  | `ai-kit drift [path]` | Detect drift between code and .ai.md docs |
194
+ | `ai-kit component-registry [path]` | Generate component catalog for AI discovery |
184
195
 
185
196
  ---
186
197
 
187
- ## Supported Tech Stacks
198
+ ## The Impact
188
199
 
189
- | Category | Technologies |
190
- |---|---|
191
- | Frameworks | Next.js (App Router, Pages Router, Hybrid), React |
192
- | CMS | Sitecore XM Cloud (Content SDK v2), Sitecore JSS |
193
- | Styling | Tailwind CSS (v3 + v4), SCSS, CSS Modules, styled-components |
194
- | Language | TypeScript (with strict mode detection) |
195
- | Formatters | Prettier, Biome (auto-detected for hooks) |
196
- | Monorepos | Turborepo, Nx, Lerna, pnpm workspaces |
197
- | Design | Figma MCP, Figma Code CLI, design tokens, visual tests |
198
- | Testing | Playwright, Storybook, axe-core |
199
- | Quality | ESLint, Snyk, Knip, @next/bundle-analyzer |
200
- | Package Managers | npm, pnpm, yarn, bun |
200
+ | Metric | Before AI Kit | After AI Kit |
201
+ |---|---|---|
202
+ | Context setup per conversation | 5-10 min | **0 min** (auto-loaded) |
203
+ | Code review cycles per PR | 2-4 rounds | **1-2 rounds** |
204
+ | Component creation time | 30-60 min | **10-15 min** |
205
+ | New developer onboarding | 1-2 weeks | **2-3 days** |
206
+ | Security issues caught | At PR review or production | **At development time** |
207
+ | Knowledge retention | Lost when developers leave | **Logged in decisions & mistakes** |
208
+ | AI tool switching cost | Start over from scratch | **Zero — same rules, 5+ tools** |
209
+ | AI-generated code quality | Inconsistent, needs fixing | **Follows project standards** |
201
210
 
202
211
  ---
203
212
 
204
- ## The Impact
213
+ <details>
214
+ <summary><strong>20 Problems AI Kit Solves</strong> (click to expand)</summary>
205
215
 
206
- | Metric | Before AI Kit | After AI Kit |
207
- |---|---|---|
208
- | Context setup per conversation | 5-10 min | 0 min (auto-loaded) |
209
- | Code review cycles per PR | 2-4 rounds | 1-2 rounds |
210
- | Component creation time | 30-60 min | 10-15 min |
211
- | New developer onboarding | 1-2 weeks | 2-3 days |
212
- | Security issues caught | At PR review or production | At development time |
213
- | Knowledge retention | Lost when developers leave | Logged in decisions and mistakes |
214
- | AI tool switching cost | Start over from scratch | Zero — same rules across 5+ tools |
215
- | AI-generated code quality | Inconsistent, needs manual fixing | Follows project standards automatically |
216
+ <br />
217
+
218
+ Every team using AI coding assistants hits these problems. AI Kit solves each one.
219
+
220
+ | # | Problem | How AI Kit Solves It |
221
+ |---|---------|---------------------|
222
+ | 1 | **AI forgets everything each session** — Every new chat starts from zero. | Generates a persistent `CLAUDE.md` with project rules, conventions, and stack details. The AI knows your project from the first prompt, every time. |
223
+ | 2 | **AI generates wrong framework patterns** — Writes Pages Router code when you use App Router. | Auto-detects your exact stack and generates rules specific to your setup. The AI can't use the wrong patterns. |
224
+ | 3 | **Developers write bad prompts** — Vague prompts lead to wrong code and rework. | Ships **48 pre-built skills** — just run `/review`, `/security-check`, `/new-component`, etc. |
225
+ | 4 | **Same mistakes happen repeatedly** — No system to track what went wrong. | Generates a **mistakes log** with **auto-capture hook** that logs every build/lint failure automatically. |
226
+ | 5 | **Every developer gets different AI behavior** — No consistency across the team. | One `ai-kit init` generates the same rules for everyone. Commit the files to the repo. |
227
+ | 6 | **No quality checks on AI-generated code** — AI output goes straight to PR. | Automated **hooks** run formatting, type-checking, linting, and git safety checks in real-time. |
228
+ | 7 | **AI generates insecure code** — No guardrails for secrets, XSS, SQL injection. | Built-in **security audit** + **security review agent** catches issues at development time. |
229
+ | 8 | **AI can't handle multi-file reasoning** — Changes to one component break others. | **16 specialized agents** with focused expertise, each maintaining context for their domain. |
230
+ | 9 | **No decision trail** — Nobody remembers why decisions were made 3 months ago. | Auto-scaffolds a **decisions log** to capture what was decided, why, and by whom. |
231
+ | 10 | **Onboarding takes too long** — New developers spend days understanding the project. | New team members get productive AI assistance from day one with zero manual setup. |
232
+ | 11 | **Context gets repeated every conversation** — Same conventions explained every session. | All conventions encoded in generated rules. The AI reads them automatically at session start. |
233
+ | 12 | **AI doesn't improve over time** — Same wrong suggestions regardless of past feedback. | Mistakes log, decisions log, and updated rules mean the AI gets smarter every session. |
234
+ | 13 | **Complex tasks need multiple manual AI passes** — Manual coordination across conversations. | **Multi-agent orchestration** runs specialists in parallel with `/orchestrate`. |
235
+ | 14 | **Switching AI tools means starting over** — Moving tools loses all configuration. | Generates configs for **5+ tools** from a single source — switch without losing context. |
236
+ | 15 | **AI creates components without tests, docs, or types** — Every file needs follow-up. | Skills like `/new-component` enforce structured workflows: component + types + tests + docs together. |
237
+ | 16 | **No visibility into AI usage costs** — No idea how many tokens the team consumes. | Built-in **token tracking** with daily/weekly/monthly summaries and cost breakdown. |
238
+ | 17 | **Cursor copies entire modules instead of targeted edits** — AI bloats the repo. | Generated rules include explicit instructions for editing patterns — update in place. |
239
+ | 18 | **No component-level AI awareness** — AI doesn't know which components have gaps. | **Component scanner** discovers all components and generates `.ai.md` docs with health scores. |
240
+ | 19 | **Setup is manual and error-prone** — Configuring AI assistants requires deep knowledge. | **Zero manual configuration** — one command auto-detects and generates everything. |
241
+ | 20 | **AI hallucinates framework-specific APIs** — Generates incorrect patterns for your version. | Stack-specific templates include exact API patterns for your detected framework version. |
242
+
243
+ </details>
244
+
245
+ ---
246
+
247
+ ## Supported Tech Stacks
248
+
249
+ | Category | Technologies |
250
+ |---|---|
251
+ | **Frameworks** | Next.js (App Router, Pages Router, Hybrid), React |
252
+ | **CMS** | Sitecore XM Cloud (Content SDK v2), Sitecore JSS |
253
+ | **Styling** | Tailwind CSS (v3 + v4), SCSS, CSS Modules, styled-components |
254
+ | **Language** | TypeScript (with strict mode detection) |
255
+ | **Formatters** | Prettier, Biome (auto-detected for hooks) |
256
+ | **Monorepos** | Turborepo, Nx, Lerna, pnpm workspaces |
257
+ | **Design** | Figma MCP, Figma Code CLI, design tokens, visual tests |
258
+ | **Testing** | Playwright, Storybook, axe-core |
259
+ | **Quality** | ESLint, Snyk, Knip, @next/bundle-analyzer |
260
+ | **Package Managers** | npm, pnpm, yarn, bun |
216
261
 
217
262
  ---
218
263
 
@@ -228,6 +273,23 @@ Period summaries, budget progress with alerts, per-project cost breakdown, week-
228
273
 
229
274
  ---
230
275
 
276
+ ## How AI Kit Compares
277
+
278
+ | Capability | AI Kit | Spec-Driven Tools |
279
+ |---|---|---|
280
+ | **Setup** | Auto-detect — zero config | Manual spec writing |
281
+ | **Stack awareness** | Scans package.json, configs, dirs | User describes stack |
282
+ | **Rules generation** | Auto-generated from stack | User-written specs |
283
+ | **Multi-tool support** | 5+ tools, single source | Varies |
284
+ | **Quality hooks** | Built-in (3 profiles) | Extension-dependent |
285
+ | **Security audit** | Built-in CLI command | Extension-dependent |
286
+ | **Token tracking** | Built-in with cost estimates | Not available |
287
+ | **Component awareness** | Auto-scanned with health scores | Not available |
288
+
289
+ > **AI Kit's philosophy**: Auto-detect everything possible, only ask for what can't be inferred.
290
+
291
+ ---
292
+
231
293
  ## Updating
232
294
 
233
295
  When your project evolves:
@@ -240,64 +302,68 @@ Only content between `AI-KIT:START/END` markers is refreshed. Your custom rules
240
302
 
241
303
  ---
242
304
 
305
+ ## Roadmap
306
+
307
+ | Feature | Description | Status |
308
+ |---|---|---|
309
+ | **Project Constitution** | `/constitution` — governance doc with coding standards, testing philosophy, performance budgets | Planned |
310
+ | **Spec-First Workflow** | `/specify` — structured feature specs with user stories and acceptance criteria before code | Planned |
311
+ | **Extension Catalog** | Community-contributed agents, skills, and templates. Install with `ai-kit extension install` | Planned |
312
+ | **Preset Bundles** | Curated bundles: `enterprise`, `startup`, `sitecore-xmc`, `fullstack`. Apply with `ai-kit preset apply` | Planned |
313
+ | **Setup Comparison** | `ai-kit compare` — gap analysis comparing your setup against other spec-driven tools | Planned |
314
+
315
+ ---
316
+
317
+ ## Requirements
318
+
319
+ - Node.js 18+
320
+ - A project with `package.json`
321
+ - Claude Code or Cursor (at least one AI tool)
322
+
323
+ ---
324
+
243
325
  ## Documentation
244
326
 
245
- **[ai-kit.mikul.me](https://ai-kit.mikul.me)**
327
+ Full documentation at **[ai-kit.mikul.me](https://ai-kit.mikul.me)**
246
328
 
247
329
  | Page | What You'll Learn |
248
330
  |---|---|
249
331
  | [Getting Started](https://ai-kit.mikul.me/getting-started) | Step-by-step setup walkthrough |
250
- | [CLI Reference](https://ai-kit.mikul.me/cli-reference) | All 13 commands with examples |
251
- | [Skills & Commands](https://ai-kit.mikul.me/slash-commands) | All 46 skills with usage guides |
332
+ | [CLI Reference](https://ai-kit.mikul.me/cli-reference) | All 14 commands with examples |
333
+ | [Skills & Commands](https://ai-kit.mikul.me/slash-commands) | All 48 skills with usage guides |
252
334
  | [What Gets Generated](https://ai-kit.mikul.me/what-gets-generated) | Detailed breakdown of every generated file |
253
335
  | [Hooks](https://ai-kit.mikul.me/hooks) | Hook profiles, mistakes auto-capture |
254
- | [Agents](https://ai-kit.mikul.me/agents) | 10 specialized agents |
336
+ | [Agents](https://ai-kit.mikul.me/agents) | 16 specialized agents |
255
337
  | [Changelog](https://ai-kit.mikul.me/changelog) | Version history and release notes |
256
338
 
257
339
  ---
258
340
 
259
- ## Roadmap
341
+ ## Need Expert Help?
260
342
 
261
- Features planned for upcoming releases, inspired by best practices from the spec-driven development ecosystem.
343
+ Whether you're rolling out AI-assisted development across your organization or need a tailored setup for a complex project — I can help.
262
344
 
263
- | Feature | Description | Status |
264
- |---|---|---|
265
- | **Project Constitution** | `/constitution` skill — generate a `PROJECT_PRINCIPLES.md` governance doc that defines coding standards, testing philosophy, performance budgets, and accessibility targets. AI agents reference it before every decision. | Planned |
266
- | **Spec-First Workflow** | `/specify` skill — create structured feature specs (`specs/<feature>.md`) with user stories, acceptance criteria, and edge cases *before* writing code. Planner agent references specs during implementation. | Planned |
267
- | **Extension Catalog** | Community-contributed agents, skills, and template fragments. Install with `ai-kit extension install <name>`. Standard manifest format for third-party contributions. | Planned |
268
- | **Preset Bundles** | Curated workflow bundles for common project types: `enterprise` (strict compliance), `startup` (fast iteration), `sitecore-xmc` (XM Cloud best practices), `fullstack` (full-stack Next.js). Apply with `ai-kit preset apply <name>`. | Planned |
269
- | **Setup Comparison** | `ai-kit compare` — gap analysis comparing your AI Kit setup against other spec-driven tools. Shows what's covered and what's missing. | Planned |
270
-
271
- See [plan.md](./plan.md) for detailed implementation plans.
345
+ | Service | Description |
346
+ |---|---|
347
+ | **Project Setup** | Custom AI Kit configuration tailored to your stack, conventions, and workflow |
348
+ | **Team Rollout** | Deploy AI Kit across your team with shared presets, skills, and agents |
349
+ | **Training & Workshops** | Help your developers get the most out of AI-assisted development |
350
+ | **Custom Extensions** | Build custom skills, agents, and hooks specific to your organization |
272
351
 
273
352
  ---
274
353
 
275
- ## How AI Kit Compares
354
+ ## Author
276
355
 
277
- | Capability | AI Kit | Spec-Driven Tools (e.g., Spec Kit) |
278
- |---|---|---|
279
- | **Setup** | Auto-detect — zero manual config | Manual spec writing required |
280
- | **Stack awareness** | Scans package.json, configs, directory structure | User describes stack in specs |
281
- | **Rules generation** | Auto-generated from detected stack | User-written specifications |
282
- | **Multi-tool support** | 5+ tools from single source | Varies by tool |
283
- | **Quality hooks** | Built-in (minimal/standard/strict profiles) | Extension-dependent |
284
- | **Security audit** | Built-in CLI command | Extension-dependent |
285
- | **Token tracking** | Built-in with cost estimates | Not available |
286
- | **Component awareness** | Auto-scanned with health scores | Not available |
287
- | **Extension ecosystem** | Coming soon | Community catalog available |
288
- | **Project principles** | Coming soon (`/constitution`) | Available (`/speckit.constitution`) |
289
- | **Spec-first workflow** | Coming soon (`/specify`) | Core feature |
356
+ **Mikul Gohil** — Senior developer and tech lead specializing in Sitecore, Next.js, and AI-assisted development workflows. Building tools that make development teams more productive.
290
357
 
291
- **AI Kit's philosophy**: Auto-detect everything possible, only ask for what can't be inferred. Spec-driven tools require manual specification upfront. Both approaches have merit — AI Kit is adding spec-first capabilities as an *optional* layer on top of auto-detection.
358
+ <p>
359
+ <a href="https://www.mikul.me">mikul.me</a> &nbsp;&middot;&nbsp;
360
+ <a href="https://github.com/mikulgohil">GitHub</a> &nbsp;&middot;&nbsp;
361
+ <a href="https://www.linkedin.com/in/mikulgohil">LinkedIn</a> &nbsp;&middot;&nbsp;
362
+ <a href="https://x.com/mikulgohil">Twitter / X</a>
363
+ </p>
292
364
 
293
365
  ---
294
366
 
295
- ## Requirements
296
-
297
- - Node.js 18+
298
- - A project with `package.json`
299
- - Claude Code or Cursor (at least one AI tool)
300
-
301
367
  ## License
302
368
 
303
369
  MIT — [github.com/mikulgohil/ai-kit](https://github.com/mikulgohil/ai-kit)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mikulgohil/ai-kit",
3
- "version": "1.8.0",
3
+ "version": "1.8.1",
4
4
  "description": "AI-assisted development setup kit. Auto-detects your tech stack and generates tailored CLAUDE.md, .cursorrules, hooks, agents, context modes, slash commands, design token rules, component registries, developer guides, project principles, and spec-first workflows.",
5
5
  "type": "module",
6
6
  "bin": {