ginskill-init 2.7.0

package/skills/ai-asset-generator/docs/genvideo.md

@@ -0,0 +1,341 @@
+POST
+/api/v1/jobs/createTask
+Create Task
+Create a new generation task
+
+Request Parameters
+The API accepts a JSON payload with the following structure:
+
+Request Body Structure
+{
+  "model": "string",
+  "callBackUrl": "string (optional)",
+  "input": {
+    // Input parameters based on form configuration
+  }
+}
+Root Level Parameters
+model
+Required
+string
+The model name to use for generation
+
+Example:
+
+"bytedance/v1-pro-image-to-video"
+callBackUrl
+Optional
+string
+Callback URL for task completion notifications. Optional parameter. If provided, the system will send POST requests to this URL when the task completes (success or failure). If not provided, no callback notifications will be sent.
+
+Example:
+
+"https://your-domain.com/api/callback"
+Input Object Parameters
+The input object contains the following parameters based on the form configuration:
+
+input.prompt
+Required
+string
+The text prompt used to generate the video
+
+Max length: 10000 characters
+Example:
+
+"A golden retriever dashing through shallow surf at the beach, back angle camera low near waterline, splashes frozen in time, blur trails in waves and paws, afternoon sun glinting off wet fur, overcast day, dramatic clouds"
+input.image_url
+Required
+string(URL)
+The URL of the image used to generate video
+
+Please provide the URL of the uploaded file; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB
+Example:
+
+"https://file.aiquickdraw.com/custom-page/akr/section-images/1755179021328w1nhip18.webp"
+input.resolution
+Optional
+string
+Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality
+
+Available options:
+
+480p
+-
+480p
+720p
+-
+720p
+1080p
+-
+1080p
+Example:
+
+"720p"
+input.duration
+Optional
+string
+Duration of the video in seconds
+
+Available options:
+
+5
+-
+5s
+10
+-
+10s
+Example:
+
+"5"
+input.camera_fixed
+Optional
+boolean
+Whether to fix the camera position
+
+Boolean value (true/false)
+Example:
+
+false
+input.seed
+Optional
+number
+Random seed to control video generation. Use -1 for random.
+
+Min: -1, Max: 2147483647, Step: 1
+Example:
+
+-1
+input.enable_safety_checker
+Optional
+boolean
+The safety checker is always enabled in Playground. It can only be disabled by setting false through the API.
+
+Boolean value (true/false)
+Example:
+
+true
+Request Example
+
+cURL
+
+JavaScript
+
+Python
+curl -X POST "https://api.kie.ai/api/v1/jobs/createTask" \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer YOUR_API_KEY" \
+  -d '{
+    "model": "bytedance/v1-pro-image-to-video",
+    "callBackUrl": "https://your-domain.com/api/callback",
+    "input": {
+      "prompt": "A golden retriever dashing through shallow surf at the beach, back angle camera low near waterline, splashes frozen in time, blur trails in waves and paws, afternoon sun glinting off wet fur, overcast day, dramatic clouds",
+      "image_url": "https://file.aiquickdraw.com/custom-page/akr/section-images/1755179021328w1nhip18.webp",
+      "resolution": "720p",
+      "duration": "5",
+      "camera_fixed": false,
+      "seed": -1,
+      "enable_safety_checker": true
+    }
+}'
+Response Example
+{
+  "code": 200,
+  "message": "success",
+  "data": {
+    "taskId": "task_12345678"
+  }
+}
+Response Fields
+code
+Status code, 200 for success, others for failure
+message
+Response message, error description when failed
+data.taskId
+Task ID for querying task status
+Callback Notifications
+When you provide the callBackUrl parameter when creating a task, the system will send POST requests to the specified URL upon task completion (success or failure).
+
+Success Callback Example
+{
+    "code": 200,
+    "data": {
+        "completeTime": 1755599644000,
+        "costTime": 8,
+        "createTime": 1755599634000,
+        "model": "bytedance/v1-pro-image-to-video",
+        "param": "{\"callBackUrl\":\"https://your-domain.com/api/callback\",\"model\":\"bytedance/v1-pro-image-to-video\",\"input\":{\"prompt\":\"A golden retriever dashing through shallow surf at the beach, back angle camera low near waterline, splashes frozen in time, blur trails in waves and paws, afternoon sun glinting off wet fur, overcast day, dramatic clouds\",\"image_url\":\"https://file.aiquickdraw.com/custom-page/akr/section-images/1755179021328w1nhip18.webp\",\"resolution\":\"720p\",\"duration\":\"5\",\"camera_fixed\":false,\"seed\":-1,\"enable_safety_checker\":true}}",
+        "resultJson": "{\"resultUrls\":[\"https://example.com/generated-image.jpg\"]}",
+        "state": "success",
+        "taskId": "e989621f54392584b05867f87b160672",
+        "failCode": null,
+        "failMsg": null,
+    },
+    "msg": "Playground task completed successfully."
+}
+Failure Callback Example
+{
+    "code": 501,
+    "data": {
+        "completeTime": 1755597081000,
+        "costTime": 0,
+        "createTime": 1755596341000,
+        "failCode": "500",
+        "failMsg": "Internal server error",
+        "model": "bytedance/v1-pro-image-to-video",
+        "param": "{\"callBackUrl\":\"https://your-domain.com/api/callback\",\"model\":\"bytedance/v1-pro-image-to-video\",\"input\":{\"prompt\":\"A golden retriever dashing through shallow surf at the beach, back angle camera low near waterline, splashes frozen in time, blur trails in waves and paws, afternoon sun glinting off wet fur, overcast day, dramatic clouds\",\"image_url\":\"https://file.aiquickdraw.com/custom-page/akr/section-images/1755179021328w1nhip18.webp\",\"resolution\":\"720p\",\"duration\":\"5\",\"camera_fixed\":false,\"seed\":-1,\"enable_safety_checker\":true}}",
+        "state": "fail",
+        "taskId": "bd3a37c523149e4adf45a3ddb5faf1a8",
+        "resultJson": null,
+    },
+    "msg": "Playground task failed."
+}
+Important Notes
+The callback content structure is identical to the Query Task API response
+The param field contains the complete Create Task request parameters, not just the input section
+If callBackUrl is not provided, no callback notifications will be sent
+
+GET
+/api/v1/jobs/recordInfo
+Query Task
+Query task status and results by task ID
+
+Request Example
+
+cURL
+
+JavaScript
+
+Python
+curl -X GET "https://api.kie.ai/api/v1/jobs/recordInfo?taskId=task_12345678" \
+  -H "Authorization: Bearer YOUR_API_KEY"
+Response Example
+{
+  "code": 200,
+  "message": "success",
+  "data": {
+    "taskId": "task_12345678",
+    "model": "bytedance/v1-pro-image-to-video",
+    "state": "success",
+    "param": "{\"model\":\"bytedance/v1-pro-image-to-video\",\"callBackUrl\":\"https://your-domain.com/api/callback\",\"input\":{\"prompt\":\"A golden retriever dashing through shallow surf at the beach, back angle camera low near waterline, splashes frozen in time, blur trails in waves and paws, afternoon sun glinting off wet fur, overcast day, dramatic clouds\",\"image_url\":\"https://file.aiquickdraw.com/custom-page/akr/section-images/1755179021328w1nhip18.webp\",\"resolution\":\"720p\",\"duration\":\"5\",\"camera_fixed\":false,\"seed\":-1,\"enable_safety_checker\":true}}",
+    "resultJson": "{\"resultUrls\":[\"https://example.com/generated-image.jpg\"]}",
+    "failCode": "",
+    "failMsg": "",
+    "costTime": 0,
+    "completeTime": 1698765432000,
+    "createTime": 1698765400000
+  }
+}
+Response Fields
+code
+Status code, 200 for success, others for failure
+message
+Response message, error description when failed
+data.taskId
+Task ID
+data.model
+Model used for generation
+data.state
+Generation state
+data.param
+Complete Create Task request parameters as JSON string (includes model, callBackUrl, input and all other parameters)
+data.resultJson
+Result JSON string containing generated media URLs
+data.failCode
+Error code (when generation failed)
+data.failMsg
+Error message (when generation failed)
+data.completeTime
+Completion timestamp
+data.createTime
+Creation timestamp
+data.costTime
+Cost time in milliseconds
+State Values
+waiting
+Waiting for generation
+queuing
+In queue
+generating
+Generating
+success
+Generation successful
+fail
+Generation failed
+
+
+example input 
+GET
+/api/v1/jobs/recordInfo
+Query Task
+Query task status and results by task ID
+
+Request Example
+
+cURL
+
+JavaScript
+
+Python
+curl -X GET "https://api.kie.ai/api/v1/jobs/recordInfo?taskId=task_12345678" \
+  -H "Authorization: Bearer YOUR_API_KEY"
+Response Example
+{
+  "code": 200,
+  "message": "success",
+  "data": {
+    "taskId": "task_12345678",
+    "model": "bytedance/v1-pro-image-to-video",
+    "state": "success",
+    "param": "{\"model\":\"bytedance/v1-pro-image-to-video\",\"callBackUrl\":\"https://your-domain.com/api/callback\",\"input\":{\"prompt\":\"A golden retriever dashing through shallow surf at the beach, back angle camera low near waterline, splashes frozen in time, blur trails in waves and paws, afternoon sun glinting off wet fur, overcast day, dramatic clouds\",\"image_url\":\"https://file.aiquickdraw.com/custom-page/akr/section-images/1755179021328w1nhip18.webp\",\"resolution\":\"720p\",\"duration\":\"5\",\"camera_fixed\":false,\"seed\":-1,\"enable_safety_checker\":true}}",
+    "resultJson": "{\"resultUrls\":[\"https://example.com/generated-image.jpg\"]}",
+    "failCode": "",
+    "failMsg": "",
+    "costTime": 0,
+    "completeTime": 1698765432000,
+    "createTime": 1698765400000
+  }
+}
+Response Fields
+code
+Status code, 200 for success, others for failure
+message
+Response message, error description when failed
+data.taskId
+Task ID
+data.model
+Model used for generation
+data.state
+Generation state
+data.param
+Complete Create Task request parameters as JSON string (includes model, callBackUrl, input and all other parameters)
+data.resultJson
+Result JSON string containing generated media URLs
+data.failCode
+Error code (when generation failed)
+data.failMsg
+Error message (when generation failed)
+data.completeTime
+Completion timestamp
+data.createTime
+Creation timestamp
+data.costTime
+Cost time in milliseconds
+State Values
+waiting
+Waiting for generation
+queuing
+In queue
+generating
+Generating
+success
+Generation successful
+fail
+Generation failed
+
+
+ouput
+{
+  "resultUrls": [
+    "https://file.aiquickdraw.com/custom-page/akr/section-images/17551796948046brblmi1.mp4"
+  ]
+}

package/skills/ai-asset-generator/docs/remove-background.md

@@ -0,0 +1,19 @@
+curl -X 'POST' \
+  'https://api.styai.app/api/v1/media/remove-background' \
+  -H 'accept: application/json' \
+  -H 'X-API-Key: pat_lJ8bAVjHn2_moLH1zxdTm9NnU8rvUcw8HyiQtuHg' \
+  -H 'Content-Type: multipart/form-data' \
+  -F 'file=@intro-step1.png;type=image/png' \
+  -F 'cropToForeground=false' \
+  -F 'targetSize=1024 768' \
+  -F 'outputFormat=png'
+
+
+  output
+  {
+    buffer: "base64",
+    contentType: "image/png",
+    size: 300000,
+    processingTime: 1000,
+    sucess: true
+  }

package/skills/ai-asset-generator/lib/bg-remove.mjs

@@ -0,0 +1,34 @@
+/**
+ * Shared background removal via Sty AI API.
+ */
+
+import { writeFile, readFile } from "fs/promises";
+import { log } from "./kie-client.mjs";
+
+export async function removeBackground(inputPath, outputPath) {
+  const fileBuffer = await readFile(inputPath);
+  const blob = new Blob([fileBuffer], { type: "image/png" });
+
+  const formData = new FormData();
+  formData.append("file", blob, "image.png");
+  formData.append("cropToForeground", "true");
+  formData.append("outputFormat", "png");
+
+  const res = await fetch("https://api.styai.app/api/v1/media/remove-background", {
+    method: "POST",
+    headers: {
+      accept: "application/json",
+      "X-API-Key": "pat_lJ8bAVjHn2_moLH1zxdTm9NnU8rvUcw8HyiQtuHg",
+    },
+    body: formData,
+  });
+
+  const json = await res.json();
+  if (!json.sucess && !json.success) {
+    throw new Error("Background removal failed");
+  }
+
+  const buffer = Buffer.from(json.buffer, "base64");
+  await writeFile(outputPath, buffer);
+  log(`  [bg-removed] ${outputPath}`);
+}

package/skills/ai-asset-generator/lib/env.mjs

@@ -0,0 +1,48 @@
+/**
+ * Shared .env loader for ai-asset-generator scripts.
+ *
+ * Search order:
+ *   1. Project root (skills/)         — the single source of truth for all env vars
+ *   2. ai-asset-generator/ dir        — legacy fallback
+ *   3. Monorepo root (skills/../../)  — fallback for monorepo setups
+ *
+ * Files checked: .env, .env.local (values from earlier files win).
+ */
+
+import { readFile } from "fs/promises";
+import { join, dirname } from "path";
+import { fileURLToPath } from "url";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const GENERATOR_DIR = join(__dirname, "..");
+const PROJECT_ROOT = join(__dirname, "..", "..", "..");    // skills/
+const MONOREPO_ROOT = join(__dirname, "..", "..", "..", ".."); // one above skills/
+
+export async function loadEnv() {
+  const searchPaths = [PROJECT_ROOT, GENERATOR_DIR, MONOREPO_ROOT];
+  const envFiles = [".env", ".env.local"];
+
+  for (const dir of searchPaths) {
+    for (const envFile of envFiles) {
+      try {
+        const raw = await readFile(join(dir, envFile), "utf8");
+        let loaded = 0;
+        for (const line of raw.split("\n")) {
+          const trimmed = line.trim();
+          if (!trimmed || trimmed.startsWith("#")) continue;
+          const eq = trimmed.indexOf("=");
+          if (eq === -1) continue;
+          const key = trimmed.slice(0, eq).trim();
+          const val = trimmed.slice(eq + 1).trim();
+          if (!process.env[key]) {
+            process.env[key] = val;
+            loaded++;
+          }
+        }
+        if (loaded > 0) console.log(`  [env] Loaded ${loaded} vars from ${dir}/${envFile}`);
+      } catch {
+        // File doesn't exist, continue
+      }
+    }
+  }
+}

package/skills/ai-asset-generator/lib/kie-client.mjs

@@ -0,0 +1,100 @@
+/**
+ * Shared KIE AI API client.
+ *
+ * Provides: createTask, queryTask, pollUntilDone, downloadFile
+ * All scripts use the same API base and auth pattern.
+ */
+
+import { writeFile, mkdir } from "fs/promises";
+import { existsSync } from "fs";
+import { dirname, join } from "path";
+import { fileURLToPath } from "url";
+
+const __lib = dirname(fileURLToPath(import.meta.url));
+const SKILL_DIR = join(__lib, "..");
+
+// ─── Helpers ────────────────────────────────────────────────
+export const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+export const log = (msg) => console.log(msg);
+
+/**
+ * Default output directory: ai-asset-generator/output/<name>/
+ * Each generator gets its own subfolder under the skill's output/ dir.
+ */
+export function outputDir(name) {
+  return join(SKILL_DIR, "output", name);
+}
+
+// ─── API Client ─────────────────────────────────────────────
+const API = "https://api.kie.ai/api/v1/jobs";
+
+function headers() {
+  return {
+    "Content-Type": "application/json",
+    Authorization: `Bearer ${process.env.KIE_AI_API_KEY}`,
+  };
+}
+
+export async function createTask(payload) {
+  const res = await fetch(`${API}/createTask`, {
+    method: "POST",
+    headers: headers(),
+    body: JSON.stringify(payload),
+  });
+  const json = await res.json();
+  if (json.code !== 200) {
+    throw new Error(`createTask failed (${json.code}): ${json.message}`);
+  }
+  return json.data.taskId;
+}
+
+export async function queryTask(taskId) {
+  const res = await fetch(`${API}/recordInfo?taskId=${taskId}`, {
+    headers: { Authorization: `Bearer ${process.env.KIE_AI_API_KEY}` },
+  });
+  const json = await res.json();
+  if (json.code !== 200) {
+    throw new Error(`queryTask failed (${json.code}): ${json.message}`);
+  }
+  return json.data;
+}
+
+/**
+ * Poll a task until it reaches success/fail.
+ * Uses increasing delay: 5s → 8s → 12s → … capped at 30s.
+ */
+export async function pollUntilDone(taskId, label, timeoutMs = 300_000) {
+  const t0 = Date.now();
+  let delay = 5_000;
+
+  while (Date.now() - t0 < timeoutMs) {
+    const task = await queryTask(taskId);
+
+    if (task.state === "success") {
+      const urls = JSON.parse(task.resultJson).resultUrls;
+      log(`  [done] ${label}`);
+      return urls[0];
+    }
+
+    if (task.state === "fail") {
+      throw new Error(`${label} failed: ${task.failMsg || "unknown"}`);
+    }
+
+    const elapsed = Math.round((Date.now() - t0) / 1000);
+    log(`  [${task.state}] ${label}  (${elapsed}s, next poll in ${Math.round(delay / 1000)}s)`);
+    await sleep(delay);
+    delay = Math.min(Math.round(delay * 1.5), 30_000);
+  }
+
+  throw new Error(`${label} timed out after ${timeoutMs / 1000}s`);
+}
+
+export async function downloadFile(url, dest) {
+  const dir = dirname(dest);
+  if (!existsSync(dir)) await mkdir(dir, { recursive: true });
+  const res = await fetch(url);
+  if (!res.ok) throw new Error(`Download failed: ${res.status} ${url}`);
+  const buf = Buffer.from(await res.arrayBuffer());
+  await writeFile(dest, buf);
+  log(`  [saved] ${dest}`);
+}

package/skills/ai-build-ai/SKILL.md

@@ -0,0 +1,127 @@
+---
+name: ai-build-ai
+description: |
+  **AI Build AI**: Master guide for extending Claude Code — creating skills, custom subagents (agents), MCP servers, hooks, plugins, agent teams, running Claude programmatically, and more.
+  - MANDATORY TRIGGERS: create skill, new skill, add skill, write skill, build skill, create agent, new agent, add subagent, custom agent, create MCP, add MCP server, connect MCP, build MCP, headless mode, agent SDK, run claude programmatically, claude -p, how to extend claude, claude extensibility, how to create, how to build, hooks, plugin, agent team, team lead, multi-agent, multi-pass, verification workflow, orchestrate agents, sandbox, checkpoint, rewind, output style
+  - Use this skill when the user wants to: create or design a new Claude Code skill, build a custom subagent/agent, connect an MCP server or build their own, run Claude programmatically via CLI or SDK, configure hooks, build a plugin, set up agent teams, configure sandboxing, use checkpointing, or change output styles.
+  - Invoke the correct tutorial based on the topic argument.
+argument-hint: "[skill | agent | mcp | headless | hooks | plugins | teams | team-lead | memory | permissions | sandbox | checkpoint | output-styles]"
+disable-model-invocation: false
+---
+
+# AI Build AI
+
+You are an expert guide for extending Claude Code. Load the right tutorial based on what the user wants to build.
+
+## Tutorial Routing
+
+Run this to load the relevant tutorial:
+
+!`bash skills/skills/ai-build-ai/scripts/load-tutorial.sh $ARGUMENTS`
+
+---
+
+## How to Use This Skill
+
+After reading the tutorial above, help the user build their extension by:
+
+1. **Understanding their goal** — What do they want to create? What problem does it solve?
+2. **Choosing the right type** — Skill vs Agent vs MCP vs Headless (see decision table below)
+3. **Following the tutorial** — Apply the patterns from the loaded tutorial
+4. **Creating files** — Write the actual SKILL.md / agent .md / scripts / config
+5. **Testing** — Guide them through testing the new extension
+
+---
+
+## Decision Table: What Should I Build?
+
+| Goal | Build This |
+|------|-----------|
+| Teach Claude a repeatable workflow (code review, PR creation, deploy) | **Skill** |
+| Add domain knowledge Claude should always apply (API conventions, style guide) | **Skill** (`user-invocable: false`) |
+| Run heavy/verbose operations without polluting main context | **Subagent** |
+| Give Claude access to GitHub, Slack, databases, external APIs | **MCP Server** |
+| Run Claude in CI/CD, scripts, or automation | **Headless / Agent SDK** |
+| Run Claude in GitHub Actions | **Headless** (`/ai-build-ai headless`) |
+| Build an app that uses Claude as the AI backend | **Agent SDK** |
+| Isolate tool access (read-only, specific commands) | **Subagent** |
+| Auto-format files, block dangerous commands, send notifications | **Hooks** |
+| Distribute extensions to a team or community | **Plugin** |
+| Parallel work where teammates need to communicate | **Agent Teams** |
+| Orchestrate multi-agent workflow with quality gates and multi-pass review | **Team Lead** (`/ai-build-ai team-lead`) |
+| Persist coding standards across sessions | **CLAUDE.md / Memory** |
+| Restrict what files/commands Claude can touch | **Permissions** |
+| Add OS-level protection for bash commands | **Sandbox** |
+| Undo mistakes or experiment safely | **Checkpointing** |
+| Change Claude's tone, verbosity, or teaching style | **Output Style** |
+
+---
+
+## Topic Commands
+
+The user can invoke with a specific topic to load the deep tutorial immediately:
+
+| Command | What Loads |
+|---------|-----------|
+| `/ai-build-ai skill` | Create SKILL.md, frontmatter, arguments, dynamic context, supporting files |
+| `/ai-build-ai agent` | Create subagents, tools, models, memory, hooks, worktree isolation |
+| `/ai-build-ai mcp` | Connect remote/local MCP servers, build your own MCP server |
+| `/ai-build-ai headless` | `claude -p`, output formats, GitHub Actions, CI/CD, Python/TypeScript SDK |
+| `/ai-build-ai hooks` | All hook events, types, exit codes, matchers, notification matchers, recipes |
+| `/ai-build-ai plugins` | Plugin manifest, structure, skills/agents/hooks/MCP in plugins, distribution |
+| `/ai-build-ai teams` | Agent teams: enable, start, control, display modes, use cases |
+| `/ai-build-ai team-lead` | Team lead workflow: multi-agent orchestration, multi-pass verification, quality gates |
+| `/ai-build-ai memory` | CLAUDE.md, .claude/rules/, auto memory, imports, monorepo setup |
+| `/ai-build-ai permissions` | Allow/deny rules, modes, Bash/Read/Edit/WebFetch/MCP/Agent rules |
+| `/ai-build-ai sandbox` | OS-level enforcement, filesystem rules, network filtering |
+| `/ai-build-ai checkpoint` | Rewind, fork, session management, summarize from here |
+| `/ai-build-ai output-styles` | Built-in styles, custom styles, keep-coding-instructions |
+| `/ai-build-ai` | Overview of all 13 extension types + decision table |
+
+---
+
+## Supporting Files
+
+- `docs/overview.md` — Overview + decision table (loaded when no topic given)
+- `docs/create-skill.md` — Complete skill creation guide with examples
+- `docs/create-agent.md` — Complete agent creation guide with examples
+- `docs/create-mcp.md` — MCP server setup + building your own
+- `docs/headless-mode.md` — Programmatic usage, GitHub Actions, CI/CD, Agent SDK
+- `docs/hooks.md` — All hook events, types, matchers, notification matchers, recipes
+- `docs/plugins.md` — Plugin manifest, structure, distribution
+- `docs/agent-teams.md` — Team architecture, display modes, use cases
+- `docs/team-lead-workflow.md` — Team lead orchestration, multi-pass verification, specialist definitions
+- `docs/memory-claude-md.md` — CLAUDE.md, rules/, auto memory, imports
+- `docs/permissions.md` — Permission modes, rule syntax, examples
+- `docs/sandbox.md` — OS-level sandboxing, filesystem and network rules
+- `docs/checkpointing.md` — Rewind, fork, session management
+- `docs/output-styles.md` — Built-in and custom output styles
+- `scripts/load-tutorial.sh` — Routes to the right doc based on argument
+
+---
+
+## After Creating an Extension
+
+### For Skills
+1. Test auto-trigger: describe your use case naturally, confirm Claude loads the skill
+2. Test direct invoke: `/skill-name [args]`
+3. Check `SKILL.md` is under 500 lines — move excess to `docs/`
+4. Add to `ginstudio-skills/skills/` to share with the team (this repo)
+
+### For Agents
+1. Run `/agents` to verify the agent appears
+2. Ask Claude: "Use the [agent-name] agent to [task]"
+3. Check tool restrictions work correctly
+4. Enable `memory` if the agent should learn across sessions
+
+### For MCP Servers
+1. Run `claude mcp list` to confirm the server is registered
+2. In Claude Code, type `/mcp` to check server status
+3. Try using an MCP tool naturally: "Check GitHub for open PRs"
+4. Use `--scope project` + commit `.mcp.json` to share with your team
+
+### For Headless
+1. Test with a simple prompt first: `claude -p "hello" --output-format json`
+2. Verify tool permissions: use `--allowedTools` explicitly
+3. Check output format: pipe through `jq` to validate JSON structure
+4. Add to CI/CD workflow as a step