geo-ai-search-optimization 1.3.0 → 1.3.1

package/README.md

@@ -104,6 +104,26 @@ geo-ai-search-optimization agent-continue ./reports/agent-resume.json --format j
 - 可以进入收尾时跑什么
 - 可直接复制给 agent 的 continue prompt
 
+## Agent State Pack 命令
+
+如果你希望下一个 agent 直接拿到一份统一的当前状态工件，而不是自己拼 `agent-resume / agent-continue / agent-status-board / agent-checkpoint`，可以直接用 `agent-state-pack`：
+
+```bash
+geo-ai-search-optimization agent-state-pack ./your-site
+geo-ai-search-optimization agent-state-pack ./reports/agent-playbook-pack.json
+geo-ai-search-optimization agent-state-pack ./reports/agent-continue.json --format json --out ./reports/agent-state-pack.json
+```
+
+它会输出：
+
+- 当前阶段和状态等级
+- 现在先执行哪条命令
+- 当前包与下一包
+- 执行前先确认什么
+- 执行后先验证什么
+- 这一轮完成后要同步哪些工件
+- 可直接复制给 agent 的 state prompt
+
 ## Auto Flow 命令
 
 如果你希望 agent 不用自己判断现在该用哪个 skill、该跑哪个命令，可以直接用 `auto-flow`：
@@ -725,6 +745,7 @@ geo-ai-search-optimization install --target ./tmp/custom-skills --json
 geo-ai-search-optimization agent-orchestrator ./your-site
 geo-ai-search-optimization agent-resume ./your-site
 geo-ai-search-optimization agent-continue ./your-site
+geo-ai-search-optimization agent-state-pack ./your-site
 geo-ai-search-optimization auto-flow "audit this site and tell me the next skill"
 geo-ai-search-optimization agent-session ./your-site
 geo-ai-search-optimization agent-runbook ./your-site
@@ -815,6 +836,14 @@ geo-ai-search-optimization help
 - `auto-flow`、`agent-session` 已能把 `playbook-pack / agent-resume / agent-continue` 统一接成继续链
 - 新增 `geo-ai-search-optimization-agent-continue` skill
 
+## New in 1.3.1
+
+- 新增 `agent-state-pack`
+- 把 `agent-resume + agent-continue + agent-status-board + agent-checkpoint` 压成一个统一状态工件
+- 输出当前阶段、当前包、现在先执行哪条命令、执行后验证项、同步状态命令和收尾路径
+- `auto-flow` 已能识别 `geo-agent-state-pack` 并继续往下路由
+- 新增 `geo-ai-search-optimization-agent-state-pack` skill
+
 ## New in 1.2.20
 
 - 新增 `agent-continue`
@@ -1079,6 +1108,7 @@ The installed package now includes a bundled GEO skill pack, including:
 - `geo-ai-search-optimization-agent-orchestrator`
 - `geo-ai-search-optimization-agent-resume`
 - `geo-ai-search-optimization-agent-continue`
+- `geo-ai-search-optimization-agent-state-pack`
 - `geo-ai-search-optimization-agent-session`
 - `geo-ai-search-optimization-agent-runbook`
 - `geo-ai-search-optimization-agent-executor`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "geo-ai-search-optimization",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "description": "Install and run a Generative Engine Optimization (GEO)-first, SEO-supported Codex skill for website optimization.",
   "type": "module",
   "bin": {

package/resources/geo-ai-search-optimization/references/skill-bundle-map.md

@@ -62,6 +62,16 @@ Best for:
 - turning a resume point into a one-round execution loop
 - giving the next agent one execution command, one validation set, and one writeback list
 
+### `geo-ai-search-optimization-agent-state-pack`
+
+Use this when the next agent should get one normalized current-state artifact instead of manually stitching together resume, continue, board, and checkpoint outputs.
+
+Best for:
+
+- creating one state snapshot from a URL, directory, or GEO execution artifact
+- telling the next agent what command runs now and what must be synced afterward
+- reducing handoff ambiguity between PM, agent, and the next execution round
+
 ### `geo-ai-search-optimization-agent-session`
 
 Use this when the next agent needs a runnable session plan, not just a routing answer.

package/resources/geo-ai-search-optimization-agent-state-pack/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: geo-ai-search-optimization-agent-state-pack
+description: Normalize the current GEO execution state into one handoff-ready artifact for the next agent. Use when an agent, PM, or workflow already has a GEO URL, codebase, resume point, continue artifact, status board, checkpoint, decision log, or playbook pack and needs one current-state package with the command to run now, the validation steps, the state writeback commands, and the closeout path.
+---
+
+# GEO Agent State Pack
+
+Use this skill when the next agent should not piece together `agent-resume`, `agent-continue`, `agent-status-board`, and `agent-checkpoint` manually.
+
+## What this skill should do
+
+- create one normalized current-state artifact
+- state what command should run now
+- state what to validate after this round
+- state which GEO artifacts must be written back
+- state when the workflow is ready for closeout
+
+## Preferred command
+
+```bash
+npx geo-ai-search-optimization agent-state-pack <input>
+```
+
+Where `<input>` can be:
+
+- a website URL
+- a local project directory
+- a GEO JSON artifact such as `agent-resume`, `agent-continue`, `agent-status-board`, `agent-checkpoint`, or `agent-playbook-pack`
+
+## Output expectations
+
+Return the result in PM-readable language while keeping the command contract explicit:
+
+- current stage
+- state level
+- now command
+- expected artifact
+- current packet
+- next packet
+- validation list
+- sync-after-round commands
+- closeout path
+
+If the state shows blockers or missing context, say that clearly and do not pretend the next agent should already be editing code.

package/resources/geo-ai-search-optimization-agent-state-pack/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "GEO Agent State Pack"
+  short_description: "Normalize current GEO state for the next agent"
+  default_prompt: "Use $geo-ai-search-optimization-agent-state-pack to turn this GEO input into one current-state artifact with the command to run now, validation steps, writeback commands, and closeout path."

package/resources/geo-ai-search-optimization-usage/SKILL.md

@@ -13,35 +13,36 @@ Treat this tool as a PM-friendly GEO workflow for websites.
 
 `GEO = Generative Engine Optimization`
 
-The package is best explained as twenty-seven layers:
+The package is best explained as twenty-eight layers:
 
 1. `agent-orchestrator`: choose the one next GEO command to run right now
 2. `agent-resume`: resume from the latest reliable GEO checkpoint instead of restarting the whole chain
 3. `agent-continue`: continue this round and write status artifacts back after execution
-4. `auto-flow`: auto-select the next skill and command chain
-5. `agent-session`: build a runnable session for the next agent
-6. `agent-runbook`: execution manual and checklist for the next agent
-7. `agent-executor`: choose one packet to execute right now
-8. `agent-batch-executor`: queue the first few packets, but still advance one packet at a time
-9. `agent-progress-tracker`: track which packet is done, which one is active, and what comes next
-10. `agent-status-board`: turn the execution state into a board view for PM and agents
-11. `agent-checkpoint`: freeze the current round into a continue / unblock / closeout decision
-12. `agent-decision-log`: preserve why each round continued, paused, or closed out
-13. `agent-retrospective`: explain multi-round patterns, lessons, and next-round advice
-14. `agent-playbook-pack`: compress retrospective, decision history, and handoff into one resume entrypoint
-15. `skills`: inspect the bundled skill package
-16. `onboard-url` / `onboard`: first look
-17. `scan`: raw signal check
-18. `audit` / `report`: diagnosis
-19. `fix-plan` / `owner-board`: execution planning
-20. `agent-handoff`: agent takeover package
-21. `apply-plan`: execution loop
-22. `completion-report`: closeout
-23. `handoff-bundle`: all-in-one package
-24. `share-pack`: audience-ready delivery
-25. `export-pack`: folder export
-26. `html-pack` / `publish-pack`: browsable and final delivery output
-27. `pm-brief` / `roadmap`: stakeholder alignment
+4. `agent-state-pack`: compress resume, continue, board, and checkpoint into one current-state artifact
+5. `auto-flow`: auto-select the next skill and command chain
+6. `agent-session`: build a runnable session for the next agent
+7. `agent-runbook`: execution manual and checklist for the next agent
+8. `agent-executor`: choose one packet to execute right now
+9. `agent-batch-executor`: queue the first few packets, but still advance one packet at a time
+10. `agent-progress-tracker`: track which packet is done, which one is active, and what comes next
+11. `agent-status-board`: turn the execution state into a board view for PM and agents
+12. `agent-checkpoint`: freeze the current round into a continue / unblock / closeout decision
+13. `agent-decision-log`: preserve why each round continued, paused, or closed out
+14. `agent-retrospective`: explain multi-round patterns, lessons, and next-round advice
+15. `agent-playbook-pack`: compress retrospective, decision history, and handoff into one resume entrypoint
+16. `skills`: inspect the bundled skill package
+17. `onboard-url` / `onboard`: first look
+18. `scan`: raw signal check
+19. `audit` / `report`: diagnosis
+20. `fix-plan` / `owner-board`: execution planning
+21. `agent-handoff`: agent takeover package
+22. `apply-plan`: execution loop
+23. `completion-report`: closeout
+24. `handoff-bundle`: all-in-one package
+25. `share-pack`: audience-ready delivery
+26. `export-pack`: folder export
+27. `html-pack` / `publish-pack`: browsable and final delivery output
+28. `pm-brief` / `roadmap`: stakeholder alignment
 
 ## Recommended command order
 
@@ -51,6 +52,7 @@ If the user only has a website URL:
 npx geo-ai-search-optimization agent-orchestrator https://example.com
 npx geo-ai-search-optimization agent-resume https://example.com
 npx geo-ai-search-optimization agent-continue https://example.com
+npx geo-ai-search-optimization agent-state-pack https://example.com
 npx geo-ai-search-optimization auto-flow https://example.com
 npx geo-ai-search-optimization agent-session https://example.com
 npx geo-ai-search-optimization agent-runbook https://example.com
@@ -73,6 +75,7 @@ If the user has the website codebase:
 npx geo-ai-search-optimization agent-orchestrator ./your-site
 npx geo-ai-search-optimization agent-resume ./your-site
 npx geo-ai-search-optimization agent-continue ./your-site
+npx geo-ai-search-optimization agent-state-pack ./your-site
 npx geo-ai-search-optimization auto-flow ./your-site
 npx geo-ai-search-optimization agent-session ./your-site
 npx geo-ai-search-optimization agent-runbook ./your-site
@@ -104,6 +107,7 @@ npx geo-ai-search-optimization roadmap ./your-site
 - `agent-orchestrator`: choose the one next GEO command to run now, plus expected artifact, stop conditions, and follow-up command
 - `agent-resume`: resume from the latest reliable checkpoint, confirm what not to reset, and tell the next agent the one resume command to run
 - `agent-continue`: continue the current round, validate it, and tell the next agent which state artifacts to update right after execution
+- `agent-state-pack`: turn the current round into one normalized state artifact with the command to run now, the validation list, and the sync-after-round commands
 - `auto-flow`: auto-select the next skill and command order from a task brief, URL, project path, or GEO artifact
 - `agent-session`: build a step-by-step session packet for the next agent from the same kinds of inputs
 - `agent-runbook`: build a checklist-driven runbook with preflight, validation, and reporting rules
@@ -142,6 +146,7 @@ When explaining the tool to a user:
 - if the user or next agent wants just one next command, move them to `agent-orchestrator`
 - if the user or next agent needs to continue from the latest reliable checkpoint without restarting, move them to `agent-resume`
 - if the user or next agent needs one round of execution plus status writeback, move them to `agent-continue`
+- if the user or next agent wants one unified current-state artifact for handoff, move them to `agent-state-pack`
 - if the user or the next agent is unsure where to start, move them to `auto-flow` first
 - if the user wants something the next agent can follow step by step, move them to `agent-session`
 - if the user wants the next agent to follow a checklist and execution manual, move them to `agent-runbook`

package/src/agent-resume.js

@@ -37,6 +37,9 @@ async function tryReadExistingPlaybookPack(input) {
     if (parsed.kind === "geo-agent-resume" && parsed.playbookPack) {
       return parsed.playbookPack;
     }
+    if (parsed.kind === "geo-agent-state-pack" && parsed.resume?.playbookPack) {
+      return parsed.resume.playbookPack;
+    }
   } catch {
     return null;
   }

package/src/agent-state-pack.js

@@ -0,0 +1,260 @@
+import { createAgentCheckpoint } from "./agent-checkpoint.js";
+import { createAgentContinue } from "./agent-continue.js";
+import { createAgentResume } from "./agent-resume.js";
+import { createAgentStatusBoard } from "./agent-status-board.js";
+import { writeScanOutput } from "./scan.js";
+
+const VALID_FORMATS = new Set(["markdown", "json"]);
+
+function normalizeFormat(format) {
+  const resolved = (format || "markdown").toLowerCase();
+  if (!VALID_FORMATS.has(resolved)) {
+    throw new Error(`不支持的 agent-state-pack 格式：${format}。可选值：${Array.from(VALID_FORMATS).join(", ")}`);
+  }
+  return resolved;
+}
+
+function uniqueList(items) {
+  return Array.from(new Set((items || []).filter(Boolean)));
+}
+
+function inferStateLevel(continueArtifact, board, checkpoint) {
+  if (continueArtifact.continue_mode === "needs-context") {
+    return "needs-context";
+  }
+  if (
+    continueArtifact.continue_mode === "closeout-loop" ||
+    checkpoint.decision === "move-to-closeout" ||
+    board.boardStatus === "completed"
+  ) {
+    return "closeout-ready";
+  }
+  if (checkpoint.decision === "resolve-blockers" || board.boardStatus === "blocked") {
+    return "blocked";
+  }
+  if (board.boardStatus === "in-progress" || continueArtifact.currentPacket) {
+    return "active";
+  }
+  if (board.boardStatus === "not-started") {
+    return "ready-to-start";
+  }
+  return "tracking";
+}
+
+function buildStateSummary(level, resume, continueArtifact, board, checkpoint) {
+  if (level === "needs-context") {
+    return "当前还缺继续执行所需的上下文，先补网址、目录或现成 GEO 工件。";
+  }
+  if (level === "closeout-ready") {
+    return "当前已经接近或进入收尾，下一步重点是复盘、交接和交付，而不是再开新包。";
+  }
+  if (level === "blocked") {
+    return checkpoint.decisionReason || `当前执行被阻塞，先解除阻塞，再回到 ${continueArtifact.currentPacket?.id || "当前包"}。`;
+  }
+  if (level === "ready-to-start") {
+    return `当前已经有明确入口，可以从 ${continueArtifact.currentPacket?.id || "第一包"} 启动这一轮。`;
+  }
+  if (continueArtifact.currentPacket) {
+    return `当前应继续 ${continueArtifact.currentPacket.id}，并在这一轮结束后同步状态工件。`;
+  }
+  return resume.resume_summary || board.boardSummary;
+}
+
+function buildNowCommand(continueArtifact, resume) {
+  return continueArtifact.continue_now || resume.resume_command || resume.orchestrator?.next_command || null;
+}
+
+function buildAfterNow(level, continueArtifact, resume) {
+  if (level === "closeout-ready") {
+    return continueArtifact.closeout_when_ready[0] || resume.after_resume || null;
+  }
+  return continueArtifact.update_artifacts[0] || resume.after_resume || continueArtifact.closeout_when_ready[0] || null;
+}
+
+function buildPreflightChecks(resume, checkpoint) {
+  return uniqueList([
+    ...(resume.verify_before_resume || []),
+    checkpoint.gateChecks?.find((item) => item.status === "fail")?.detail,
+    checkpoint.gateChecks?.find((item) => item.status === "warn")?.detail
+  ]);
+}
+
+function buildStatePrompt(pack) {
+  const lines = [
+    "你现在进入 GEO Agent State Pack 模式。",
+    `当前输入：${pack.source}`,
+    `当前状态等级：${pack.state_level}`,
+    `当前阶段：${pack.current_stage}`,
+    `状态摘要：${pack.state_summary}`,
+    `现在先执行：${pack.now_command || "先补上下文"}`
+  ];
+
+  if (pack.currentPacket) {
+    lines.push(`当前包：${pack.currentPacket.id}｜${pack.currentPacket.title}`);
+  }
+  if (pack.nextPacket) {
+    lines.push(`下一包：${pack.nextPacket.id}｜${pack.nextPacket.title}`);
+  }
+  lines.push(`看板状态：${pack.board_status}｜进度：${pack.progress_percent}%`);
+  lines.push(`检查点决策：${pack.checkpoint_decision}`);
+
+  if (pack.preflight_checks.length > 0) {
+    lines.push("执行前先确认：");
+    for (const item of pack.preflight_checks) {
+      lines.push(`- ${item}`);
+    }
+  }
+  if (pack.sync_after_round.length > 0) {
+    lines.push("这一轮完成后要同步这些工件：");
+    for (const item of pack.sync_after_round) {
+      lines.push(`- ${item}`);
+    }
+  }
+
+  lines.push("请先解释为什么现在应沿着这份状态包继续，而不是重新生成整条链。");
+  lines.push("然后给出本轮动作、验证点、回写动作和何时进入收尾。");
+  return lines.join("\n");
+}
+
+export async function createAgentStatePack(input, options = {}) {
+  const format = normalizeFormat(options.format);
+  const [resume, continueArtifact, statusBoard, checkpoint] = await Promise.all([
+    createAgentResume(input, { format: "json", intent: options.intent }),
+    createAgentContinue(input, { format: "json", intent: options.intent }),
+    createAgentStatusBoard(input, {
+      format: "json",
+      currentTaskId: options.currentTaskId,
+      completedPacketIds: options.completedPacketIds,
+      blockedReasons: options.blockedReasons
+    }),
+    createAgentCheckpoint(input, {
+      format: "json",
+      currentTaskId: options.currentTaskId,
+      completedPacketIds: options.completedPacketIds,
+      blockedReasons: options.blockedReasons
+    })
+  ]);
+
+  const stateLevel = inferStateLevel(continueArtifact, statusBoard, checkpoint);
+  const source = continueArtifact.source || resume.source || statusBoard.source;
+
+  const pack = {
+    kind: "geo-agent-state-pack",
+    input,
+    source,
+    sourceType: continueArtifact.sourceType || resume.sourceType || statusBoard.sourceType,
+    artifactKind: resume.artifactKind || statusBoard.artifactKind,
+    format,
+    state_level: stateLevel,
+    state_summary: buildStateSummary(stateLevel, resume, continueArtifact, statusBoard, checkpoint),
+    current_stage: resume.orchestrator?.current_stage || "Agent 执行",
+    now_command: buildNowCommand(continueArtifact, resume),
+    expected_artifact: resume.expected_artifact || continueArtifact.executor?.expectedArtifact || null,
+    after_now: buildAfterNow(stateLevel, continueArtifact, resume),
+    currentPacket: continueArtifact.currentPacket || checkpoint.currentPacket || null,
+    nextPacket: continueArtifact.nextPacket || checkpoint.nextPacket || null,
+    board_status: statusBoard.boardStatus,
+    progress_percent: statusBoard.progressPercent,
+    checkpoint_type: checkpoint.checkpointType,
+    checkpoint_decision: checkpoint.decision,
+    checkpoint_reason: checkpoint.decisionReason,
+    preflight_checks: buildPreflightChecks(resume, checkpoint),
+    do_now_checklist: uniqueList(continueArtifact.do_now_checklist),
+    validate_after: uniqueList(continueArtifact.validate_after),
+    sync_after_round: uniqueList(continueArtifact.update_artifacts),
+    closeout_when_ready: uniqueList(continueArtifact.closeout_when_ready),
+    do_not_reset: uniqueList(continueArtifact.do_not_restart),
+    handoff_note: checkpoint.handoffNote,
+    selectedSkill: {
+      name: "geo-ai-search-optimization-agent-state-pack",
+      displayName: "GEO Agent State Pack",
+      shortDescription: "Normalize the current GEO state for the next agent"
+    },
+    next_skill: continueArtifact.selectedSkill?.name || "geo-ai-search-optimization-agent-continue",
+    resume,
+    continue: continueArtifact,
+    statusBoard,
+    checkpoint,
+    state_prompt: ""
+  };
+
+  pack.state_prompt = buildStatePrompt(pack);
+  return pack;
+}
+
+export function renderAgentStatePackMarkdown(pack) {
+  const lines = [
+    "# GEO Agent State Pack",
+    "",
+    `- 输入：\`${pack.source}\``,
+    `- 输入类型：\`${pack.sourceType}\``,
+    `- 工件类型：\`${pack.artifactKind}\``,
+    `- 当前阶段：${pack.current_stage}`,
+    `- 状态等级：\`${pack.state_level}\``,
+    `- 看板状态：\`${pack.board_status}\``,
+    `- 进度：\`${pack.progress_percent}%\``,
+    `- 检查点决策：\`${pack.checkpoint_decision}\``,
+    "",
+    "## 当前摘要",
+    "",
+    `- ${pack.state_summary}`,
+    `- 现在先执行：\`${pack.now_command || "先补上下文"}\``
+  ];
+
+  if (pack.expected_artifact) {
+    lines.push(`- 预期产物：${pack.expected_artifact}`);
+  }
+  if (pack.after_now) {
+    lines.push(`- 做完后第一条：\`${pack.after_now}\``);
+  }
+
+  if (pack.currentPacket) {
+    lines.push("", "## 当前包", "", `- ${pack.currentPacket.id}｜${pack.currentPacket.title}`);
+  }
+  if (pack.nextPacket) {
+    lines.push("", "## 下一包", "", `- ${pack.nextPacket.id}｜${pack.nextPacket.title}`);
+  }
+
+  lines.push("", "## 执行前先确认", "");
+  if (pack.preflight_checks.length === 0) {
+    lines.push("- 当前没有额外 preflight 项。");
+  } else {
+    for (const item of pack.preflight_checks) {
+      lines.push(`- ${item}`);
+    }
+  }
+
+  lines.push("", "## 这一轮先做什么", "");
+  for (const item of pack.do_now_checklist) {
+    lines.push(`- ${item}`);
+  }
+
+  lines.push("", "## 执行后先验证", "");
+  for (const item of pack.validate_after) {
+    lines.push(`- ${item}`);
+  }
+
+  lines.push("", "## 这一轮完成后同步什么", "");
+  for (const item of pack.sync_after_round) {
+    lines.push(`- \`${item}\``);
+  }
+
+  lines.push("", "## 可以进入收尾时跑什么", "");
+  for (const item of pack.closeout_when_ready) {
+    lines.push(`- \`${item}\``);
+  }
+
+  lines.push("", "## 不要重置什么", "");
+  for (const item of pack.do_not_reset) {
+    lines.push(`- ${item}`);
+  }
+
+  lines.push("", "## 交接说明", "", `- ${pack.handoff_note}`);
+  lines.push("", "## 可直接复制给 Agent 的 State Prompt", "", "```text", pack.state_prompt, "```");
+
+  return `${lines.join("\n")}\n`;
+}
+
+export async function writeAgentStatePackOutput(outputPath, content) {
+  return writeScanOutput(outputPath, content);
+}

package/src/auto-flow.js

@@ -41,6 +41,9 @@ function detectArtifactKindFromParsedJson(parsed) {
 function inferTaskTextMode(text) {
   const normalized = String(text).toLowerCase();
 
+  if (/(agent-state-pack|state pack|state snapshot|统一状态包|当前状态包|state artifact)/i.test(normalized)) {
+    return "execute";
+  }
   if (/(agent-continue|continue this round|继续这轮|继续当前轮次|回写状态后继续)/i.test(normalized)) {
     return "execute";
   }
@@ -177,6 +180,9 @@ function resolveEffectiveIntent(intent, detected) {
   if (detected.artifactKind === "geo-agent-playbook-pack") {
     return detected.parsed?.playbookStatus === "closeout-ready" ? "closeout" : "execute";
   }
+  if (detected.artifactKind === "geo-agent-state-pack") {
+    return detected.parsed?.state_level === "closeout-ready" ? "closeout" : "execute";
+  }
   if (detected.artifactKind === "geo-agent-resume") {
     return detected.parsed?.resume_mode === "resume-closeout" ? "closeout" : "execute";
   }
@@ -205,6 +211,7 @@ function resolveEffectiveIntent(intent, detected) {
       "geo-agent-status-board",
       "geo-agent-checkpoint",
       "geo-agent-decision-log",
+      "geo-agent-state-pack",
       "geo-apply-plan",
       "geo-handoff-bundle",
       "geo-fix-plan"
@@ -246,10 +253,11 @@ function buildCommandChain(detected, intent) {
   }
 
   if (intent === "closeout") {
+    const baseSource = detected.parsed?.source || source;
     return [
-      `geo-ai-search-optimization completion-report ${source}`,
-      `geo-ai-search-optimization meeting-pack ${source}`,
-      `geo-ai-search-optimization publish-pack ${source}`
+      `geo-ai-search-optimization completion-report ${baseSource}`,
+      `geo-ai-search-optimization meeting-pack ${baseSource}`,
+      `geo-ai-search-optimization publish-pack ${baseSource}`
     ];
   }
 
@@ -447,6 +455,11 @@ function buildCommandChain(detected, intent) {
             `geo-ai-search-optimization agent-decision-log ${baseSource}`
           ];
     }
+    case "geo-agent-state-pack": {
+      const nowCommand = detected.parsed?.now_command;
+      const syncCommands = Array.isArray(detected.parsed?.sync_after_round) ? detected.parsed.sync_after_round : [];
+      return [nowCommand, ...syncCommands.slice(0, 2)].filter(Boolean);
+    }
     case "geo-agent-resume": {
       return [`geo-ai-search-optimization agent-continue ${source}`];
     }
@@ -534,6 +547,8 @@ function pickSkillName(detected, intent) {
     case "geo-agent-status-board":
     case "geo-agent-checkpoint":
     case "geo-agent-decision-log":
+    case "geo-agent-state-pack":
+      return "geo-ai-search-optimization-agent-state-pack";
     case "geo-agent-playbook-pack":
     case "geo-agent-resume":
     case "geo-agent-continue":
@@ -581,6 +596,7 @@ function buildSecondarySkillNames(primarySkill, intent, detected) {
       "geo-agent-status-board",
       "geo-agent-checkpoint",
       "geo-agent-decision-log",
+      "geo-agent-state-pack",
       "geo-agent-resume",
       "geo-agent-continue",
       "geo-agent-playbook-pack",
@@ -591,6 +607,7 @@ function buildSecondarySkillNames(primarySkill, intent, detected) {
   ) {
     names.add("geo-ai-search-optimization-agent-resume");
     names.add("geo-ai-search-optimization-agent-continue");
+    names.add("geo-ai-search-optimization-agent-state-pack");
     names.add("geo-ai-search-optimization-agent-batch-executor");
     names.add("geo-ai-search-optimization-agent-progress-tracker");
     names.add("geo-ai-search-optimization-agent-status-board");
@@ -612,6 +629,9 @@ function buildSecondarySkillNames(primarySkill, intent, detected) {
 }
 
 function buildStage(intent, detected) {
+  if (detected.artifactKind === "geo-agent-state-pack") {
+    return "当前状态";
+  }
   if (detected.artifactKind === "geo-agent-continue") {
     return "继续执行";
   }
@@ -638,6 +658,7 @@ function buildStage(intent, detected) {
       "geo-agent-status-board",
       "geo-agent-checkpoint",
       "geo-agent-decision-log",
+      "geo-agent-state-pack",
       "geo-agent-resume",
       "geo-agent-continue",
       "geo-agent-playbook-pack",
@@ -659,6 +680,7 @@ function buildStage(intent, detected) {
       "geo-agent-status-board",
       "geo-agent-checkpoint",
       "geo-agent-decision-log",
+      "geo-agent-state-pack",
       "geo-agent-resume",
       "geo-agent-continue",
       "geo-agent-playbook-pack",
@@ -749,6 +771,9 @@ function buildNextAction(detected, intent, commands) {
     return `先运行 \`${commands[0]}\` 生成适合外发或交接的结果。`;
   }
   if (intent === "execute") {
+    if (detected.artifactKind === "geo-agent-state-pack") {
+      return `先运行 \`${commands[0]}\`，沿着这份统一状态包继续当前这一轮，并按包内要求回写状态工件。`;
+    }
     if (detected.artifactKind === "geo-agent-continue") {
       return `先运行 \`${commands[0]}\`，继续当前这一轮，并把状态与决策工件一起回写。`;
     }

package/src/cli.js

@@ -12,6 +12,11 @@ import {
   renderAgentContinueMarkdown,
   writeAgentContinueOutput
 } from "./agent-continue.js";
+import {
+  createAgentStatePack,
+  renderAgentStatePackMarkdown,
+  writeAgentStatePackOutput
+} from "./agent-state-pack.js";
 import { createAgentExecutor, renderAgentExecutorMarkdown, writeAgentExecutorOutput } from "./agent-executor.js";
 import { createAgentHandoff, renderAgentHandoffMarkdown, writeAgentHandoffOutput } from "./agent-handoff.js";
 import {
@@ -94,6 +99,7 @@ function printHelp() {
       "  geo-ai-search-optimization agent-orchestrator <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--format <markdown|json>] [--out <file>]",
       "  geo-ai-search-optimization agent-resume <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--format <markdown|json>] [--out <file>]",
       "  geo-ai-search-optimization agent-continue <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--format <markdown|json>] [--out <file>]",
+      "  geo-ai-search-optimization agent-state-pack <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--current <id>] [--completed <id,id>] [--blocked <reason,reason>] [--format <markdown|json>] [--out <file>]",
       "  geo-ai-search-optimization auto-flow <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--json] [--out <file>]",
       "  geo-ai-search-optimization agent-session <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--json] [--out <file>]",
       "  geo-ai-search-optimization agent-runbook <input> [--intent <auto|diagnose|guide|execute|share|closeout>] [--task <id>] [--format <markdown|json>] [--out <file>]",
@@ -273,6 +279,35 @@ async function handleAgentContinue(args) {
   process.stdout.write(renderedOutput);
 }
 
+async function handleAgentStatePack(args) {
+  const input = args.find((value) => !value.startsWith("-"));
+  if (!input) {
+    throw new Error("agent-state-pack 需要一个输入值，可以是任务描述、项目路径、网站网址或已导出的工件");
+  }
+
+  const format = getFlagValue(args, "--format") || (hasFlag(args, "--json") ? "json" : undefined);
+  const artifact = await createAgentStatePack(input, {
+    intent: getFlagValue(args, "--intent"),
+    format,
+    currentTaskId: getFlagValue(args, "--current"),
+    completedPacketIds: getFlagValue(args, "--completed"),
+    blockedReasons: getFlagValue(args, "--blocked")
+  });
+  const outputJson = artifact.format === "json";
+  const renderedOutput = outputJson
+    ? `${JSON.stringify(artifact, null, 2)}\n`
+    : renderAgentStatePackMarkdown(artifact);
+
+  const outputPath = getFlagValue(args, "--out");
+  if (outputPath) {
+    const resolvedOutputPath = await writeAgentStatePackOutput(outputPath, renderedOutput);
+    process.stdout.write(`已保存 agent-state-pack 结果：${resolvedOutputPath}\n`);
+    return;
+  }
+
+  process.stdout.write(renderedOutput);
+}
+
 async function handleAgentSession(args) {
   const input = args.find((value) => !value.startsWith("-"));
   if (!input) {
@@ -1104,6 +1139,11 @@ export async function runCli(args = []) {
     return;
   }
 
+  if (command === "agent-state-pack") {
+    await handleAgentStatePack(rest);
+    return;
+  }
+
   if (command === "agent-session") {
     await handleAgentSession(rest);
     return;

package/src/index.js

@@ -8,6 +8,7 @@ export {
 export { createAutoFlow, renderAutoFlowMarkdown, writeAutoFlowOutput } from "./auto-flow.js";
 export { createApplyPlan, renderApplyPlanMarkdown, writeApplyPlanOutput } from "./apply-plan.js";
 export { createAgentContinue, renderAgentContinueMarkdown, writeAgentContinueOutput } from "./agent-continue.js";
+export { createAgentStatePack, renderAgentStatePackMarkdown, writeAgentStatePackOutput } from "./agent-state-pack.js";
 export { createAgentOrchestrator, renderAgentOrchestratorMarkdown, writeAgentOrchestratorOutput } from "./agent-orchestrator.js";
 export { createAgentResume, renderAgentResumeMarkdown, writeAgentResumeOutput } from "./agent-resume.js";
 export { createAgentBatchExecutor, renderAgentBatchExecutorMarkdown, writeAgentBatchExecutorOutput } from "./agent-batch-executor.js";

package/src/skills.js

@@ -8,6 +8,7 @@ const SKILL_ORDER = [
   "geo-ai-search-optimization-agent-orchestrator",
   "geo-ai-search-optimization-agent-resume",
   "geo-ai-search-optimization-agent-continue",
+  "geo-ai-search-optimization-agent-state-pack",
   "geo-ai-search-optimization-agent-session",
   "geo-ai-search-optimization-agent-runbook",
   "geo-ai-search-optimization-agent-executor",
@@ -35,6 +36,7 @@ const SKILL_CATEGORY = {
   "geo-ai-search-optimization-agent-orchestrator": "routing",
   "geo-ai-search-optimization-agent-resume": "routing",
   "geo-ai-search-optimization-agent-continue": "routing",
+  "geo-ai-search-optimization-agent-state-pack": "routing",
   "geo-ai-search-optimization-agent-session": "routing",
   "geo-ai-search-optimization-agent-runbook": "execution",
   "geo-ai-search-optimization-agent-executor": "execution",
@@ -180,6 +182,7 @@ export function renderBundledSkillsMarkdown(bundle) {
     "- 如果你只想让 agent 立刻知道现在唯一该跑哪条命令，先跑 agent-orchestrator。",
     "- 如果工作中断后要从最近一个可靠恢复点继续，先跑 agent-resume。",
     "- 如果你希望 agent 不只恢复，还要拿到这一轮继续后的状态回写动作，继续跑 agent-continue。",
+    "- 如果你希望下一个 agent 直接拿到统一的当前状态工件，而不是自己拼 resume / continue / board / checkpoint，跑 agent-state-pack。",
     "- 如果 agent 需要自动选 skill，先跑 auto-flow。",
     "- 如果要给 agent 明确步骤，继续进入 agent-session。",
     "- 如果要给 agent 一份执行手册和检查表，再进入 agent-runbook。",