openryoko 2026.8.21 → 2026.8.27

package/template/docs/org.md

@@ -4,7 +4,7 @@
 
 ## Employee Personas
 
-Employee files live at `~/.jinn/org/<department>/<name>.yaml`.
+Employee files live at `~/.ryoko/org/<department>/<name>.yaml`.
 
 ```yaml
 name: alice
@@ -33,10 +33,10 @@ persona: |
 
 ## Departments
 
-Each department is a directory under `~/.jinn/org/` containing:
+Each department is a directory under `~/.ryoko/org/` containing:
 
 ```
-~/.jinn/org/engineering/
+~/.ryoko/org/engineering/
   department.yaml     # Department metadata
   board.json          # Shared task board
   alice.yaml          # Employee persona
@@ -90,16 +90,22 @@ Task fields: `id`, `title`, `assignee`, `status` (open, in-progress, done, block
 
 ## Default Organization
 
-{{portalName}} ships with a single executive employee:
+`org/` starts empty. {{portalName}} itself is the executive (COO) and is not
+defined as an org employee — employees are the workers {{portalName}} delegates to.
+
+The onboarding skill proposes a starter scaffold matched to the user's profile
+(e.g. an `engineering/` department with a `dev-assistant` employee for a solo
+developer), and the management skill handles hiring from there. An employee
+file looks like:
 
 ```yaml
-name: {{portalSlug}}
-displayName: {{portalName}}
-department: executive
-rank: executive
+name: dev-assistant
+displayName: Dev Assistant
+department: engineering
+rank: employee
 engine: claude
-model: opus
+model: claude-opus-5
 persona: |
-  You are {{portalName}}, the executive AI assistant and gateway administrator.
-  You manage the organization, delegate tasks, and handle direct requests.
+  You are a careful software engineer. You implement tasks assigned by
+  {{portalName}}, report progress on the board, and escalate blockers.
 ```

package/template/docs/overview.md

@@ -1,6 +1,6 @@
 # {{portalName}} Overview
 
-{{portalName}} is a lightweight AI gateway daemon that wraps professional AI CLI tools as "engines." It is published as `jinn-cli`.
+{{portalName}} is a lightweight AI gateway daemon that wraps professional AI CLI tools as "engines." It is published as `openryoko`.
 
 ## Core Principle
 
@@ -22,9 +22,10 @@ Traditional approaches build custom tool-calling loops, manage context windows,
 ## Directory Structure
 
 ```
-~/.jinn/
+~/.ryoko/
   config.yaml          # Gateway configuration
-  jinn.db             # SQLite session registry
+  sessions/
+    registry.db        # SQLite session registry
   docs/                # These reference docs
   skills/              # Skill directories with SKILL.md files
   cron/

package/template/docs/self-modification.md

@@ -1,6 +1,6 @@
 # Self-Modification
 
-{{portalName}}'s engines operate within `~/.jinn/` and can modify any file in that directory. This enables {{portalName}} to update its own configuration, create skills, manage cron jobs, and restructure the organization at runtime.
+{{portalName}}'s engines operate within `~/.ryoko/` and can modify any file in that directory. This enables {{portalName}} to update its own configuration, create skills, manage cron jobs, and restructure the organization at runtime.
 
 ## What {{portalName}} Can Edit
 
@@ -25,7 +25,7 @@ Changes take effect immediately. No restart required.
 
 ## Safety Guidelines
 
-Engines have full file access within `~/.jinn/`. To avoid breaking the gateway:
+Engines have full file access within `~/.ryoko/`. To avoid breaking the gateway:
 
 ### Do
 
@@ -38,28 +38,28 @@ Engines have full file access within `~/.jinn/`. To avoid breaking the gateway:
 ### Do Not
 
 - Break `config.yaml` structure — invalid YAML will prevent config reload
-- Corrupt `jinn.db` — the SQLite database is managed by the gateway process
+- Corrupt `sessions/registry.db` — the SQLite database is managed by the gateway process
 - Write invalid JSON to `jobs.json` — this will cancel all cron jobs with nothing to replace them
 - Delete the `docs/` directory — these reference docs are needed for self-awareness
-- Modify files outside `~/.jinn/` unless explicitly instructed by the user
+- Modify files outside `~/.ryoko/` unless explicitly instructed by the user
 
 ## Example: Creating a Cron Job at Runtime
 
 An engine can create a new cron job by reading `cron/jobs.json`, appending a new entry, and writing it back:
 
 ```
-1. Read ~/.jinn/cron/jobs.json
+1. Read ~/.ryoko/cron/jobs.json
 2. Parse the JSON array
 3. Append new job object with unique id, schedule, prompt, etc.
 4. Validate the full array
-5. Write back to ~/.jinn/cron/jobs.json
+5. Write back to ~/.ryoko/cron/jobs.json
 6. The file watcher automatically reschedules all jobs
 ```
 
 ## Example: Adding a New Employee
 
 ```
-1. Create ~/.jinn/org/<department>/<name>.yaml with required fields
+1. Create ~/.ryoko/org/<department>/<name>.yaml with required fields
 2. The file watcher detects the new file and rebuilds the employee registry
 3. The new employee is immediately available for @mention routing
 ```

package/template/docs/skills.md

@@ -4,7 +4,7 @@ Skills are markdown instruction sets that engines read and follow. There is no r
 
 ## How Skills Work
 
-Each skill is a directory in `~/.jinn/skills/` containing at minimum a `SKILL.md` file. When an engine starts a session, it has access to the skills directory and can read any skill's instructions.
+Each skill is a directory in `~/.ryoko/skills/` containing at minimum a `SKILL.md` file. When an engine starts a session, it has access to the skills directory and can read any skill's instructions.
 
 The `SKILL.md` file contains:
 - **Trigger description**: When this skill should be activated
@@ -14,7 +14,7 @@ The `SKILL.md` file contains:
 ## Creating a Skill
 
 ```
-~/.jinn/skills/
+~/.ryoko/skills/
   my-skill/
     SKILL.md          # Required: instructions
     data.json         # Optional: supporting data
@@ -41,13 +41,16 @@ When the user says "deploy" or asks about deployment status.
 
 ## Pre-packaged Skills
 
-{{portalName}} ships with several default skills:
+{{portalName}} ships with these default skills (see `~/.ryoko/skills/`):
 
-- **self**: Instructions for {{portalName}} to understand and modify its own configuration
-- **slack**: Slack-specific behavior and formatting guidelines
-- **cron**: How to create and manage scheduled jobs
-- **org**: Working with the organization structure and employee personas
-- **skills**: Meta-skill for creating and managing other skills
+- **onboarding**: First-run setup — fills IDENTITY.md / SOUL.md / MEMORY.md interactively
+- **management**: Hiring, firing, promotions, delegation, and board reviews for the org
+- **cron-manager**: Create, edit, enable/disable, and troubleshoot cron jobs
+- **skill-creator**: Write a SKILL.md playbook to create a new skill
+- **find-and-install**: Discover skills via `npx skills find` and install them
+- **self-heal**: Diagnose and repair {{portalName}}'s own configuration and runtime
+- **migrate**: Apply pending version migrations
+- **sync** / **new** / **status**: Slash-command playbooks (`/sync`, `/new`, `/status`)
 
 ## Key Points
 

package/template/skills/cron-manager/SKILL.md

@@ -11,7 +11,7 @@ This skill activates when the user wants to create, edit, delete, enable, disabl
 
 ## Data File
 
-All cron jobs are stored in `~/.jinn/cron/jobs.json` as a JSON array of job objects. If the file does not exist, create it with an empty array `[]`.
+All cron jobs are stored in `cron/jobs.json` (relative to the {{portalName}} home directory, which is always your working directory) as a JSON array of job objects. If the file does not exist, create it with an empty array `[]`.
 
 ## CronJob Schema
 
@@ -51,7 +51,7 @@ Field details:
 
 ### Creating a Job
 
-1. Read the current `~/.jinn/cron/jobs.json` (or initialize as `[]` if missing).
+1. Read the current `cron/jobs.json` (or initialize as `[]` if missing).
 2. Ask the user for the required fields: name, schedule, engine, model, and prompt.
 3. Ask about the timezone. Default to `UTC` if not specified.
 4. Ask about the employee persona to use. This is optional.
@@ -60,12 +60,12 @@ Field details:
 7. Generate a UUID for the `id` field.
 8. Set `enabled` to `true` by default.
 9. Append the new job object to the array.
-10. Write the updated array back to `~/.jinn/cron/jobs.json`.
+10. Write the updated array back to `cron/jobs.json`.
 11. Confirm the creation and summarize the schedule in plain English.
 
 ### Editing a Job
 
-1. Read `~/.jinn/cron/jobs.json`.
+1. Read `cron/jobs.json`.
 2. Find the job by name or id.
 3. Show the current values to the user.
 4. Apply the requested changes.
@@ -74,7 +74,7 @@ Field details:
 
 ### Deleting a Job
 
-1. Read `~/.jinn/cron/jobs.json`.
+1. Read `cron/jobs.json`.
 2. Find the job by name or id.
 3. Confirm deletion with the user (show job details).
 4. Remove the job from the array.
@@ -83,7 +83,7 @@ Field details:
 
 ### Enabling / Disabling a Job
 
-1. Read `~/.jinn/cron/jobs.json`.
+1. Read `cron/jobs.json`.
 2. Find the job by name or id.
 3. Set `enabled` to `true` (enable) or `false` (disable).
 4. Write the updated array back.
@@ -91,7 +91,7 @@ Field details:
 
 ### Listing Jobs
 
-1. Read `~/.jinn/cron/jobs.json`.
+1. Read `cron/jobs.json`.
 2. Display jobs in a readable format, grouped by enabled/disabled.
 3. Include name, schedule (with plain-English interpretation), timezone, engine, and delivery info.
 

package/template/skills/management/SKILL.md

@@ -11,7 +11,7 @@ This skill activates when the user wants to manage their organization: hiring or
 
 ## Organization Structure
 
-The organization lives under the `org/` directory in the {{portalName}} home folder (`~/.jinn/org/`). Each department is a subdirectory containing employee persona YAML files and a task board.
+The organization lives under `org/` in the {{portalName}} home directory — which is always your working directory, so relative paths in this skill resolve correctly on any instance. Each department is a subdirectory containing employee persona YAML files and a task board.
 
 ```
 org/

package/template/skills/self-heal/SKILL.md

@@ -11,11 +11,11 @@ This skill activates when {{portalName}} is experiencing issues, errors, or unex
 
 ## Diagnostic Steps
 
-Work through these checks in order. Stop and fix issues as you find them.
+Work through these checks in order. Stop and fix issues as you find them. All relative paths below are relative to the {{portalName}} home directory, which is always your working directory.
 
 ### 1. Check Gateway Logs
 
-Read `~/.jinn/logs/gateway.log` and look for:
+Read the newest log file under `logs/` and look for:
 - Error messages or stack traces
 - Repeated failures or crash loops
 - Connection refused or timeout errors
@@ -26,7 +26,7 @@ Summarize any problems found to the user.
 
 ### 2. Validate Configuration
 
-Read `~/.jinn/config.yaml` and verify:
+Read `config.yaml` and verify:
 - The file is valid YAML (no syntax errors)
 - The `port` field is a valid number (typically 3777)
 - Required fields are present: `port`, `engine`, `model`
@@ -44,13 +44,13 @@ If the engine command is not found, inform the user that the engine is not insta
 ### 4. Check Session Database
 
 Look at the session registry for stuck sessions:
-- Read `~/.jinn/sessions.db` or the session storage
+- Read `sessions/registry.db` (the SQLite session registry)
 - Look for sessions with status `running` that have not been updated recently (more than 30 minutes old)
 - These may be stuck and need to be reset
 
 ### 5. Check Disk and Temp Files
 
-- Check if `~/.jinn/tmp/` contains stale files that should be cleaned up
+- Check if `tmp/` contains stale files that should be cleaned up
 - Large or numerous temp files can cause issues
 
 ## Common Fixes
@@ -68,7 +68,7 @@ jinn stop && jinn start
 
 If temp files are stale or causing issues:
 
-Delete all contents of `~/.jinn/tmp/` but keep the directory itself.
+Delete all contents of `tmp/` but keep the directory itself.
 
 ### Fix Malformed JSON
 
@@ -104,7 +104,7 @@ If the gateway cannot bind to its configured port:
 
 ## Reference
 
-For understanding {{portalName}}'s architecture and component relationships, refer to the documentation in `~/.jinn/docs/` if available.
+For understanding {{portalName}}'s architecture and component relationships, refer to the documentation in `docs/` if available.
 
 ## Error Handling
 

package/template/skills/skill-creator/SKILL.md

@@ -11,25 +11,25 @@ This skill activates when the user wants to create a new custom skill for {{port
 
 ## Output Location
 
-All skills are stored at `~/.jinn/skills/<skill-name>/SKILL.md`. Each skill lives in its own directory named with kebab-case.
+All skills are stored at `skills/<skill-name>/SKILL.md`. Each skill lives in its own directory named with kebab-case.
 
 ## Behavior by Engine
 
 ### Claude Code (claude engine)
 
-Claude Code has native skill creation capabilities. Defer to the engine's built-in skill/memory system when available. The engine knows how to create well-structured instruction files. Simply ensure the output file lands at the correct path: `~/.jinn/skills/<skill-name>/SKILL.md`.
+Claude Code has native skill creation capabilities. Defer to the engine's built-in skill/memory system when available. The engine knows how to create well-structured instruction files. Simply ensure the output file lands at the correct path: `skills/<skill-name>/SKILL.md`.
 
 ### Codex (codex engine)
 
-Create the SKILL.md file manually following the conventions below. Write the file directly to `~/.jinn/skills/<skill-name>/SKILL.md`.
+Create the SKILL.md file manually following the conventions below. Write the file directly to `skills/<skill-name>/SKILL.md`.
 
 ## Steps
 
 1. Ask the user what the skill should do. Get a clear description of the capability.
 2. Ask for a name (kebab-case). Suggest one if the user does not provide it.
-3. Create the directory `~/.jinn/skills/<skill-name>/` if it does not exist.
+3. Create the directory `skills/<skill-name>/` if it does not exist.
 4. Generate the SKILL.md content following the conventions below.
-5. Write the file to `~/.jinn/skills/<skill-name>/SKILL.md`.
+5. Write the file to `skills/<skill-name>/SKILL.md`.
 6. Confirm the skill was created and summarize what it does.
 
 ## Conventions for Writing Good SKILL.md Files
@@ -47,12 +47,12 @@ Bad: "This skill does reporting stuff."
 
 Provide numbered steps that an AI engine can follow without ambiguity. Each step should be a concrete action, not a vague directive.
 
-Good: "1. Read the file at `~/.jinn/data/repos.json`. 2. For each repository, fetch the latest commits from the past 7 days."
+Good: "1. Read the file at `data/repos.json`. 2. For each repository, fetch the latest commits from the past 7 days."
 Bad: "1. Get the data. 2. Process it."
 
 ### 3. Data File References
 
-Specify exact file paths for any data the skill reads or writes. Use `~/.jinn/` as the base directory. Define the expected schema for any JSON or YAML files.
+Specify exact file paths for any data the skill reads or writes, relative to the {{portalName}} home directory (always the working directory). Define the expected schema for any JSON or YAML files.
 
 ### 4. Error Handling Guidance
 
@@ -84,7 +84,7 @@ This skill activates when <specific trigger description>.
 
 ## Data Files
 
-- `~/.jinn/<path>` — <description of the file and its format>
+- `<path>` — <description of the file and its format>
 
 ## Steps
 
@@ -103,7 +103,7 @@ This skill activates when <specific trigger description>.
 
 ## Auto-Sync
 
-The gateway automatically creates symlinks in `~/.jinn/.claude/skills/` and `~/.jinn/.agents/skills/` pointing to each skill directory. This happens on startup and whenever the `skills/` directory changes. You do not need to manage symlinks manually.
+The gateway automatically creates symlinks in `.claude/skills/` and `.agents/skills/` pointing to each skill directory. This happens on startup and whenever the `skills/` directory changes. You do not need to manage symlinks manually.
 
 ## Error Handling
 

package/dist/web/__next._head.txt

@@ -1,6 +0,0 @@
-1:"$Sreact.fragment"
-2:I[84459,["/_next/static/chunks/0y3dnnq~kxyz_.js","/_next/static/chunks/14ge_q22f0n.f.js","/_next/static/chunks/0~6m1p5hnsx2f.js"],"ViewportBoundary"]
-3:I[84459,["/_next/static/chunks/0y3dnnq~kxyz_.js","/_next/static/chunks/14ge_q22f0n.f.js","/_next/static/chunks/0~6m1p5hnsx2f.js"],"MetadataBoundary"]
-4:"$Sreact.suspense"
-5:I[93236,["/_next/static/chunks/0y3dnnq~kxyz_.js","/_next/static/chunks/14ge_q22f0n.f.js","/_next/static/chunks/0~6m1p5hnsx2f.js"],"IconMark"]
-0:{"rsc":["$","$1","h",{"children":[null,["$","$L2",null,{"children":[["$","meta","0",{"charSet":"utf-8"}],["$","meta","1",{"name":"viewport","content":"width=device-width, initial-scale=1, maximum-scale=1, user-scalable=no"}]]}],["$","div",null,{"hidden":true,"children":["$","$L3",null,{"children":["$","$4",null,{"name":"Next.Metadata","children":[["$","title","0",{"children":"OpenRyoko"}],["$","meta","1",{"name":"description","content":"OpenRyoko — Slackで空気を読んで働くAIゲートウェイ"}],["$","link","2",{"rel":"icon","href":"/icon.jpg?icon.0.wpl4.d-5bkf.jpg","sizes":"800x800","type":"image/jpeg"}],["$","link","3",{"rel":"apple-touch-icon","href":"/apple-icon.jpg?apple-icon.0.wpl4.d-5bkf.jpg","sizes":"800x800","type":"image/jpeg"}],["$","$L5","4",{}]]}]}]}],null]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"UDwWEfKiZ-eIOpfOIPKQr"}

package/dist/web/__next._index.txt

@@ -1,6 +0,0 @@
-1:"$Sreact.fragment"
-2:I[3971,["/_next/static/chunks/0y3dnnq~kxyz_.js","/_next/static/chunks/14ge_q22f0n.f.js","/_next/static/chunks/0~6m1p5hnsx2f.js"],"ClientProviders"]
-3:I[87979,["/_next/static/chunks/0y3dnnq~kxyz_.js","/_next/static/chunks/14ge_q22f0n.f.js","/_next/static/chunks/0~6m1p5hnsx2f.js"],"default"]
-4:I[35855,["/_next/static/chunks/0y3dnnq~kxyz_.js","/_next/static/chunks/14ge_q22f0n.f.js","/_next/static/chunks/0~6m1p5hnsx2f.js"],"default"]
-:HL["/_next/static/chunks/103zsy0q9psfj.css","style"]
-0:{"rsc":["$","$1","c",{"children":[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/chunks/103zsy0q9psfj.css","precedence":"next"}],["$","script","script-0",{"src":"/_next/static/chunks/0y3dnnq~kxyz_.js","async":true}],["$","script","script-1",{"src":"/_next/static/chunks/14ge_q22f0n.f.js","async":true}],["$","script","script-2",{"src":"/_next/static/chunks/0~6m1p5hnsx2f.js","async":true}]],["$","html",null,{"lang":"ja","suppressHydrationWarning":true,"children":[["$","head",null,{"children":["$","script",null,{"dangerouslySetInnerHTML":{"__html":"(function(){try{var t=localStorage.getItem('openryoko-theme')||localStorage.getItem('jinn-theme')||'ryoko';if(t==='system'){t=window.matchMedia('(prefers-color-scheme:dark)').matches?'dark':'ryoko'}document.documentElement.setAttribute('data-theme',t)}catch(e){}})()"}}]}],["$","body",null,{"children":["$","$L2",null,{"children":["$","$L3",null,{"parallelRouterKey":"children","template":["$","$L4",null,{}],"notFound":[[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":404}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],[]]}]}]}]]}]]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"UDwWEfKiZ-eIOpfOIPKQr"}