菜单
Contract for proposing improvements to the Eidos Skills Hub ecosystem. Use when a search returns poor results, a hub is missing, a skill is stale, or the ranking policy should change. Produces a structured proposal that can be reviewed and applied.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when the user asks about Eidos, Eidos AGI, platform status, `eidos do`, closeout, cleanup before done, docket-task orchestration, evidence verification, praxis learning, gateway routing, vault/secrets, plugins, or which Eidos AGI specialist system should handle a task. This skill tells Codex to call the installed `eidos` CLI first; MCP and plugins should only point to CLIs, while CLIs provide progressive reveal of the deeper tool graph.
Investigate current context before predicting likely futures, failures, user objections, and concrete changes. Use when Zoltar needs to research an app, plugin, architecture, workflow, plan, decision, or implementation and answer what is likely to go wrong, what evidence supports it, what complaint or failure is being prevented, and what should change today.
Answer a specific foresight decision question with researched evidence, a clear judgment, likely futures, user complaint prediction, and concrete changes. Use when Daniel asks whether an idea, implementation, plugin, architecture, or workflow is likely to be regretted, whether it is the right thing in the right place with the right authority, or what decision should be made given future effects.
Compatibility entrypoint for Zoltar foresight. Use when Daniel mentions Zoltar, asks to predict the future, asks for second-order effects, asks what he will complain about, or wants future-backed product/spec changes; route the work through researched evidence, judgment, structured output, doer/checker handoff, and self-improvement notes rather than generic prediction.
Maintain and check the Eidos marketplace when plugins must work in both Claude Code and Codex. Use when adding, refactoring, auditing, or debugging marketplace plugins, dual-host packaging, .claude-plugin and .codex-plugin manifests, root marketplace entries, source/store/cache drift, install proof, or host-neutral plugin payloads.
Challenge whether a Zoltar prediction, product idea, plugin, workflow, category framing, or architecture is overfit to existing market patterns. Use when Daniel asks for a Challenger Matrix, anti-consensus review, category redefinition, frontier user needs, non-consensus futures, Doubter voice, or whether an answer is too derivative, market-shaped, competitor-shaped, or copied from current agent/product patterns.
基于 SOC 职业分类
| name | improve-skills-hub |
| description | Contract for proposing improvements to the Eidos Skills Hub ecosystem. Use when a search returns poor results, a hub is missing, a skill is stale, or the ranking policy should change. Produces a structured proposal that can be reviewed and applied. |
{
"$schema": "https://json-schema.org/draft/2020-12",
"title": "Skills Hub Improvement Proposal",
"purpose": "Propose a specific, actionable change to the eidos-skills-hub ecosystem — a new hub, a new skill, a ranking adjustment, or a search fix. Every proposal must be motivated by an observed failure, not a hypothetical.",
"context": "Read the current state: eidos-skills-hub/index.js for search logic and hub wiring, .well-known/agent-skills/index.json in each hub for skill inventory, and the SKILL.md files for content quality. Base the proposal on what's actually there.",
"constraints": [
"One proposal per output — don't bundle unrelated changes",
"observed_failure must describe a real search or use case that didn't work",
"New hubs require at least 2 concrete skills ready to populate them",
"Ranking changes must include a before/after example showing improvement",
"Runtime changes must add or update deterministic tests",
"Changes affecting installation or updates must include rollback steps",
"self_update steps must be copy-pasteable — no placeholders"
],
"required": ["observed_failure", "proposal_type", "proposal", "self_update"],
"properties": {
"observed_failure": {
"type": "string",
"description": "What search query, use case, or result revealed the gap"
},
"proposal_type": {
"enum": ["new_hub", "new_skill", "ranking_change", "search_fix", "skill_update"]
},
"proposal": {
"type": "object",
"required": ["title", "description", "rationale"],
"properties": {
"title": { "type": "string" },
"description": { "type": "string" },
"rationale": { "type": "string" },
"affected_files": {
"type": "array",
"items": { "type": "string" }
},
"example_before": { "type": "string" },
"example_after": { "type": "string" }
}
},
"self_update": {
"type": "object",
"required": ["steps"],
"properties": {
"steps": {
"type": "array",
"items": { "type": "string" },
"description": "Exact shell commands or file edits to apply the proposal"
},
"verify": {
"type": "string",
"description": "How to confirm the change worked"
}
}
}
}
}
cd ~/repos-eidos-agi/eidos-skills-hub
# apply the self_update.steps from the proposal output
git add -A && git commit -m "improve: <proposal title>"
git push
self_update.steps are literal commands, not descriptions of commands