Ocas Vesper logo

Ocas Vesper

Community
jiaxiaojunQAQ
ocas-vesper

Daily briefing generator. Aggregates signals from across the system into concise morning and evening briefings. Surfaces outcomes, opportunities, and decisions in natural language without exposing internal processes. Use for morning/evening briefings, on-demand briefings, or pending decision review. Do not use for deep research (Sift), pattern analysis (Corvus), or message drafting (Dispatch).

Overview

PublisherjiaxiaojunQAQ
RepositorySkillJect
Skill nameocas-vesper
Stars
79
Forks
8
Bundled files
6
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jiaxiaojunQAQ on GitHub. Read the source before you install it.

Installation

Install the Ocas Vesper AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jiaxiaojunQAQ/SkillJect.git /tmp/SkillJect
mkdir -p .claude/skills
cp -r /tmp/SkillJect/data/skills_sample/ocas-vesper-2.0.0 .claude/skills/ocas-vesper
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ocas Vesper in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ocas Vesper on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ocas Vesper is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Vesper

Vesper generates concise daily briefings by aggregating signals from across the system. It presents outcomes and opportunities in natural assistant language while hiding internal processes.

When to use

  • Generate morning or evening briefing
  • Request an on-demand briefing
  • Check pending decision requests
  • Configure briefing schedule or sections

When not to use

  • Deep research — use Sift
  • Pattern analysis — use Corvus
  • Message drafting — use Dispatch
  • Action execution — use relevant domain skill

Responsibility boundary

Vesper owns briefing generation, signal aggregation, and decision presentation.

Vesper does not own: pattern analysis (Corvus), web research (Sift), communications delivery (Dispatch), action decisions (Praxis).

Vesper receives InsightProposal files from Corvus. Vesper may request Dispatch to deliver briefings.

Commands

  • vesper.briefing.morning — generate morning briefing
  • vesper.briefing.evening — generate evening briefing
  • vesper.briefing.manual — on-demand briefing
  • vesper.decisions.pending — list unacted decision requests
  • vesper.config.set — update schedule, sections, delivery
  • vesper.status — last briefing time, pending decisions, schedule
  • vesper.journal — write journal for the current run; called at end of every run

Invocation modes

  • Automatic morning — during configured morning window
  • Automatic evening — during configured evening window
  • Manual — on user request

Signal filtering rules

Include: actionable information, meaningful outcomes, plan-affecting changes, multi-signal opportunities, preparation-useful information.

Exclude: routine background activity, already-experienced events, internal system reasoning, speculative observations.

Evening-specific: no past weather, no summaries of attended meetings.

Read references/signal_filtering.md for full rules.

Formatting rules

  • Conversational paragraphs, not bullet dumps
  • Section headers use emoji: 📅 Today, ✉️ Messages, 🧭 Logistics, 📈 Markets, 🔐 Decisions, 🛠 System
  • Links use [[artifact name]] format
  • Weather in opening paragraph, no section header
  • Decision requests: option, benefit, cost — framed as optional
  • Opportunities surfaced without exposing underlying analysis

Read references/briefing_templates.md for structure and examples.

Behavior constraints

  • No nagging — ignored decisions are treated as intentional
  • No internal system terminology
  • No references to architecture or analysis processes
  • No speculative observations
  • Only concrete outcomes and actionable opportunities

Inter-skill interfaces

Vesper receives InsightProposal files from Corvus at: ~/openclaw/data/ocas-vesper/intake/{proposal_id}.json

Vesper checks its intake during briefing generation. Applies signal filtering rules before including. After processing each file, move to intake/processed/.

See spec-ocas-interfaces.md for the InsightProposal schema and handoff contract.

Storage layout

~/openclaw/data/ocas-vesper/
  config.json
  briefings.jsonl
  signals_evaluated.jsonl
  decisions_presented.jsonl
  decisions.jsonl
  intake/
    {proposal_id}.json
    processed/

~/openclaw/journals/ocas-vesper/
  YYYY-MM-DD/
    {run_id}.json

The OCAS_ROOT environment variable overrides ~/openclaw if set.

Default config.json:

json
{
  "skill_id": "ocas-vesper",
  "skill_version": "2.0.0",
  "config_version": "1",
  "created_at": "",
  "updated_at": "",
  "schedule": {
    "morning_window": "07:00-09:00",
    "evening_window": "17:00-19:00",
    "timezone": "America/Los_Angeles"
  },
  "sections": {
    "today": true,
    "messages": true,
    "logistics": true,
    "markets": true,
    "decisions": true,
    "system": true
  },
  "retention": {
    "days": 30,
    "max_records": 10000
  }
}

OKRs

Universal OKRs from spec-ocas-journal.md apply to all runs.

yaml
skill_okrs:
  - name: signal_precision
    metric: fraction of included signals rated actionable by user
    direction: maximize
    target: 0.85
    evaluation_window: 30_runs
  - name: terminology_compliance
    metric: fraction of briefings free of internal system terminology
    direction: maximize
    target: 1.0
    evaluation_window: 30_runs
  - name: decision_framing
    metric: fraction of decision requests including option, benefit, and cost
    direction: maximize
    target: 1.0
    evaluation_window: 30_runs

Optional skill cooperation

  • Corvus — receives InsightProposal files via intake directory
  • Dispatch — may request Dispatch to deliver briefings
  • Rally — reads portfolio outcome signals
  • Calendar/Weather — reads external context for briefing content

Journal outputs

Action Journal — every briefing generation run.

Visibility

public

Support file map

File | When to read references/schemas.md | Before creating briefings, sections, or decision requests references/briefing_templates.md | Before generating briefing content references/signal_filtering.md | Before evaluating signals for inclusion references/journal.md | Before vesper.journal; at end of every run

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ocas Vesper AI skill do?

Daily briefing generator. Aggregates signals from across the system into concise morning and evening briefings. Surfaces outcomes, opportunities, and decisions in natural language without exposing internal processes. Use for morning/evening briefings, on-demand briefings, or pending decision review. Do not use for deep research (Sift), pattern analysis (Corvus), or message drafting (Dispatch).

Why use Ocas Vesper on TypingMind?

Because you install it once and use it with any model. Ocas Vesper is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ocas Vesper in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jiaxiaojunQAQ/SkillJect/tree/main/data/skills_sample/ocas-vesper-2.0.0. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ocas Vesper?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ocas Vesper?

As many as you like. As long as a model supports skills, you can use Ocas Vesper with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ocas Vesper AI skill free?

It is published on GitHub by jiaxiaojunQAQ. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇