mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-06-11 02:33:10 +08:00
feat: publish ECC 2.0 skill pack surfaces
This commit is contained in:
Affaan Mustafa
75
docs/releases/2.0.0-rc.1/ito-prediction-market-skill-pack.md
Normal file
75
docs/releases/2.0.0-rc.1/ito-prediction-market-skill-pack.md
Normal file
@@ -0,0 +1,75 @@
|
||||
# Itô Prediction-Market Skill Pack
|
||||
|
||||
This rc.1 note records a public teaser skill pack that connects ECC's skill
|
||||
distribution loop with Itô prediction-market workflows while keeping the two
|
||||
businesses separate.
|
||||
|
||||
ECC remains the open agent-harness substrate and ECC Tools remains the hosted
|
||||
GitHub App / Pro surface. Itô remains a separate prediction-market basket
|
||||
business. The link is distribution: ECC can ship reusable skills that make
|
||||
agents better at researching, comparing, explaining, and planning around
|
||||
prediction-market baskets. Live Itô API access stays gated.
|
||||
|
||||
## Included Skills
|
||||
|
||||
| Skill | Use |
|
||||
| --- | --- |
|
||||
| `ito-market-intelligence` | Source-grounded event, underlier, venue, liquidity, and news context |
|
||||
| `ito-basket-compare` | Compare baskets against a knowledge base, portfolio notes, financial context, or thesis |
|
||||
| `ito-trade-planner` | Build a manual, non-advisory worksheet for market and venue review |
|
||||
| `ito-data-atlas-agent` | Design background research/drafting agents with human edit points |
|
||||
| `prediction-market-oracle-research` | Treat prediction markets as data/oracle inputs for agents and decision intelligence |
|
||||
| `prediction-market-risk-review` | Review advice, venue, security, privacy, and execution boundaries |
|
||||
|
||||
## Access Model
|
||||
|
||||
The public skills work without Itô credentials for research and planning. Any
|
||||
Itô-backed call requires explicit gated access:
|
||||
|
||||
```bash
|
||||
export ITO_API_KEY=...
|
||||
```
|
||||
|
||||
Do not include live keys, account data, positions, private strategy, or venue
|
||||
credentials in public docs, prompts, commits, slide decks, or support tickets.
|
||||
|
||||
Suggested public CTA:
|
||||
|
||||
> The Itô skill pack works as public research/planning workflows today. DM or
|
||||
> request access for the Itô API key if you want live basket data.
|
||||
|
||||
## Non-Advisory Boundary
|
||||
|
||||
These skills do not provide investment, legal, tax, or trading advice. They do
|
||||
not place trades. They can help a user:
|
||||
|
||||
- inspect markets and underliers;
|
||||
- compare a basket against their own notes or constraints;
|
||||
- understand resolution and venue mechanics;
|
||||
- use prediction-market signals as one input to a broader research process;
|
||||
- draft a manual worksheet the user can review themselves.
|
||||
|
||||
## Growth Loop
|
||||
|
||||
The loop is intentionally simple:
|
||||
|
||||
1. ECC users discover useful public prediction-market skills.
|
||||
2. Builders run the skills with public sources and see the Itô-shaped workflow.
|
||||
3. Serious users request gated API access for live Itô basket data.
|
||||
4. Itô usage creates more operator patterns.
|
||||
5. Sanitized patterns can become new ECC skills.
|
||||
|
||||
This sends agent/tooling traffic toward Itô without making ECC Tools look like
|
||||
an Itô product or mixing subscription ownership between businesses.
|
||||
|
||||
## Useful Chain
|
||||
|
||||
For a full workflow, chain:
|
||||
|
||||
`deep-research` -> `x-api` or `exa-search` -> `ito-market-intelligence` ->
|
||||
`ito-basket-compare` -> `prediction-market-risk-review` ->
|
||||
`ito-trade-planner`
|
||||
|
||||
For corporate or industry use cases, replace trade planning with
|
||||
`prediction-market-oracle-research` and route the output into a dashboard,
|
||||
decision memo, or agent memory record.
|
||||
@@ -4,7 +4,8 @@ ECC v2.0.0-rc.1 is ready for final release review as the first release-candidate
|
||||
|
||||
The practical shift is simple: ECC is no longer framed as only a Claude Code plugin or config bundle.
|
||||
|
||||
It is becoming a cross-harness operating system for agentic work:
|
||||
It is becoming a meta-harness for agentic work: the portable layer above the
|
||||
individual AI coding clients.
|
||||
|
||||
- reusable skills instead of one-off prompts
|
||||
- hooks and tests instead of manual discipline
|
||||
@@ -22,10 +23,18 @@ I did not publish private workspace state. I shipped the reusable layer:
|
||||
- Hermes import guidance for turning local operator patterns into public ECC skills
|
||||
- release-readiness gates for PRs, issues, discussions, Linear progress, legacy tails, observability, and supply-chain checks
|
||||
- a deterministic preview-pack smoke test so the public pack can be verified before a release action
|
||||
- a gated Itô prediction-market skill pack for research, comparison, planning,
|
||||
and risk review, with Itô API access kept separate from ECC Tools and
|
||||
approval-based
|
||||
|
||||
The leverage is not just better prompting.
|
||||
|
||||
It is reducing the number of isolated surfaces, turning repeated workflows into reusable skills, and making the operating system around the agent measurable.
|
||||
It is reducing the number of isolated surfaces, turning repeated workflows into
|
||||
reusable skills, and making the operating system around the agent measurable.
|
||||
|
||||
That is the reason I like the phrase meta-harness. The goal is not to replace
|
||||
the harness. The goal is to make the workflow layer above the harness portable,
|
||||
auditable, and useful across teams.
|
||||
|
||||
The supply-chain work became part of the release story too. After the Mini
|
||||
Shai-Hulud/TanStack campaign, rc.1 now includes IOC scanning, no-lifecycle CI
|
||||
|
||||
@@ -154,7 +154,11 @@ agentic work more measurable and portable.
|
||||
```text
|
||||
ECC v2.0.0-rc.1 preview pack is ready for final release review.
|
||||
|
||||
The main point: ECC 2.0 is the harness-native operator system for agentic work.
|
||||
The main point: ECC 2.0 is a meta-harness for agentic work.
|
||||
|
||||
It is the portable layer that keeps skills, hooks, MCP conventions, release
|
||||
gates, security checks, and team workflows reusable across the AI coding tools
|
||||
people actually use.
|
||||
|
||||
It now has a reviewed public surface for:
|
||||
|
||||
@@ -164,12 +168,15 @@ It now has a reviewed public surface for:
|
||||
- Hermes as the optional operator shell;
|
||||
- release, security, queue, discussion, Linear, observability, and video-suite
|
||||
gates.
|
||||
- a gated Itô prediction-market skill pack for research, comparison, planning,
|
||||
and risk review, with Itô API access kept separate and approval-based.
|
||||
|
||||
The release is still approval-gated until the GitHub prerelease, npm package,
|
||||
plugin paths, final URLs, and billing claims have live evidence.
|
||||
|
||||
Feedback wanted: install friction, cross-harness gaps, partner integrations,
|
||||
sponsor fit, and examples of teams using multiple AI coding harnesses.
|
||||
sponsor fit, prediction-market research use cases, and examples of teams using
|
||||
multiple AI coding harnesses.
|
||||
```
|
||||
|
||||
## Video CTA Hooks
|
||||
|
||||
@@ -42,6 +42,24 @@ surfaces, or posting announcements.
|
||||
| `docs/releases/2.0.0-rc.1/article-outline.md` | Longform launch outline | Must stay release-candidate framed until GA evidence exists |
|
||||
| `docs/releases/2.0.0-rc.1/telegram-handoff.md` | Internal/shareable handoff copy | Must not include private workspace or credential details |
|
||||
| `docs/releases/2.0.0-rc.1/demo-prompts.md` | Demo prompts and proof-of-work prompts | Must keep private Hermes workflows abstracted into public examples |
|
||||
| `docs/releases/2.0.0-rc.1/ito-prediction-market-skill-pack.md` | Public Itô skill-pack distribution note | Keeps Itô API access gated, non-advisory, and separate from ECC Tools billing |
|
||||
|
||||
## Itô Skill Pack Boundary
|
||||
|
||||
The preview pack includes six public teaser skills for prediction-market and
|
||||
Itô-adjacent workflows:
|
||||
|
||||
- `skills/ito-market-intelligence/SKILL.md`
|
||||
- `skills/ito-basket-compare/SKILL.md`
|
||||
- `skills/ito-trade-planner/SKILL.md`
|
||||
- `skills/ito-data-atlas-agent/SKILL.md`
|
||||
- `skills/prediction-market-oracle-research/SKILL.md`
|
||||
- `skills/prediction-market-risk-review/SKILL.md`
|
||||
|
||||
They are research, comparison, planning, and risk-review skills. They do not
|
||||
place trades, do not provide investment advice, and do not merge ECC Tools with
|
||||
Itô. Any Itô-backed data call requires explicit gated API access through
|
||||
`ITO_API_KEY`.
|
||||
|
||||
## Hermes Skill Boundary
|
||||
|
||||
|
||||
@@ -16,6 +16,13 @@ Claude Code remains a core target. Codex, OpenCode, Cursor, Gemini, and other ha
|
||||
- Added Zed as a project-local planning/install target while keeping BYOK and OpenRouter secrets outside ECC-managed project files.
|
||||
- Added command-registry coverage, platform audit, discussion audit, operator dashboard, Linear progress readiness, and preview-pack smoke gates.
|
||||
- Added a local [observability readiness gate](../../architecture/observability-readiness.md) for loop status, session traces, harness audit, and ECC2 tool-risk logs.
|
||||
- Added the public teaser [Itô prediction-market skill pack](ito-prediction-market-skill-pack.md)
|
||||
for read-only basket research, comparison, oracle-style market intelligence,
|
||||
and risk review. Live Itô API access remains gated and separate from ECC
|
||||
Tools billing.
|
||||
- Added the rollout-derived optimization skill pack: parallel execution,
|
||||
benchmark loops, data-throughput acceleration, latency-critical systems, and
|
||||
recursive decision ledgers.
|
||||
- Refreshed the release-readiness evidence after the May 2026 Mini
|
||||
Shai-Hulud/TanStack campaign follow-up, including full-campaign AgentShield
|
||||
IOC coverage, queue-zero/discussion checks, a detailed Linear roadmap gate,
|
||||
@@ -48,6 +55,8 @@ feature branch:
|
||||
- launch collateral for GitHub release copy, X, LinkedIn, article outline,
|
||||
Telegram/Hermes handoff, demo prompts, partner/sponsor/talk outreach, and
|
||||
the approval-gated launch checklist.
|
||||
- gated Itô skill distribution as a public workflow teaser, not a live trading
|
||||
claim or a merge of ECC Tools and Itô ownership.
|
||||
- a release URL ledger that separates links which already resolve from links
|
||||
that must wait for the GitHub release, npm rc package, plugin tag/directory,
|
||||
and ECC Tools billing readback.
|
||||
|
||||
@@ -2,7 +2,8 @@
|
||||
|
||||
1/ ECC v2.0.0-rc.1 is the first release-candidate pass at the 2.0 direction.
|
||||
|
||||
The repo is moving from a Claude Code config pack into a cross-harness operating system for agentic work.
|
||||
The repo is moving from a Claude Code config pack into a meta-harness for
|
||||
agentic work.
|
||||
|
||||
2/ The important split:
|
||||
|
||||
@@ -11,17 +12,29 @@ Hermes is the operator shell that can run on top.
|
||||
|
||||
Skills, hooks, MCP configs, rules, and workflow packs live in ECC.
|
||||
|
||||
3/ Claude Code is still a core target.
|
||||
3/ A meta-harness matters because the agent layer is fragmenting.
|
||||
|
||||
Codex, OpenCode, Cursor, Gemini, and other harnesses are part of the same story now.
|
||||
Claude Code, Codex, OpenCode, Cursor, Gemini, Zed, Copilot, and terminal
|
||||
workflows all need similar operating primitives:
|
||||
|
||||
The goal is fewer one-off harness tricks and more reusable workflow surface.
|
||||
- context
|
||||
- tools
|
||||
- memory
|
||||
- gates
|
||||
- evaluation
|
||||
- release evidence
|
||||
- security checks
|
||||
|
||||
4/ Since v1.10.0, the work also picked up the operator layer:
|
||||
4/ ECC gives those primitives a shared shape instead of leaving every workflow
|
||||
stuck inside one client.
|
||||
|
||||
Use the harness you like. Keep the workflow layer portable.
|
||||
|
||||
5/ Since v1.10.0, the work also picked up the operator layer:
|
||||
|
||||
PR/issue/discussion audits, Linear progress sync, release evidence, observability checks, and a generated readiness dashboard.
|
||||
|
||||
5/ The security posture changed too.
|
||||
6/ The security posture changed too.
|
||||
|
||||
The Mini Shai-Hulud/TanStack campaign forced a real supply-chain loop:
|
||||
|
||||
@@ -31,7 +44,7 @@ The Mini Shai-Hulud/TanStack campaign forced a real supply-chain loop:
|
||||
- npm audit/signature checks
|
||||
- AI-tool persistence targets
|
||||
|
||||
6/ The rc.1 surface ships the public pieces:
|
||||
7/ The rc.1 surface ships the public pieces:
|
||||
|
||||
- Hermes setup guide
|
||||
- release notes
|
||||
@@ -41,7 +54,23 @@ The Mini Shai-Hulud/TanStack campaign forced a real supply-chain loop:
|
||||
- preview-pack smoke gate
|
||||
- X, LinkedIn, and article drafts
|
||||
|
||||
7/ It does not ship private workspace state.
|
||||
8/ It also adds the public teaser surface for the Itô prediction-market skill
|
||||
pack.
|
||||
|
||||
That is separate from ECC Tools billing and Itô remains a separate business.
|
||||
|
||||
The public skills are research, comparison, planning, and risk review.
|
||||
|
||||
9/ Important boundary:
|
||||
|
||||
No investment advice.
|
||||
No default live trading.
|
||||
No private keys.
|
||||
No Itô-backed call without explicit gated API access.
|
||||
|
||||
Useful workflow shape first, gated data access second.
|
||||
|
||||
10/ It does not ship private workspace state.
|
||||
|
||||
No secrets.
|
||||
No OAuth tokens.
|
||||
@@ -50,25 +79,25 @@ No personal datasets.
|
||||
|
||||
The point is to publish the reusable system shape.
|
||||
|
||||
8/ Why Hermes matters:
|
||||
11/ Why Hermes matters:
|
||||
|
||||
Most agent systems fail in the daily operating loop.
|
||||
|
||||
They can code, but they do not keep research, content, handoffs, reminders, and execution in one measurable surface.
|
||||
|
||||
9/ ECC gives the reusable layer.
|
||||
12/ ECC gives the reusable layer.
|
||||
|
||||
Hermes gives the operator shell.
|
||||
|
||||
Together they make the work feel less like scattered chat windows and more like a system you can run.
|
||||
|
||||
10/ This is still a release candidate.
|
||||
13/ This is still a release candidate.
|
||||
|
||||
The public docs and reusable surfaces are ready for review.
|
||||
|
||||
The deeper local integrations stay local until they are sanitized, and publication still waits on the GitHub release, npm, plugin, and final URL gates.
|
||||
|
||||
11/ Start here:
|
||||
14/ Start here:
|
||||
|
||||
Repo:
|
||||
<https://github.com/affaan-m/ECC>
|
||||
@@ -76,8 +105,11 @@ Repo:
|
||||
Hermes x ECC setup:
|
||||
<https://github.com/affaan-m/ECC/blob/main/docs/HERMES-SETUP.md>
|
||||
|
||||
12/ Release notes:
|
||||
15/ Release notes:
|
||||
<https://github.com/affaan-m/ECC/blob/main/docs/releases/2.0.0-rc.1/release-notes.md>
|
||||
|
||||
Itô skill pack boundary:
|
||||
<https://github.com/affaan-m/ECC/blob/main/docs/releases/2.0.0-rc.1/ito-prediction-market-skill-pack.md>
|
||||
|
||||
URL ledger:
|
||||
<https://github.com/affaan-m/ECC/blob/main/docs/releases/2.0.0-rc.1/release-url-ledger-2026-05-19.md>
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Everything Claude Code (ECC) — 智能体指令
|
||||
|
||||
这是一个**生产就绪的 AI 编码插件**，提供 60 个专业代理、232 项技能、75 条命令以及自动化钩子工作流，用于软件开发。
|
||||
这是一个**生产就绪的 AI 编码插件**，提供 60 个专业代理、243 项技能、75 条命令以及自动化钩子工作流，用于软件开发。
|
||||
|
||||
**版本:** 2.0.0-rc.1
|
||||
|
||||
@@ -147,7 +147,7 @@
|
||||
|
||||
```
|
||||
agents/ — 60 个专业子代理
|
||||
skills/ — 232 个工作流技能和领域知识
|
||||
skills/ — 243 个工作流技能和领域知识
|
||||
commands/ — 75 个斜杠命令
|
||||
hooks/ — 基于触发的自动化
|
||||
rules/ — 始终遵循的指导方针（通用 + 每种语言）
|
||||
|
||||
@@ -224,7 +224,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
|
||||
/plugin list ecc@ecc
|
||||
```
|
||||
|
||||
**搞定！** 你现在可以使用 60 个智能体、232 项技能和 75 个命令了。
|
||||
**搞定！** 你现在可以使用 60 个智能体、243 项技能和 75 个命令了。
|
||||
|
||||
***
|
||||
|
||||
@@ -1138,7 +1138,7 @@ opencode
|
||||
|---------|-------------|----------|--------|
|
||||
| 智能体 | PASS: 60 个 | PASS: 12 个 | **Claude Code 领先** |
|
||||
| 命令 | PASS: 75 个 | PASS: 35 个 | **Claude Code 领先** |
|
||||
| 技能 | PASS: 232 项 | PASS: 37 项 | **Claude Code 领先** |
|
||||
| 技能 | PASS: 243 项 | PASS: 37 项 | **Claude Code 领先** |
|
||||
| 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多！** |
|
||||
| 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
|
||||
| MCP 服务器 | PASS: 14 个 | PASS: 完整 | **完全对等** |
|
||||
@@ -1246,7 +1246,7 @@ ECC 是**第一个最大化利用每个主要 AI 编码工具的插件**。以
|
||||
|---------|------------|------------|-----------|----------|
|
||||
| **智能体** | 60 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
|
||||
| **命令** | 75 | 共享 | 基于指令 | 35 |
|
||||
| **技能** | 232 | 共享 | 10 (原生格式) | 37 |
|
||||
| **技能** | 243 | 共享 | 10 (原生格式) | 37 |
|
||||
| **钩子事件** | 8 种类型 | 15 种类型 | 暂无 | 11 种类型 |
|
||||
| **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | N/A | 插件钩子 |
|
||||
| **规则** | 34 (通用 + 语言) | 34 (YAML 前页) | 基于指令 | 13 条指令 |
|
||||
|
||||
Reference in New Issue
Block a user