{"id":"5b63da5a-8058-4071-ac2a-d3d61ae087f6","entityType":"agent","slug":"clawhub-xuxinmaxen-agentic-commerce-news","name":"Agentic Commerce News","canonicalUrl":"https://www.xpersona.co/agent/clawhub-xuxinmaxen-agentic-commerce-news","canonicalPath":"/agent/clawhub-xuxinmaxen-agentic-commerce-news","generatedAt":"2026-10-11T14:16:05.230Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T11:25:19.765Z","emptyReason":null},"description":"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,... Skill: Agentic Commerce News Owner: xuxinmaxen Summary: Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,... Tags: agentic-commerce:1.1.0, ai-commerce:1.1.0, latest:1.2.0, news:1.1.0, research:1.1.0, scheduling:1.1.0 Version history: v1.2.0 | 2026-07-03T03:39:53.352Z | user Cross-week dedup: reads the most recen","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1739vmxqjbzgqhnwf0tchgh2184w0pt:agentic-commerce-news","sourceUrl":"https://clawhub.ai/xuxinmaxen/agentic-commerce-news","homepage":"https://clawhub.ai/xuxinmaxen/skills/agentic-commerce-news","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/xuxinmaxen/agentic-commerce-news","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/xuxinmaxen/skills/agentic-commerce-news","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,... "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T11:25:19.765Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T11:25:19.765Z","emptyReason":null},"stars":null,"forks":null,"downloads":1077,"packageName":null,"latestVersion":"1.2.0","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T11:25:19.750Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T11:25:19.765Z","lastCrawledAt":"2026-10-11T11:25:19.750Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T11:25:19.750Z","lastVerifiedAt":null,"highlights":[{"version":"1.2.0","createdAt":"2026-07-03T03:39:53.352Z","changelog":"Cross-week dedup: reads the most recent file in briefings/ and skips already-covered items unless there's a material new development. Mandatory source-date spot-check: top 3 items and any fuzzy-dated item get their publish date confirmed on the source page via WebFetch. Two new quality gates. Ships the published briefing archive (briefings/).","fileCount":8,"zipByteSize":17161},{"version":"1.1.0","createdAt":"2026-06-15T13:00:48.013Z","changelog":"English-only docs and output templates (default output language switched to English, multilingual support retained). Fixed evals skill_name (was agentic-commerce-scout). Added MIT-0 LICENSE. Now mirrored on GitHub: github.com/xuxinmaxen/agentic-commerce-news.","fileCount":6,"zipByteSize":9206},{"version":"1.0.1","createdAt":"2026-04-17T02:30:03.489Z","changelog":"agentic-commerce-news 1.0.1 - Clarified the skill's description, emphasizing triggers like \"AI shopping agent startups\", \"agent checkout products\", and general requests for agentic commerce updates — even when the skill isn't named explicitly. - Expanded trigger examples to include broader, more natural user questions about agentic commerce news, funding, or setting up digests. - No changes to logic or workflow; only the description was improved for usability and discoverability. - No code or functionality changes detected in this version.","fileCount":4,"zipByteSize":8086},{"version":"1.0.0","createdAt":"2026-04-15T07:20:47.366Z","changelog":"Initial release: agentic commerce weekly news briefing with 9-layer taxonomy","fileCount":3,"zipByteSize":6988}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1739vmxqjbzgqhnwf0tchgh2184w0pt:agentic-commerce-news","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T14:16:05.227Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xuxinmaxen-agentic-commerce-news/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T11:25:19.765Z","emptyReason":null},"readme":"Skill: Agentic Commerce News\n\nOwner: xuxinmaxen\n\nSummary: Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,...\n\nTags: agentic-commerce:1.1.0, ai-commerce:1.1.0, latest:1.2.0, news:1.1.0, research:1.1.0, scheduling:1.1.0\n\nVersion history:\n\nv1.2.0 | 2026-07-03T03:39:53.352Z | user\n\nCross-week dedup: reads the most recent file in briefings/ and skips already-covered items unless there's a material new development. Mandatory source-date spot-check: top 3 items and any fuzzy-dated item get their publish date confirmed on the source page via WebFetch. Two new quality gates. Ships the published briefing archive (briefings/).\n\nv1.1.0 | 2026-06-15T13:00:48.013Z | user\n\nEnglish-only docs and output templates (default output language switched to English, multilingual support retained). Fixed evals skill_name (was agentic-commerce-scout). Added MIT-0 LICENSE. Now mirrored on GitHub: github.com/xuxinmaxen/agentic-commerce-news.\n\nv1.0.1 | 2026-04-17T02:30:03.489Z | user\n\nagentic-commerce-news 1.0.1\n\n- Clarified the skill's description, emphasizing triggers like \"AI shopping agent startups\", \"agent checkout products\", and general requests for agentic commerce updates — even when the skill isn't named explicitly.\n- Expanded trigger examples to include broader, more natural user questions about agentic commerce news, funding, or setting up digests.\n- No changes to logic or workflow; only the description was improved for usability and discoverability.\n- No code or functionality changes detected in this version.\n\nv1.0.0 | 2026-04-15T07:20:47.366Z | user\n\nInitial release: agentic commerce weekly news briefing with 9-layer taxonomy\n\nArchive index:\n\nArchive v1.2.0: 8 files, 17161 bytes\n\nFiles: briefings/2026-06-29.md (13031b), briefings/README.md (1052b), evals/evals.json (1339b), LICENSE (917b), README.md (5937b), skill-card.md (2495b), SKILL.md (10294b), _meta.json (140b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: agentic-commerce-news\ndescription: \"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.\"\nallowed-tools: WebSearch, WebFetch\n---\n\n# Agentic Commerce News\n\nYou are a news analyst covering the agentic commerce beat. Your job is to scan X/Twitter, industry media, VC announcements, and conference coverage to find **the past week's** most noteworthy startups, products, funding rounds, and opinions from influential people (VCs, founders, AI leaders) in the agentic commerce space.\n\nThink of yourself as a weekly newsletter editor: what happened this week that someone building in agentic commerce absolutely needs to know?\n\n## Why this matters\n\nAgentic commerce — where AI agents shop, compare, and buy on behalf of humans — is a rapidly forming market ($135B in 2025, projected $1.7T by 2030). The landscape shifts weekly as new protocols (ACP, UCP), platforms (ChatGPT Shopping, Perplexity Buy with Pro), and infrastructure layers emerge. The user needs a curated, credible, **timely** signal — not stale noise.\n\n## Time Window\n\n**All searches must focus on the past 7 days.** This is a news product, not a research report.\n\nWhen constructing search queries, always include date-scoping keywords to get fresh results:\n- Use \"this week\", \"today\", \"yesterday\", or the specific date range (e.g., \"April 8-15 2026\")\n- Use the current year and month explicitly\n- If a search returns mostly older results, add the current month name or specific dates to narrow it down\n\nOlder context (e.g., a company's founding story or total funding to date) is fine as background, but the **trigger for inclusion** must be something that happened in the past 7 days: a new tweet, a funding announcement, a product launch, a keynote, a partnership, a blog post.\n\n## Scheduling Support\n\nThis skill supports scheduled execution. When the user asks to set up a recurring job, handle it based on their environment:\n\n**Claude Code — Session-scoped (CronCreate):**\nIf the user says something like \"set up a daily digest at 8am\" or \"push it to me every morning\", and they're running in Claude Code:\n\nUse the `CronCreate` tool with:\n- `cron`: an appropriate expression that avoids the :00 mark (e.g., `\"3 8 * * *\"` for ~8am daily, nudge a few minutes off the round hour to avoid API pile-ups)\n- `prompt`: `\"Run the agentic-commerce-news skill: scan the past 7 days of agentic commerce activity and generate the weekly briefing.\"`\n- `recurring`: `true`\n\nTell the user:\n- Scheduled jobs live in the current Claude session memory (not persisted to disk by default — pass `durable: true` if they want it to survive restarts)\n- Recurring tasks auto-expire after 7 days of this session\n- Jobs only fire while the REPL is idle\n\n**Claude Code — Persistent (remote triggers):**\nIf the user wants a schedule that runs even when their laptop is closed, suggest they use the `/schedule` skill to create a remote trigger (managed by claude.ai). This runs on Anthropic's infrastructure, not locally.\n\n**OpenClaw:**\nIf the environment has `openclaw` CLI available (check with `which openclaw`), use `openclaw cron add` instead. OpenClaw jobs run 24/7 as a persistent agent.\n\n**Other runtimes:**\nIf none of the above is available, fall back to system `crontab` with a script that invokes the CLI (advanced).\n\n## Execution Flow\n\n### Phase 1: Broad Search (parallel, 8-12 queries)\n\nLaunch WebSearch queries in parallel. Every query must be scoped to recent content. Adapt the date references to the current date:\n\n**Breaking news & announcements:**\n- `\"agentic commerce\" news this week {current_month} {current_year}`\n- `\"agentic commerce\" startup launch OR funding OR announced {current_month} {current_year}`\n\n**VC & Investment (this week):**\n- `agentic commerce startup funding raised {current_month} {current_year}`\n- `YC OR a16z OR Sequoia \"agentic commerce\" OR \"AI shopping\" investment {current_year}`\n\n**Influencer activity (this week):**\n- `agentic commerce tweet site:x.com {current_month} {current_year}`\n- `\"agentic commerce\" OR \"AI shopping agent\" CEO founder opinion {current_month} {current_year}`\n\n**Product launches & updates:**\n- `agentic commerce product launch update new feature {current_month} {current_year}`\n- `AI shopping agent checkout new product {current_month} {current_year}`\n\n**Protocol & platform moves:**\n- `Shopify OR OpenAI OR Google agentic commerce update {current_month} {current_year}`\n- `Visa OR Mastercard OR Stripe agentic commerce news {current_month} {current_year}`\n\n**Vertical signals:**\n- `agentic checkout payment startup news {current_month} {current_year}`\n- `brand AI agent storefront discovery news {current_month} {current_year}`\n\n### Phase 2: Verify recency & fill gaps\n\nFrom Phase 1 results, filter strictly:\n- **Keep** only items with activity in the past 7 days\n- **Drop** anything that's just a rehash of old news\n- For promising leads, do a quick targeted search to confirm details (funding amount, investor names, product specifics)\n\n**Source date spot-check (mandatory):** search-result snippets routinely misreport dates, and SEO farms recycle old news with fresh timestamps. Before finalizing, WebFetch the actual source page for **at least the top 3 items** and for **any item whose date is fuzzy** (\"recently\", \"this month\", undated). Confirm the publish date on the page itself. If a date can't be confirmed inside the 7-day window, either drop the item or include it with an explicit date caveat visible in the card — never present an unverified date as fact.\n\n### Phase 2.5: Dedupe against previous briefings\n\nIf a `briefings/` directory exists alongside this SKILL.md (it does in the git repo), read the **most recent** briefing file before finalizing:\n\n- **Skip** any item already covered in the previous briefing, unless there is a material new development this week (a new funding stage, GA after a beta, a major partner joining, a reversal).\n- When you keep a follow-up item, say what's *new* in the first line and add \"(follow-up to last week)\" so readers see continuity, not repetition.\n- Cross-week repetition is the fastest way to make a weekly briefing feel worthless — when in doubt, cut.\n\nIf no archive is available (e.g., skill installed standalone), skip this phase silently.\n\n### Phase 3: Classify into the Agentic Commerce Stack\n\nOrganize qualifying items into layers:\n\n| Layer | Description |\n|-------|-------------|\n| Brand Discovery | Help brands get found by AI agents (GEO, catalog optimization) |\n| Brand Storefront | Brand presence inside LLM environments |\n| Checkout Execution | Complete purchases on behalf of agents |\n| Payment Infrastructure | Financial rails for agent transactions |\n| Consumer Agent | End-user AI shopping assistants |\n| Agent Framework | Platforms for building commerce-capable agents |\n| Enterprise Procurement | B2B purchasing automation via agents |\n| Retail Decision Intelligence | AI-powered merchandising and pricing decisions |\n| Full-Stack Platform | End-to-end agentic commerce solutions |\n\n### Phase 4: Generate the weekly briefing\n\nStructure the output as a news briefing:\n\n**Header:**\n```\n## Agentic Commerce Weekly Briefing ({date_range})\n> {N} noteworthy signals from the past week\n```\n\n**For each item, use this card format:**\n\n```\n### ProductName (Event type: Funding / Product launch / Endorsement / Partnership / Opinion) — one-line summary\n\n**Date:** specific date\n**Endorsement:** who said it / who invested / who partnered\n\n**Key points:**\n- point 1\n- point 2\n- point 3\n\n**Layer:** xxx\n\nSource: https://...\n```\n\nGroup cards by event type (Funding → Product launches → Founder / VC opinions → Partnerships & ecosystem → Industry reports), not by layer.\n\n### Phase 5: Summary table\n\n```\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| 4/12 | Wildcard | Product launch | Launched ChatGPT Shopping optimization tool v2 | Brand Discovery |\n| ... | ... | ... | ... | ... |\n```\n\n### Phase 6: Weekly trend takeaways\n\nClose with 3-5 short observations:\n- This week's biggest signal\n- Money flow direction\n- What big players are doing\n- Emerging themes vs. last week\n- One thing to watch next week\n\n## Quality Gates\n\n- **Recency is the #1 filter.** If it didn't happen this week, it doesn't belong (unless it's essential background for a this-week event).\n- **Credible endorsement required.** Every item must have: VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership.\n- **Source links are mandatory.** No link, no inclusion.\n- **Minimum 5 items.** If it's a quiet week, 5 is OK. If you can't find 5, say so honestly rather than padding with old news.\n- **No pay-to-play.** Exclude items that only appear in sponsored content.\n- **Dates are verified, not assumed.** Top items and fuzzy-dated items must have their publish date confirmed on the source page (Phase 2), not inferred from a search snippet.\n- **No cross-week repeats.** An item covered in the previous briefing only returns with a material new development, labeled as a follow-up (Phase 2.5).\n\n## Language\n\nMatch the user's language. Default to English. If the user writes in another language (e.g. Chinese), respond in that language while keeping product names and proper nouns in English.\n\n## When the user asks for a specific vertical\n\nFocus searches and output on that vertical only. Skip the full taxonomy.\n\n## When the user asks to go deeper on a specific item\n\nSwitch to deep-dive mode: search for full details on the company/event and output a research memo.\n\nFile v1.2.0:briefings/README.md\n\n# Briefing Archive\n\nPublished output of this skill — one file per week, newest first.\n\nEach briefing is generated by running `/agentic-commerce-news` in Claude Code, then committed here verbatim (sources and all). If you want to judge whether the skill is worth installing, read one of these first: the archive **is** the demo.\n\n| Week | File |\n|------|------|\n| Jun 26 – Jul 3, 2026 | [2026-06-29.md](./2026-06-29.md) |\n\n## Format\n\nEvery file follows the structure defined in [`SKILL.md`](../SKILL.md):\n\n- Cards grouped by event type — **Funding / Product Launches / Founder & VC Opinions / Partnerships / Reports**\n- Every item: date, endorsement (who backed or amplified it), key points, [9-layer stack](../SKILL.md) classification, and a source link\n- An **At a Glance** table plus 2–3 **Weekly Takeaways**\n\n## Contributing a week\n\nRun the skill yourself and open a PR adding `YYYY-MM-DD.md` (the Monday of that week). Briefings must pass the skill's quality gates — 7-day window, credible endorsement, source link per item, no PR fluff.\n\nFile v1.2.0:README.md\n\n# agentic-commerce-news\n\n> Agentic Commerce Weekly Briefing — scans the past 7 days of X/Twitter, industry media, and VC announcements for startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing.\n\n### 📰 [Read the latest briefing](./briefings/2026-06-29.md) · [archive](./briefings/)\n\nEvery week's output is published in [`briefings/`](./briefings/) — read one before installing; the archive **is** the demo.\n\n## What it does\n\nA news aggregation skill focused on **agentic commerce** — the rapidly evolving space where AI agents shop, compare, check out, and pay on behalf of humans. On every invocation, it:\n\n1. Launches 10+ parallel WebSearch queries across different angles, scoped to the past 7 days\n2. Filters results to items with credible VC / institutional / platform endorsement\n3. Classifies each item into the 9-layer Agentic Commerce Stack (Brand Discovery → Payments → Consumer Agent → Full-Stack Platform)\n4. Generates cards grouped by event type (funding / product launch / founder quote / partnership / report)\n5. Appends a summary table and weekly trend takeaways\n\n## When it triggers\n\n- User types `/agentic-commerce-news`\n- User mentions keywords like \"agentic commerce news\", \"AI commerce updates\", \"agent shopping this week\"\n- User asks things like \"what's new in agentic commerce this week?\" or \"who's funding AI shopping startups?\"\n- User asks to set up a scheduled/recurring digest on agentic commerce\n\n## Scheduling\n\nThree ways to run this on a schedule, depending on your environment:\n\n| Environment | Command | Notes |\n|-------------|---------|-------|\n| Claude Code (session) | `CronCreate` tool | In-session only, not persisted across restarts |\n| Claude Code (persistent) | `/schedule` skill | Runs on claude.ai infrastructure, survives restarts |\n| OpenClaw | `openclaw cron add` | 24/7 background execution |\n\n### Example: Daily 8am digest in Claude Code\n\nSay to Claude:\n> \"Set up a daily task to run agentic-commerce-news at 8am.\"\n\nClaude will use `CronCreate` with `\"3 8 * * *\"` (8:03am — nudged a few minutes off the round hour to avoid API pile-ups).\n\n### Example: OpenClaw persistent schedule\n\n```bash\nopenclaw cron add \\\n  --name \"Agentic Commerce Daily\" \\\n  --cron \"3 8 * * *\" \\\n  --tz \"America/New_York\" \\\n  --message \"Run the agentic-commerce-news skill to surface the past week's agentic commerce activity\" \\\n  --channel <your-channel> \\\n  --to \"<your-id>\"\n```\n\n## Quality Gates\n\n- Only items from the past 7 days qualify\n- Every item must have credible endorsement (VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership)\n- Every item must include a source link\n- Minimum 5 items (a quiet week is OK — do not pad with stale news)\n- Exclude pure PR / sponsored content\n- Publish dates of top items are confirmed on the source page, not inferred from search snippets\n- Items covered in the previous briefing (see [`briefings/`](./briefings/)) don't repeat unless there's a material new development\n\n## Output Format\n\n```\n## Agentic Commerce Weekly Briefing (Apr 8 – Apr 15)\n> 8 noteworthy signals from the past week\n\n### Funding\n### ProductName (raised $XM) — one-line summary\n**Date:** Apr 12\n**Endorsement:** who invested\n**Key points:**\n- point 1\n- point 2\n**Layer:** Payment Infrastructure\nSource: https://...\n\n### Product Launches\n...\n\n### Founder / VC Opinions\n...\n\n## At a Glance\n\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| ... | ... | ... | ... | ... |\n\n## Weekly Takeaways\n1. ...\n2. ...\n```\n\n## Installation\n\n### Option A: Clone from GitHub\n\n```bash\ngit clone https://github.com/xuxinmaxen/agentic-commerce-news.git \\\n  ~/.claude/skills/agentic-commerce-news\n```\n\nRestart your Claude Code session to pick it up.\n\n### Option B: Install from ClawHub\n\n```bash\nclawhub install agentic-commerce-news\n```\n\n### Option C: Manual copy (Claude Code)\n\n```bash\n# Copy into ~/.claude/skills/\ncp -r agentic-commerce-news ~/.claude/skills/\n\n# Verify frontmatter\ncat ~/.claude/skills/agentic-commerce-news/SKILL.md | head -5\n```\n\nRestart your Claude Code session to pick it up.\n\n## Dependencies\n\n- Claude Code ≥ 1.0 (requires the `WebSearch` tool)\n- (Optional) `CronCreate` tool or `openclaw cron` — for scheduled execution\n- **No** API keys or external services required\n\n## Privacy & Data Sources\n\nThis skill reads only **publicly available** information and stores **no personal data**:\n\n- **Sources**: public web search results, public posts on X/Twitter, public industry blogs and media, and publicly announced VC funding data.\n- **No personal data is collected or stored.** Results are used only for in-session synthesis of the briefing — nothing is persisted to disk or sent to any third-party server beyond the standard web-search / web-fetch calls Claude already performs.\n- **No credentials required.** The skill needs no API keys, tokens, or logins.\n- **Tools used**: `WebSearch` and `WebFetch` (read-only). Optionally `CronCreate` (Claude Code) or `openclaw cron` only if you explicitly ask it to run on a schedule.\n- Please respect the terms of service of any source consulted.\n\n## Customization\n\nTo adjust the search strategy:\n\n1. Edit the Phase 1 section of `SKILL.md` to add or replace WebSearch query templates\n2. Edit the Phase 3 classification table to introduce new vertical segments\n3. Edit the Phase 4 card format to tweak output style\n\nTo change the time window (e.g., 3 days or 30 days instead of 7):\n\n- Update the `## Time Window` section's \"past 7 days\" phrasing\n- Adjust the `this week` / `today` keywords in the search queries\n\n## License\n\nMIT-0 (MIT No Attribution) — free to use, modify, and redistribute. No attribution required. See [LICENSE](LICENSE).\n\nFile v1.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn7d2dhgbt152nj3ywh93f507h84xk7w\",\n  \"slug\": \"agentic-commerce-news\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1783049993352\n}\n\nFile v1.2.0:briefings/2026-06-29.md\n\n# Agentic Commerce Weekly Briefing (Jun 26 – Jul 3, 2026)\n\n> Generated by the [agentic-commerce-news](https://github.com/xuxinmaxen/agentic-commerce-news) Claude Code skill on 2026-07-03.\n\n> 7 noteworthy signals from the past week\n\n## Funding\n\nNo qualifying funding rounds this week. The closest miss was Seltz's $12.5M seed (agent-native web search infrastructure, led by Speedinvest and B Capital), announced June 24 — two days before this briefing's window opened ([Fortune](https://fortune.com/2026/06/24/exclusive-seltz-a-startup-rebuilding-web-search-for-ai-agents-raises-12-5-million-in-seed-funding/)). Rather than pad with stale deals, we're calling it honestly: agentic commerce venture money took a breather this week, even as strategic capital moved massively (see Open USD below).\n\n## Product Launches\n\n### Salesforce Agentforce Commerce (Event type: Product launch) — Salesforce ships its \"biggest Agentforce Commerce release yet,\" wiring merchant catalogs directly into ChatGPT and Google AI surfaces\n\n**Date:** Late June 2026 (week of Jun 29; ChatGPT channel GA lands July 2026)\n**Endorsement:** Official platform partnerships with OpenAI (ChatGPT catalog integration GA July 2026) and Google (AI Mode + Gemini app GA summer 2026); announced by Nitin Mangtani, EVP & GM of Agentforce Commerce\n\n**Key points:**\n- Agentic Commerce Channels sync merchant product catalogs from Business Manager directly into ChatGPT (GA July 2026) and Google Search AI Mode / Gemini app (GA summer 2026) — no extra software or third-party connectors; the merchant stays merchant of record and orders land on their existing platform\n- Ships a workforce of ready-to-deploy agents: Shopper Agent (discovery-to-checkout-to-service on brand properties), Buyer Agent (B2B via WhatsApp/SMS), and Merchant Agent (catalog and merchandising in plain language), plus GA of Storefront Next and an Agentic B2C Developer Toolkit (CLI, MCP server, IDE extension)\n- Salesforce's supporting data: AI influenced 20% of global online sales ($262B) this past holiday season, and retailers running their own shopper agents grew sales 59% faster than those without. Mangtani's thesis: \"The brands that win will have their Shopper Agent live on their own properties for the 2026 shopping season\"\n\n**Layer:** Full-Stack Platform\n\nSource: https://www.salesforce.com/news/stories/agentforce-commerce-announcement/ (see also [CX Today](https://www.cxtoday.com/crm/salesforce-agentforce-commerce-generally-available/))\n\n## Founder / VC Opinions\n\n### Signifyd — Nicole Jass (Event type: Opinion) — \"Agentic commerce is moving both faster and slower than the buzz\": LLM referrals up 600%+ YoY, but agent-executed purchases still under 1% of orders\n\n**Date:** June 30, 2026\n**Endorsement:** Nicole Jass, SVP of Enterprise Strategy at Signifyd, backed by Signifyd's live merchant network data\n\n**Key points:**\n- Online orders from LLM referrals are up more than 600% year over year across Signifyd's network — the discovery shift is real and accelerating\n- But purchases actually executed by AI agents remain under 1% of all orders — the \"set-it-and-forget-it\" autonomous agent narrative is outrunning reality\n- Practical read for retailers: optimize for AI-driven discovery traffic now (it converts), while treating fully autonomous checkout as a 2027+ bet rather than a 2026 requirement\n\n**Layer:** Retail Decision Intelligence\n\nSource: https://www.retailcustomerexperience.com/blogs/the-now-and-next-steps-retailers-should-take-in-the-agentic-commerce-era/\n\n### American Banker (Event type: Opinion) — When software becomes the shopper, issuers must compete for algorithms, not humans\n\n**Date:** June 30, 2026\n**Endorsement:** American Banker payments opinion section, citing Morgan Stanley estimates\n\n**Key points:**\n- Morgan Stanley estimates agentic shoppers could represent $190B–$385B in US e-commerce spending by 2030 — 10% to 20% of market share\n- Core argument: purchasing decisions will be made at machine speed, and agents will optimize for price, delivery speed, rewards, financing terms, and protections in real time — card issuers' human-oriented loyalty playbooks won't survive contact with an optimizing agent\n- \"When software becomes the shopper, trust becomes the fundamental principle\" — issuers and merchants need machine-readable trust signals, not brand advertising\n\n**Layer:** Payment Infrastructure\n\nSource: https://www.americanbanker.com/payments/opinion/agentic-commerce-is-going-to-require-rethinking-consumer-payments\n\n## Partnerships & Ecosystem\n\n### Open USD / OUSD (Event type: Partnership) — Stripe, Visa, Mastercard, Google, Shopify and 140+ firms back a shared stablecoin — the settlement rail play for agentic commerce\n\n**Date:** June 30, 2026\n**Endorsement:** 140+ launch partners including Visa, Mastercard, American Express, Stripe, Adyen, Klarna, BlackRock, BNY, Coinbase, Google, Shopify, Samsung, and DoorDash; led by Zach Abrams (co-founder of Bridge, acquired by Stripe)\n\n**Key points:**\n- Open Standard announced Open USD (OUSD), a US dollar stablecoin with no mint/redeem fees and reserve revenue shared back to participating partners — a direct structural challenge to Circle (CRCL fell ~17% on the news) and Tether\n- Stripe is making OUSD the default stablecoin for businesses transacting on Stripe; Coinbase is bringing it to Base; launch slated for later this year\n- Agentic commerce relevance: nearly every major agent-payments initiative announced this year (Mastercard AP4M, Stripe/Tempo's Machine Payments Protocol) lists stablecoin settlement as a core rail for high-frequency, sub-cent agent-to-agent transactions — OUSD is the ecosystem consolidating on whose stablecoin that will be, with commerce platforms (Shopify, Google) at the table from day one\n\n**Layer:** Payment Infrastructure\n\nSource: https://fortune.com/2026/06/30/stripe-visa-stablecoin-rival-ousd-tether-circle/ (see also [CoinDesk](https://www.coindesk.com/business/2026/06/30/circle-slides-8-as-stripe-coinbase-and-blackrock-back-rival-stablecoin-network), [American Banker](https://www.americanbanker.com/payments/news/open-standards-stablecoin-draws-stripe-visa-and-mastercard))\n\n### Amazon × OpenAI (Event type: Partnership) — Amazon starts buying ads inside ChatGPT to promote Prime Day, even while blocking ChatGPT's crawlers\n\n**Date:** June 26, 2026\n**Endorsement:** Amazon's first paid promotion as an advertiser in OpenAI's ChatGPT ad system; spotted and verified by independent e-commerce analyst Juozas Kaziukėnas\n\n**Key points:**\n- A ChatGPT query for \"best deal on Apple 11-inch iPad\" surfaced a sponsored Prime Day ad routing shoppers to Amazon's site — Amazon's first paid placement in the ChatGPT ecosystem since OpenAI opened ads to US free/Go-tier users in February\n- The strategic irony: Amazon still blocks ~100 bots including ChatGPT's crawlers from reading its listings, and is simultaneously litigating against Perplexity's Comet agent — yet it now pays to appear inside the assistant it locks out. AI chat surfaces have become too large a demand source for even the biggest vertical player to ignore\n- Sits atop a deepening capital relationship: OpenAI's $38B AWS deal and Amazon's planned $50B investment in OpenAI\n\n**Layer:** Brand Discovery\n\nSource: https://www.modernretail.co/technology/amazon-buys-ads-in-chatgpt-to-promote-prime-day/ (see also [Shopifreaks](https://www.shopifreaks.com/amazon-begins-advertising-on-chatgpt-and-its-ads-have-been-spotted-in-the-wild/))\n\n## Industry Reports\n\n### Adobe Prime Day Data (Event type: Industry report) — AI-referred shoppers converted 40% better than search/email/social during a record $26.4B Prime Day\n\n**Date:** June 30, 2026 (Prime Day ran June 23–26)\n**Endorsement:** Adobe Analytics (Adobe Digital Insights), covered by GeekWire and Tech Times\n\n**Key points:**\n- US shoppers spent a record $26.4B across retail sites during the four-day Prime Day event — and for the first time, visitors arriving from AI chatbots were the most likely cohort to complete a purchase\n- Adobe: shoppers who clicked through from AI assistants were 40% more likely to buy than those arriving via search, email, or social — the strongest public conversion evidence yet that AI referral traffic is high-intent, not just high-volume\n- Frames Amazon's dilemma (and its ChatGPT ad buy above): AI assistants are becoming the highest-quality top-of-funnel in e-commerce, testing Amazon's walled-garden posture\n\n**Layer:** Consumer Agent\n\nSource: https://www.geekwire.com/2026/prime-day-shows-how-ai-is-changing-shopping-testing-amazons-bet-against-chatgpt-and-others/ (see also [Tech Times](https://www.techtimes.com/articles/319387/20260630/amazon-chatgpt-ads-ai-shoppers-converted-40-better-search-during-prime-day.htm))\n\n### PYMNTS Intelligence × Visa Acceptance Solutions (Event type: Industry report) — AI shopping assistants are now the #1 digital investment priority for retailers\n\n**Date:** July 1, 2026\n**Endorsement:** PYMNTS Intelligence \"Global Digital Shopping Index: The AI-Powered Shopper Has Arrived,\" commissioned by Visa Acceptance Solutions (5,841 consumers + 1,185 merchants surveyed across US, Brazil, UAE)\n\n**Key points:**\n- AI shopping assistants are the most frequently cited digital capability merchants plan to invest in over the next three years, selected by 37% of retailers — the first time AI assistants top the retail investment stack\n- 47% of online shoppers used some form of AI during their most recent purchase, and 64% expect to use AI shopping agents within two years\n- Caution flag inside the same data: merchant support for cross-channel shopping and stored payment methods actually declined, and the number of features merchants have \"no plans\" to offer hit a four-year high — investment is concentrating into AI assistants at the expense of other digital capabilities\n\n**Layer:** Retail Decision Intelligence\n\nSource: https://www.pymnts.com/news/artificial-intelligence/2026/ai-shopping-assistants-top-retail-budgets/\n\n## At a Glance\n\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| ~6/29 | Salesforce | Product launch | Biggest Agentforce Commerce release: catalogs wired into ChatGPT (GA July) and Google AI surfaces | Full-Stack Platform |\n| 6/30 | Signifyd (Nicole Jass) | Opinion | LLM referrals +600% YoY but agent-executed purchases <1% of orders | Retail Decision Intelligence |\n| 6/30 | American Banker / Morgan Stanley | Opinion | Agentic shoppers = $190B–$385B of US e-commerce by 2030; issuers must court algorithms | Payment Infrastructure |\n| 6/30 | Open Standard (OUSD) | Partnership | Visa, Mastercard, Stripe, Google, Shopify + 140 firms back shared stablecoin for the agent economy | Payment Infrastructure |\n| 6/26 | Amazon × OpenAI | Partnership | Amazon runs its first paid ads inside ChatGPT to promote Prime Day | Brand Discovery |\n| 6/30 | Adobe | Industry report | AI-referred shoppers converted 40% better during record $26.4B Prime Day | Consumer Agent |\n| 7/1 | PYMNTS × Visa | Industry report | AI shopping assistants top retailer digital investment priorities (37%) | Retail Decision Intelligence |\n\n## Weekly Takeaways\n\n1. **Biggest signal: AI referral traffic now provably converts.** Adobe's Prime Day data (AI-referred shoppers +40% conversion vs. search/email/social) is the hardest evidence yet that AI assistants are the highest-intent acquisition channel in e-commerce — and Signifyd's +600% LLM referral growth corroborates it from the fraud-network side. The entrance layer of commerce is repricing in real time.\n\n2. **Money flowed strategic, not venture.** Zero qualifying startup rounds this week, but 140+ corporates committed to Open USD in a single announcement. The capital story in agentic commerce right now is incumbents collectively building shared settlement rails, not VCs writing seed checks.\n\n3. **Amazon blinked.** The company suing Perplexity and blocking ChatGPT's crawlers just bought ads inside ChatGPT. When the largest vertical player pays to appear on a horizontal agent surface it actively litigates against, the \"walled garden vs. open agent\" debate has a directional answer.\n\n4. **The narrative split is now quantified: discovery is agentic, checkout is not.** Salesforce claims AI influenced 20% of holiday sales and PYMNTS says 64% of consumers expect AI agents within two years — yet agent-executed purchases are still under 1% of orders (Signifyd). Builders should ship for AI-driven discovery today and treat autonomous checkout as the next wave, not this one.\n\n5. **Watch next week:** Salesforce's ChatGPT channel hits GA in July — the first mass-market test of catalog-native brand storefronts inside ChatGPT for enterprise merchants — and the Ninth Circuit's pending Amazon v. Perplexity ruling (argued June 11) could land any week, setting the legal boundary for whether agents may shop logged-in retail sites at all.\n\nFile v1.2.0:skill-card.md\n\n## Description:\n\nScans recent public web, industry media, and VC announcements to produce a structured briefing on agentic commerce startups, products, funding rounds, partnerships, and influential opinions.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xuxinmaxen](https://clawhub.ai/user/xuxinmaxen)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, founders, investors, and commerce operators use this skill to monitor the agentic commerce market and receive timely briefings with dated sources, stack-layer classifications, summary tables, and trend takeaways. It can also guide setup of recurring digests when the user's agent environment supports scheduling.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Recurring digest setup can create background jobs through agent schedulers or system cron.\n\nMitigation: Only create a recurring job after showing the exact scheduler, command or prompt, schedule, expiration, and cancellation steps; prefer platform-managed schedulers and use system crontab only when the user explicitly wants a local persistent job.\n\nRisk: Public web searches and fetched source pages can include stale, recycled, or misleading news dates.\n\nMitigation: Confirm publish dates on source pages for top items and fuzzy-dated items, drop items outside the requested window, and cite source links for every included signal.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/xuxinmaxen/skills/agentic-commerce-news)\n- [README](artifact/README.md)\n- [Briefing archive](artifact/briefings/README.md)\n- [Latest briefing example](artifact/briefings/2026-06-29.md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown briefing with source links, grouped news cards, a summary table, weekly takeaways, and optional scheduling commands.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Uses public web search and source fetching; briefing items are expected to be recent, source-linked, date-checked, and deduplicated against the latest archive entry when available.]\n\n## Skill Version(s):\n\n1.2.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.0:evals/evals.json\n\n{\n  \"skill_name\": \"agentic-commerce-news\",\n  \"evals\": [\n    {\n      \"id\": 1,\n      \"prompt\": \"Show me the most noteworthy startups in agentic commerce lately, especially the ones endorsed by prominent VCs and founders.\",\n      \"expected_output\": \"Structured briefing with 10+ startups that have VC/institutional endorsement, classified by layer. Each item includes name, positioning, funding, endorsement, key capabilities, and a source link, followed by a summary table and trend takeaways.\",\n      \"files\": []\n    },\n    {\n      \"id\": 2,\n      \"prompt\": \"I'm building an agentic commerce product and need inspiration. What startups are VCs and AI leaders talking about in the checkout and payment infrastructure space?\",\n      \"expected_output\": \"Focused report on checkout execution and payment infrastructure layer startups, with detailed cards for companies like Rye, Firmly, Nekuda, Skyfire, Basis Theory etc., including VC backing and endorsement sources.\",\n      \"files\": []\n    },\n    {\n      \"id\": 3,\n      \"prompt\": \"Which AI shopping startups raised funding recently? Pull together a summary for me.\",\n      \"expected_output\": \"Funding-focused roundup ordered by amount or date. Each item includes funding details, investors, product positioning, and a source link, ending with a trend summary.\",\n      \"files\": []\n    }\n  ]\n}\n\nFile v1.2.0:LICENSE\n\nMIT No Attribution\n\nCopyright 2026 Maxen Xu (@xuxinmaxen)\n\nPermission is hereby granted, free of charge, to any person obtaining a copy of this\nsoftware and associated documentation files (the \"Software\"), to deal in the Software\nwithout restriction, including without limitation the rights to use, copy, modify,\nmerge, publish, distribute, sublicense, and/or sell copies of the Software, and to\npermit persons to whom the Software is furnished to do so.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,\nINCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A\nPARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT\nHOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION\nOF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE\nSOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\nArchive v1.1.0: 6 files, 9206 bytes\n\nFiles: evals/evals.json (1339b), LICENSE (917b), README.md (4670b), skill-card.md (2230b), SKILL.md (8662b), _meta.json (140b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: agentic-commerce-news\ndescription: \"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.\"\n---\n\n# Agentic Commerce News\n\nYou are a news analyst covering the agentic commerce beat. Your job is to scan X/Twitter, industry media, VC announcements, and conference coverage to find **the past week's** most noteworthy startups, products, funding rounds, and opinions from influential people (VCs, founders, AI leaders) in the agentic commerce space.\n\nThink of yourself as a weekly newsletter editor: what happened this week that someone building in agentic commerce absolutely needs to know?\n\n## Why this matters\n\nAgentic commerce — where AI agents shop, compare, and buy on behalf of humans — is a rapidly forming market ($135B in 2025, projected $1.7T by 2030). The landscape shifts weekly as new protocols (ACP, UCP), platforms (ChatGPT Shopping, Perplexity Buy with Pro), and infrastructure layers emerge. The user needs a curated, credible, **timely** signal — not stale noise.\n\n## Time Window\n\n**All searches must focus on the past 7 days.** This is a news product, not a research report.\n\nWhen constructing search queries, always include date-scoping keywords to get fresh results:\n- Use \"this week\", \"today\", \"yesterday\", or the specific date range (e.g., \"April 8-15 2026\")\n- Use the current year and month explicitly\n- If a search returns mostly older results, add the current month name or specific dates to narrow it down\n\nOlder context (e.g., a company's founding story or total funding to date) is fine as background, but the **trigger for inclusion** must be something that happened in the past 7 days: a new tweet, a funding announcement, a product launch, a keynote, a partnership, a blog post.\n\n## Scheduling Support\n\nThis skill supports scheduled execution. When the user asks to set up a recurring job, handle it based on their environment:\n\n**Claude Code — Session-scoped (CronCreate):**\nIf the user says something like \"set up a daily digest at 8am\" or \"push it to me every morning\", and they're running in Claude Code:\n\nUse the `CronCreate` tool with:\n- `cron`: an appropriate expression that avoids the :00 mark (e.g., `\"3 8 * * *\"` for ~8am daily, nudge a few minutes off the round hour to avoid API pile-ups)\n- `prompt`: `\"Run the agentic-commerce-news skill: scan the past 7 days of agentic commerce activity and generate the weekly briefing.\"`\n- `recurring`: `true`\n\nTell the user:\n- Scheduled jobs live in the current Claude session memory (not persisted to disk by default — pass `durable: true` if they want it to survive restarts)\n- Recurring tasks auto-expire after 7 days of this session\n- Jobs only fire while the REPL is idle\n\n**Claude Code — Persistent (remote triggers):**\nIf the user wants a schedule that runs even when their laptop is closed, suggest they use the `/schedule` skill to create a remote trigger (managed by claude.ai). This runs on Anthropic's infrastructure, not locally.\n\n**OpenClaw:**\nIf the environment has `openclaw` CLI available (check with `which openclaw`), use `openclaw cron add` instead. OpenClaw jobs run 24/7 as a persistent agent.\n\n**Other runtimes:**\nIf none of the above is available, fall back to system `crontab` with a script that invokes the CLI (advanced).\n\n## Execution Flow\n\n### Phase 1: Broad Search (parallel, 8-12 queries)\n\nLaunch WebSearch queries in parallel. Every query must be scoped to recent content. Adapt the date references to the current date:\n\n**Breaking news & announcements:**\n- `\"agentic commerce\" news this week {current_month} {current_year}`\n- `\"agentic commerce\" startup launch OR funding OR announced {current_month} {current_year}`\n\n**VC & Investment (this week):**\n- `agentic commerce startup funding raised {current_month} {current_year}`\n- `YC OR a16z OR Sequoia \"agentic commerce\" OR \"AI shopping\" investment {current_year}`\n\n**Influencer activity (this week):**\n- `agentic commerce tweet site:x.com {current_month} {current_year}`\n- `\"agentic commerce\" OR \"AI shopping agent\" CEO founder opinion {current_month} {current_year}`\n\n**Product launches & updates:**\n- `agentic commerce product launch update new feature {current_month} {current_year}`\n- `AI shopping agent checkout new product {current_month} {current_year}`\n\n**Protocol & platform moves:**\n- `Shopify OR OpenAI OR Google agentic commerce update {current_month} {current_year}`\n- `Visa OR Mastercard OR Stripe agentic commerce news {current_month} {current_year}`\n\n**Vertical signals:**\n- `agentic checkout payment startup news {current_month} {current_year}`\n- `brand AI agent storefront discovery news {current_month} {current_year}`\n\n### Phase 2: Verify recency & fill gaps\n\nFrom Phase 1 results, filter strictly:\n- **Keep** only items with activity in the past 7 days\n- **Drop** anything that's just a rehash of old news\n- For promising leads, do a quick targeted search to confirm details (funding amount, investor names, product specifics)\n\n### Phase 3: Classify into the Agentic Commerce Stack\n\nOrganize qualifying items into layers:\n\n| Layer | Description |\n|-------|-------------|\n| Brand Discovery | Help brands get found by AI agents (GEO, catalog optimization) |\n| Brand Storefront | Brand presence inside LLM environments |\n| Checkout Execution | Complete purchases on behalf of agents |\n| Payment Infrastructure | Financial rails for agent transactions |\n| Consumer Agent | End-user AI shopping assistants |\n| Agent Framework | Platforms for building commerce-capable agents |\n| Enterprise Procurement | B2B purchasing automation via agents |\n| Retail Decision Intelligence | AI-powered merchandising and pricing decisions |\n| Full-Stack Platform | End-to-end agentic commerce solutions |\n\n### Phase 4: Generate the weekly briefing\n\nStructure the output as a news briefing:\n\n**Header:**\n```\n## Agentic Commerce Weekly Briefing ({date_range})\n> {N} noteworthy signals from the past week\n```\n\n**For each item, use this card format:**\n\n```\n### ProductName (Event type: Funding / Product launch / Endorsement / Partnership / Opinion) — one-line summary\n\n**Date:** specific date\n**Endorsement:** who said it / who invested / who partnered\n\n**Key points:**\n- point 1\n- point 2\n- point 3\n\n**Layer:** xxx\n\nSource: https://...\n```\n\nGroup cards by event type (Funding → Product launches → Founder / VC opinions → Partnerships & ecosystem → Industry reports), not by layer.\n\n### Phase 5: Summary table\n\n```\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| 4/12 | Wildcard | Product launch | Launched ChatGPT Shopping optimization tool v2 | Brand Discovery |\n| ... | ... | ... | ... | ... |\n```\n\n### Phase 6: Weekly trend takeaways\n\nClose with 3-5 short observations:\n- This week's biggest signal\n- Money flow direction\n- What big players are doing\n- Emerging themes vs. last week\n- One thing to watch next week\n\n## Quality Gates\n\n- **Recency is the #1 filter.** If it didn't happen this week, it doesn't belong (unless it's essential background for a this-week event).\n- **Credible endorsement required.** Every item must have: VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership.\n- **Source links are mandatory.** No link, no inclusion.\n- **Minimum 5 items.** If it's a quiet week, 5 is OK. If you can't find 5, say so honestly rather than padding with old news.\n- **No pay-to-play.** Exclude items that only appear in sponsored content.\n\n## Language\n\nMatch the user's language. Default to English. If the user writes in another language (e.g. Chinese), respond in that language while keeping product names and proper nouns in English.\n\n## When the user asks for a specific vertical\n\nFocus searches and output on that vertical only. Skip the full taxonomy.\n\n## When the user asks to go deeper on a specific item\n\nSwitch to deep-dive mode: search for full details on the company/event and output a research memo.\n\nFile v1.1.0:README.md\n\n# agentic-commerce-news\n\n> Agentic Commerce Weekly Briefing — scans the past 7 days of X/Twitter, industry media, and VC announcements for startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing.\n\n## What it does\n\nA news aggregation skill focused on **agentic commerce** — the rapidly evolving space where AI agents shop, compare, check out, and pay on behalf of humans. On every invocation, it:\n\n1. Launches 10+ parallel WebSearch queries across different angles, scoped to the past 7 days\n2. Filters results to items with credible VC / institutional / platform endorsement\n3. Classifies each item into the 9-layer Agentic Commerce Stack (Brand Discovery → Payments → Consumer Agent → Full-Stack Platform)\n4. Generates cards grouped by event type (funding / product launch / founder quote / partnership / report)\n5. Appends a summary table and weekly trend takeaways\n\n## When it triggers\n\n- User types `/agentic-commerce-news`\n- User mentions keywords like \"agentic commerce news\", \"AI commerce updates\", \"agent shopping this week\"\n- User asks things like \"what's new in agentic commerce this week?\" or \"who's funding AI shopping startups?\"\n- User asks to set up a scheduled/recurring digest on agentic commerce\n\n## Scheduling\n\nThree ways to run this on a schedule, depending on your environment:\n\n| Environment | Command | Notes |\n|-------------|---------|-------|\n| Claude Code (session) | `CronCreate` tool | In-session only, not persisted across restarts |\n| Claude Code (persistent) | `/schedule` skill | Runs on claude.ai infrastructure, survives restarts |\n| OpenClaw | `openclaw cron add` | 24/7 background execution |\n\n### Example: Daily 8am digest in Claude Code\n\nSay to Claude:\n> \"Set up a daily task to run agentic-commerce-news at 8am.\"\n\nClaude will use `CronCreate` with `\"3 8 * * *\"` (8:03am — nudged a few minutes off the round hour to avoid API pile-ups).\n\n### Example: OpenClaw persistent schedule\n\n```bash\nopenclaw cron add \\\n  --name \"Agentic Commerce Daily\" \\\n  --cron \"3 8 * * *\" \\\n  --tz \"America/New_York\" \\\n  --message \"Run the agentic-commerce-news skill to surface the past week's agentic commerce activity\" \\\n  --channel <your-channel> \\\n  --to \"<your-id>\"\n```\n\n## Quality Gates\n\n- Only items from the past 7 days qualify\n- Every item must have credible endorsement (VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership)\n- Every item must include a source link\n- Minimum 5 items (a quiet week is OK — do not pad with stale news)\n- Exclude pure PR / sponsored content\n\n## Output Format\n\n```\n## Agentic Commerce Weekly Briefing (Apr 8 – Apr 15)\n> 8 noteworthy signals from the past week\n\n### Funding\n### ProductName (raised $XM) — one-line summary\n**Date:** Apr 12\n**Endorsement:** who invested\n**Key points:**\n- point 1\n- point 2\n**Layer:** Payment Infrastructure\nSource: https://...\n\n### Product Launches\n...\n\n### Founder / VC Opinions\n...\n\n## At a Glance\n\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| ... | ... | ... | ... | ... |\n\n## Weekly Takeaways\n1. ...\n2. ...\n```\n\n## Installation\n\n### Option A: Clone from GitHub\n\n```bash\ngit clone https://github.com/xuxinmaxen/agentic-commerce-news.git \\\n  ~/.claude/skills/agentic-commerce-news\n```\n\nRestart your Claude Code session to pick it up.\n\n### Option B: Install from ClawHub\n\n```bash\nclawhub install agentic-commerce-news\n```\n\n### Option C: Manual copy (Claude Code)\n\n```bash\n# Copy into ~/.claude/skills/\ncp -r agentic-commerce-news ~/.claude/skills/\n\n# Verify frontmatter\ncat ~/.claude/skills/agentic-commerce-news/SKILL.md | head -5\n```\n\nRestart your Claude Code session to pick it up.\n\n## Dependencies\n\n- Claude Code ≥ 1.0 (requires the `WebSearch` tool)\n- (Optional) `CronCreate` tool or `openclaw cron` — for scheduled execution\n- **No** API keys or external services required\n\n## Customization\n\nTo adjust the search strategy:\n\n1. Edit the Phase 1 section of `SKILL.md` to add or replace WebSearch query templates\n2. Edit the Phase 3 classification table to introduce new vertical segments\n3. Edit the Phase 4 card format to tweak output style\n\nTo change the time window (e.g., 3 days or 30 days instead of 7):\n\n- Update the `## Time Window` section's \"past 7 days\" phrasing\n- Adjust the `this week` / `today` keywords in the search queries\n\n## License\n\nMIT-0 (MIT No Attribution) — free to use, modify, and redistribute. No attribution required. See [LICENSE](LICENSE).\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn7d2dhgbt152nj3ywh93f507h84xk7w\",\n  \"slug\": \"agentic-commerce-news\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1781528448013\n}\n\nFile v1.1.0:skill-card.md\n\n## Description: <br>\nAgentic Commerce News scans recent agentic commerce activity from X/Twitter, industry media, VC announcements, and conference coverage, then produces a structured news briefing about startups, products, funding rounds, partnerships, and influential opinions. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[xuxinmaxen](https://clawhub.ai/user/xuxinmaxen) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, founders, investors, and commerce teams use this skill to monitor recent agentic commerce market signals and receive concise, source-linked briefings. It can also help set up a recurring digest when the user's runtime supports scheduling. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Recurring digest setup can create persistent or background jobs if the user approves scheduling. <br>\nMitigation: Review every scheduling request before approving it, especially OpenClaw cron or system crontab requests. <br>\nRisk: News briefings can include stale or weakly sourced market claims if search results are not checked carefully. <br>\nMitigation: Require recent source links for included items and avoid padding quiet weeks with older news. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/xuxinmaxen/agentic-commerce-news) <br>\n- [README](README.md) <br>\n- [Evaluations](evals/evals.json) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown briefing with source links, event cards, summary tables, trend takeaways, and optional scheduling commands.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Focuses on the past 7 days of activity and filters for credible endorsements or official announcements.] <br>\n\n## Skill Version(s): <br>\n1.1.0 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.1.0:evals/evals.json\n\n{\n  \"skill_name\": \"agentic-commerce-news\",\n  \"evals\": [\n    {\n      \"id\": 1,\n      \"prompt\": \"Show me the most noteworthy startups in agentic commerce lately, especially the ones endorsed by prominent VCs and founders.\",\n      \"expected_output\": \"Structured briefing with 10+ startups that have VC/institutional endorsement, classified by layer. Each item includes name, positioning, funding, endorsement, key capabilities, and a source link, followed by a summary table and trend takeaways.\",\n      \"files\": []\n    },\n    {\n      \"id\": 2,\n      \"prompt\": \"I'm building an agentic commerce product and need inspiration. What startups are VCs and AI leaders talking about in the checkout and payment infrastructure space?\",\n      \"expected_output\": \"Focused report on checkout execution and payment infrastructure layer startups, with detailed cards for companies like Rye, Firmly, Nekuda, Skyfire, Basis Theory etc., including VC backing and endorsement sources.\",\n      \"files\": []\n    },\n    {\n      \"id\": 3,\n      \"prompt\": \"Which AI shopping startups raised funding recently? Pull together a summary for me.\",\n      \"expected_output\": \"Funding-focused roundup ordered by amount or date. Each item includes funding details, investors, product positioning, and a source link, ending with a trend summary.\",\n      \"files\": []\n    }\n  ]\n}\n\nFile v1.1.0:LICENSE\n\nMIT No Attribution\n\nCopyright 2026 Maxen Xu (@xuxinmaxen)\n\nPermission is hereby granted, free of charge, to any person obtaining a copy of this\nsoftware and associated documentation files (the \"Software\"), to deal in the Software\nwithout restriction, including without limitation the rights to use, copy, modify,\nmerge, publish, distribute, sublicense, and/or sell copies of the Software, and to\npermit persons to whom the Software is furnished to do so.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,\nINCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A\nPARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT\nHOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION\nOF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE\nSOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.\n\nArchive v1.0.1: 4 files, 8086 bytes\n\nFiles: README.md (4864b), skill-card.md (2047b), SKILL.md (8600b), _meta.json (140b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: agentic-commerce-news\ndescription: \"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.\"\n---\n\n# Agentic Commerce News\n\nYou are a news analyst covering the agentic commerce beat. Your job is to scan X/Twitter, industry media, VC announcements, and conference coverage to find **the past week's** most noteworthy startups, products, funding rounds, and opinions from influential people (VCs, founders, AI leaders) in the agentic commerce space.\n\nThink of yourself as a weekly newsletter editor: what happened this week that someone building in agentic commerce absolutely needs to know?\n\n## Why this matters\n\nAgentic commerce — where AI agents shop, compare, and buy on behalf of humans — is a rapidly forming market ($135B in 2025, projected $1.7T by 2030). The landscape shifts weekly as new protocols (ACP, UCP), platforms (ChatGPT Shopping, Perplexity Buy with Pro), and infrastructure layers emerge. The user needs a curated, credible, **timely** signal — not stale noise.\n\n## Time Window\n\n**All searches must focus on the past 7 days.** This is a news product, not a research report.\n\nWhen constructing search queries, always include date-scoping keywords to get fresh results:\n- Use \"this week\", \"today\", \"yesterday\", or the specific date range (e.g., \"April 8-15 2026\")\n- Use the current year and month explicitly\n- If a search returns mostly older results, add the current month name or specific dates to narrow it down\n\nOlder context (e.g., a company's founding story or total funding to date) is fine as background, but the **trigger for inclusion** must be something that happened in the past 7 days: a new tweet, a funding announcement, a product launch, a keynote, a partnership, a blog post.\n\n## Scheduling Support\n\nThis skill supports scheduled execution. When the user asks to set up a recurring job, handle it based on their environment:\n\n**Claude Code — Session-scoped (CronCreate):**\nIf the user says something like \"每天早上8点推送\" or \"set up a daily digest at 8am\", and they're running in Claude Code:\n\nUse the `CronCreate` tool with:\n- `cron`: an appropriate expression that avoids the :00 mark (e.g., `\"3 8 * * *\"` for ~8am daily, nudge a few minutes off the round hour to avoid API pile-ups)\n- `prompt`: `\"运行 agentic-commerce-news skill，搜索过去一周 agentic commerce 领域的最新动态，生成简报\"`\n- `recurring`: `true`\n\nTell the user:\n- Scheduled jobs live in the current Claude session memory (not persisted to disk by default — pass `durable: true` if they want it to survive restarts)\n- Recurring tasks auto-expire after 7 days of this session\n- Jobs only fire while the REPL is idle\n\n**Claude Code — Persistent (remote triggers):**\nIf the user wants a schedule that runs even when their laptop is closed, suggest they use the `/schedule` skill to create a remote trigger (managed by claude.ai). This runs on Anthropic's infrastructure, not locally.\n\n**OpenClaw:**\nIf the environment has `openclaw` CLI available (check with `which openclaw`), use `openclaw cron add` instead. OpenClaw jobs run 24/7 as a persistent agent.\n\n**Other runtimes:**\nIf none of the above is available, fall back to system `crontab` with a script that invokes the CLI (advanced).\n\n## Execution Flow\n\n### Phase 1: Broad Search (parallel, 8-12 queries)\n\nLaunch WebSearch queries in parallel. Every query must be scoped to recent content. Adapt the date references to the current date:\n\n**Breaking news & announcements:**\n- `\"agentic commerce\" news this week {current_month} {current_year}`\n- `\"agentic commerce\" startup launch OR funding OR announced {current_month} {current_year}`\n\n**VC & Investment (this week):**\n- `agentic commerce startup funding raised {current_month} {current_year}`\n- `YC OR a16z OR Sequoia \"agentic commerce\" OR \"AI shopping\" investment {current_year}`\n\n**Influencer activity (this week):**\n- `agentic commerce tweet site:x.com {current_month} {current_year}`\n- `\"agentic commerce\" OR \"AI shopping agent\" CEO founder opinion {current_month} {current_year}`\n\n**Product launches & updates:**\n- `agentic commerce product launch update new feature {current_month} {current_year}`\n- `AI shopping agent checkout new product {current_month} {current_year}`\n\n**Protocol & platform moves:**\n- `Shopify OR OpenAI OR Google agentic commerce update {current_month} {current_year}`\n- `Visa OR Mastercard OR Stripe agentic commerce news {current_month} {current_year}`\n\n**Vertical signals:**\n- `agentic checkout payment startup news {current_month} {current_year}`\n- `brand AI agent storefront discovery news {current_month} {current_year}`\n\n### Phase 2: Verify recency & fill gaps\n\nFrom Phase 1 results, filter strictly:\n- **Keep** only items with activity in the past 7 days\n- **Drop** anything that's just a rehash of old news\n- For promising leads, do a quick targeted search to confirm details (funding amount, investor names, product specifics)\n\n### Phase 3: Classify into the Agentic Commerce Stack\n\nOrganize qualifying items into layers:\n\n| Layer | Description |\n|-------|-------------|\n| Brand Discovery | Help brands get found by AI agents (GEO, catalog optimization) |\n| Brand Storefront | Brand presence inside LLM environments |\n| Checkout Execution | Complete purchases on behalf of agents |\n| Payment Infrastructure | Financial rails for agent transactions |\n| Consumer Agent | End-user AI shopping assistants |\n| Agent Framework | Platforms for building commerce-capable agents |\n| Enterprise Procurement | B2B purchasing automation via agents |\n| Retail Decision Intelligence | AI-powered merchandising and pricing decisions |\n| Full-Stack Platform | End-to-end agentic commerce solutions |\n\n### Phase 4: Generate the weekly briefing\n\nStructure the output as a news briefing:\n\n**Header:**\n```\n## Agentic Commerce 周报（{date_range}）\n> 本周 {N} 条值得关注的动态\n```\n\n**For each item, use this card format:**\n\n```\n### ProductName（事件类型：融资/产品发布/大V推荐/合作/观点）— 一句话摘要\n\n**时间：** 具体日期\n**背书：** 谁说的/谁投的/谁合作的\n\n**核心内容：**\n- 要点 1\n- 要点 2\n- 要点 3\n\n**所属层级：** xxx\n\n原文链接：https://...\n```\n\nGroup cards by event type (融资动态 → 产品发布 → 大V观点 → 合作与生态 → 行业报告), not by layer.\n\n### Phase 5: Summary table\n\n```\n| 日期 | 公司/人物 | 事件类型 | 一句话摘要 | 层级 |\n|------|----------|----------|-----------|------|\n| 4/12 | Wildcard | 产品发布 | 推出 ChatGPT Shopping 优化工具 v2 | 品牌发现 |\n| ... | ... | ... | ... | ... |\n```\n\n### Phase 6: Weekly trend takeaways\n\nClose with 3-5 short observations:\n- This week's biggest signal\n- Money flow direction\n- What big players are doing\n- Emerging themes vs. last week\n- One thing to watch next week\n\n## Quality Gates\n\n- **Recency is the #1 filter.** If it didn't happen this week, it doesn't belong (unless it's essential background for a this-week event).\n- **Credible endorsement required.** Every item must have: VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership.\n- **Source links are mandatory.** No link, no inclusion.\n- **Minimum 5 items.** If it's a quiet week, 5 is OK. If you can't find 5, say so honestly rather than padding with old news.\n- **No pay-to-play.** Exclude items that only appear in sponsored content.\n\n## Language\n\nMatch the user's language. If the user writes in Chinese, output in Chinese (product names and proper nouns stay in English). If English, output in English. Default to Chinese with English proper nouns.\n\n## When the user asks for a specific vertical\n\nFocus searches and output on that vertical only. Skip the full taxonomy.\n\n## When the user asks to go deeper on a specific item\n\nSwitch to deep-dive mode: search for full details on the company/event and output a research memo.\n\nFile v1.0.1:README.md\n\n# agentic-commerce-news\n\n> Agentic Commerce Weekly Briefing — scans the past 7 days of X/Twitter, industry media, and VC announcements for startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing.\n\n## What it does\n\nA news aggregation skill focused on **agentic commerce** — the rapidly evolving space where AI agents shop, compare, check out, and pay on behalf of humans. On every invocation, it:\n\n1. Launches 10+ parallel WebSearch queries across different angles, scoped to the past 7 days\n2. Filters results to items with credible VC / institutional / platform endorsement\n3. Classifies each item into the 9-layer Agentic Commerce Stack (Brand Discovery → Payments → Consumer Agent → Full-Stack Platform)\n4. Generates cards grouped by event type (funding / product launch / founder quote / partnership / report)\n5. Appends a summary table and weekly trend takeaways\n\n## When it triggers\n\n- User types `/agentic-commerce-news`\n- User mentions keywords like \"agentic commerce news\", \"AI commerce updates\", \"agent shopping this week\"\n- User asks things like \"what's new in agentic commerce this week?\" or \"who's funding AI shopping startups?\"\n- User asks to set up a scheduled/recurring digest on agentic commerce\n\n## Scheduling\n\nThree ways to run this on a schedule, depending on your environment:\n\n| Environment | Command | Notes |\n|-------------|---------|-------|\n| Claude Code (session) | `CronCreate` tool | In-session only, not persisted across restarts |\n| Claude Code (persistent) | `/schedule` skill | Runs on claude.ai infrastructure, survives restarts |\n| OpenClaw | `openclaw cron add` | 24/7 background execution |\n\n### Example: Daily 8am digest in Claude Code\n\nSay to Claude:\n> \"Set up a daily task to run agentic-commerce-news at 8am.\"\n\nClaude will use `CronCreate` with `\"3 8 * * *\"` (8:03am — nudged a few minutes off the round hour to avoid API pile-ups).\n\n### Example: OpenClaw persistent schedule\n\n```bash\nopenclaw cron add \\\n  --name \"Agentic Commerce Daily\" \\\n  --cron \"3 8 * * *\" \\\n  --tz \"America/New_York\" \\\n  --message \"Run the agentic-commerce-news skill to surface the past week's agentic commerce activity\" \\\n  --channel <your-channel> \\\n  --to \"<your-id>\"\n```\n\n## Quality Gates\n\n- Only items from the past 7 days qualify\n- Every item must have credible endorsement (VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership)\n- Every item must include a source link\n- Minimum 5 items (a quiet week is OK — do not pad with stale news)\n- Exclude pure PR / sponsored content\n\n## Output Format\n\n```\n## Agentic Commerce Weekly Briefing (Apr 8 – Apr 15)\n> 8 noteworthy signals from the past week\n\n### Funding\n### ProductName (raised $XM) — one-line summary\n**Date:** Apr 12\n**Endorsement:** who invested\n**Key points:**\n- point 1\n- point 2\n**Layer:** Payment Infrastructure\nSource: https://...\n\n### Product Launches\n...\n\n### Founder / VC Opinions\n...\n\n## At a Glance\n\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| ... | ... | ... | ... | ... |\n\n## Weekly Takeaways\n1. ...\n2. ...\n```\n\n## Installation\n\n### Option A: Manual local install (Claude Code)\n\n```bash\n# Copy into ~/.claude/skills/\ncp -r agentic-commerce-news ~/.claude/skills/\n\n# Verify frontmatter\ncat ~/.claude/skills/agentic-commerce-news/SKILL.md | head -5\n```\n\nRestart your Claude Code session to pick it up.\n\n### Option B: Install from .skill package\n\n```bash\n# Unzip the .skill bundle into the skills directory\nunzip agentic-commerce-news.skill -d ~/.claude/skills/\n```\n\n### Option C: Publish to ClawHub (OpenClaw ecosystem)\n\n```bash\n# Ensure openclaw CLI is installed and logged in\nopenclaw auth login\n\n# Publish\nopenclaw publish ./agentic-commerce-news\n```\n\nBefore publishing, make sure:\n- The `name` field in `SKILL.md` matches the directory name\n- The `description` field clearly states when the skill should trigger\n- README.md includes usage examples\n\n## Dependencies\n\n- Claude Code ≥ 1.0 (requires the `WebSearch` tool)\n- (Optional) `CronCreate` tool or `openclaw cron` — for scheduled execution\n- **No** API keys or external services required\n\n## Customization\n\nTo adjust the search strategy:\n\n1. Edit the Phase 1 section of `SKILL.md` to add or replace WebSearch query templates\n2. Edit the Phase 3 classification table to introduce new vertical segments\n3. Edit the Phase 4 card format to tweak output style\n\nTo change the time window (e.g., 3 days or 30 days instead of 7):\n\n- Update the `## Time Window` section's \"past 7 days\" phrasing\n- Adjust the `this week` / `today` keywords in the search queries\n\n## License\n\nMIT — free to use, modify, and distribute.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7d2dhgbt152nj3ywh93f507h84xk7w\",\n  \"slug\": \"agentic-commerce-news\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1776393003489\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nAgentic Commerce Weekly Briefing scans X/Twitter, industry media, and VC announcements from the past 7 days to surface agentic commerce startups, products, funding rounds, and influential opinions, then produces a structured news briefing. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[xuxinmaxen](https://clawhub.ai/user/xuxinmaxen) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, founders, investors, and commerce teams use this skill to monitor the past week's agentic commerce activity, including launches, funding, partnerships, and influential market commentary. It can also help set up scheduled digest workflows when the user's runtime supports them. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Scheduled digest jobs may persist or run in a different scope than the user expects. <br>\nMitigation: Before enabling scheduled mode, confirm whether the job is session-only, remote, OpenClaw-managed, or system crontab, and verify how to disable it. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/xuxinmaxen/agentic-commerce-news) <br>\n- [Publisher profile](https://clawhub.ai/user/xuxinmaxen) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown news briefing with source links, summary tables, trend takeaways, and optional scheduling commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Matches the user's language and defaults to Chinese with English proper nouns when no language preference is given.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 3 files, 6988 bytes\n\nFiles: README.md (4309b), SKILL.md (8444b), _meta.json (140b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: agentic-commerce-news\ndescription: \"Agentic Commerce 每周产品快报 — 搜索过去一周内大V（VC、企业家、AI领袖）推荐的 Agentic Commerce 相关创业产品和动态，生成结构化新闻简报。支持定时任务（如每天早上8点自动执行）。当用户提到 agentic commerce 新闻、AI commerce 最新动态、agent shopping 本周新产品、agentic 电商创业新闻、或输入 /agentic-commerce-news 时使用。当用户说'帮我看看 agentic commerce 这周有什么新动态'或'设置一个定时任务每天早上推送 agentic commerce 新闻'，也应该触发此 skill。\"\n---\n\n# Agentic Commerce News\n\nYou are a news analyst covering the agentic commerce beat. Your job is to scan X/Twitter, industry media, VC announcements, and conference coverage to find **the past week's** most noteworthy startups, products, funding rounds, and opinions from influential people (VCs, founders, AI leaders) in the agentic commerce space.\n\nThink of yourself as a weekly newsletter editor: what happened this week that someone building in agentic commerce absolutely needs to know?\n\n## Why this matters\n\nAgentic commerce — where AI agents shop, compare, and buy on behalf of humans — is a rapidly forming market ($135B in 2025, projected $1.7T by 2030). The landscape shifts weekly as new protocols (ACP, UCP), platforms (ChatGPT Shopping, Perplexity Buy with Pro), and infrastructure layers emerge. The user needs a curated, credible, **timely** signal — not stale noise.\n\n## Time Window\n\n**All searches must focus on the past 7 days.** This is a news product, not a research report.\n\nWhen constructing search queries, always include date-scoping keywords to get fresh results:\n- Use \"this week\", \"today\", \"yesterday\", or the specific date range (e.g., \"April 8-15 2026\")\n- Use the current year and month explicitly\n- If a search returns mostly older results, add the current month name or specific dates to narrow it down\n\nOlder context (e.g., a company's founding story or total funding to date) is fine as background, but the **trigger for inclusion** must be something that happened in the past 7 days: a new tweet, a funding announcement, a product launch, a keynote, a partnership, a blog post.\n\n## Scheduling Support\n\nThis skill supports scheduled execution. When the user asks to set up a recurring job, handle it based on their environment:\n\n**Claude Code — Session-scoped (CronCreate):**\nIf the user says something like \"每天早上8点推送\" or \"set up a daily digest at 8am\", and they're running in Claude Code:\n\nUse the `CronCreate` tool with:\n- `cron`: an appropriate expression that avoids the :00 mark (e.g., `\"3 8 * * *\"` for ~8am daily, nudge a few minutes off the round hour to avoid API pile-ups)\n- `prompt`: `\"运行 agentic-commerce-news skill，搜索过去一周 agentic commerce 领域的最新动态，生成简报\"`\n- `recurring`: `true`\n\nTell the user:\n- Scheduled jobs live in the current Claude session memory (not persisted to disk by default — pass `durable: true` if they want it to survive restarts)\n- Recurring tasks auto-expire after 7 days of this session\n- Jobs only fire while the REPL is idle\n\n**Claude Code — Persistent (remote triggers):**\nIf the user wants a schedule that runs even when their laptop is closed, suggest they use the `/schedule` skill to create a remote trigger (managed by claude.ai). This runs on Anthropic's infrastructure, not locally.\n\n**OpenClaw:**\nIf the environment has `openclaw` CLI available (check with `which openclaw`), use `openclaw cron add` instead. OpenClaw jobs run 24/7 as a persistent agent.\n\n**Other runtimes:**\nIf none of the above is available, fall back to system `crontab` with a script that invokes the CLI (advanced).\n\n## Execution Flow\n\n### Phase 1: Broad Search (parallel, 8-12 queries)\n\nLaunch WebSearch queries in parallel. Every query must be scoped to recent content. Adapt the date references to the current date:\n\n**Breaking news & announcements:**\n- `\"agentic commerce\" news this week {current_month} {current_year}`\n- `\"agentic commerce\" startup launch OR funding OR announced {current_month} {current_year}`\n\n**VC & Investment (this week):**\n- `agentic commerce startup funding raised {current_month} {current_year}`\n- `YC OR a16z OR Sequoia \"agentic commerce\" OR \"AI shopping\" investment {current_year}`\n\n**Influencer activity (this week):**\n- `agentic commerce tweet site:x.com {current_month} {current_year}`\n- `\"agentic commerce\" OR \"AI shopping agent\" CEO founder opinion {current_month} {current_year}`\n\n**Product launches & updates:**\n- `agentic commerce product launch update new feature {current_month} {current_year}`\n- `AI shopping agent checkout new product {current_month} {current_year}`\n\n**Protocol & platform moves:**\n- `Shopify OR OpenAI OR Google agentic commerce update {current_month} {current_year}`\n- `Visa OR Mastercard OR Stripe agentic commerce news {current_month} {current_year}`\n\n**Vertical signals:**\n- `agentic checkout payment startup news {current_month} {current_year}`\n- `brand AI agent storefront discovery news {current_month} {current_year}`\n\n### Phase 2: Verify recency & fill gaps\n\nFrom Phase 1 results, filter strictly:\n- **Keep** only items with activity in the past 7 days\n- **Drop** anything that's just a rehash of old news\n- For promising leads, do a quick targeted search to confirm details (funding amount, investor names, product specifics)\n\n### Phase 3: Classify into the Agentic Commerce Stack\n\nOrganize qualifying items into layers:\n\n| Layer | Description |\n|-------|-------------|\n| Brand Discovery | Help brands get found by AI agents (GEO, catalog optimization) |\n| Brand Storefront | Brand presence inside LLM environments |\n| Checkout Execution | Complete purchases on behalf of agents |\n| Payment Infrastructure | Financial rails for agent transactions |\n| Consumer Agent | End-user AI shopping assistants |\n| Agent Framework | Platforms for building commerce-capable agents |\n| Enterprise Procurement | B2B purchasing automation via agents |\n| Retail Decision Intelligence | AI-powered merchandising and pricing decisions |\n| Full-Stack Platform | End-to-end agentic commerce solutions |\n\n### Phase 4: Generate the weekly briefing\n\nStructure the output as a news briefing:\n\n**Header:**\n```\n## Agentic Commerce 周报（{date_range}）\n> 本周 {N} 条值得关注的动态\n```\n\n**For each item, use this card format:**\n\n```\n### ProductName（事件类型：融资/产品发布/大V推荐/合作/观点）— 一句话摘要\n\n**时间：** 具体日期\n**背书：** 谁说的/谁投的/谁合作的\n\n**核心内容：**\n- 要点 1\n- 要点 2\n- 要点 3\n\n**所属层级：** xxx\n\n原文链接：https://...\n```\n\nGroup cards by event type (融资动态 → 产品发布 → 大V观点 → 合作与生态 → 行业报告), not by layer.\n\n### Phase 5: Summary table\n\n```\n| 日期 | 公司/人物 | 事件类型 | 一句话摘要 | 层级 |\n|------|----------|----------|-----------|------|\n| 4/12 | Wildcard | 产品发布 | 推出 ChatGPT Shopping 优化工具 v2 | 品牌发现 |\n| ... | ... | ... | ... | ... |\n```\n\n### Phase 6: Weekly trend takeaways\n\nClose with 3-5 short observations:\n- This week's biggest signal\n- Money flow direction\n- What big players are doing\n- Emerging themes vs. last week\n- One thing to watch next week\n\n## Quality Gates\n\n- **Recency is the #1 filter.** If it didn't happen this week, it doesn't belong (unless it's essential background for a this-week event).\n- **Credible endorsement required.** Every item must have: VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership.\n- **Source links are mandatory.** No link, no inclusion.\n- **Minimum 5 items.** If it's a quiet week, 5 is OK. If you can't find 5, say so honestly rather than padding with old news.\n- **No pay-to-play.** Exclude items that only appear in sponsored content.\n\n## Language\n\nMatch the user's language. If the user writes in Chinese, output in Chinese (product names and proper nouns stay in English). If English, output in English. Default to Chinese with English proper nouns.\n\n## When the user asks for a specific vertical\n\nFocus searches and output on that vertical only. Skip the full taxonomy.\n\n## When the user asks to go deeper on a specific item\n\nSwitch to deep-dive mode: search for full details on the company/event and output a research memo.\n\nFile v1.0.0:README.md\n\n# agentic-commerce-news\n\n> Agentic Commerce 每周产品快报 — 搜索过去一周大V（VC、企业家、AI领袖）推荐的 Agentic Commerce 相关创业产品和动态，生成结构化新闻简报。\n\n## What it does\n\n这是一个新闻聚合类 skill，专注于 **Agentic Commerce**（AI Agent 代人购物）这个快速演化的赛道。每次触发时，它会：\n\n1. 并行发起 10+ 条不同角度的 WebSearch 查询（过去 7 天窗口）\n2. 过滤出有大V / 机构背书的创业产品和动态\n3. 按 9 层 Agentic Commerce Stack 分类（品牌发现→支付→消费端 Agent→全栈平台）\n4. 生成按事件类型分组的卡片（融资 / 产品发布 / 大V观点 / 合作 / 报告）\n5. 附速览汇总表 + 本周趋势洞察\n\n## When it triggers\n\n- 用户输入 `/agentic-commerce-news`\n- 用户提到 \"agentic commerce 新闻\"、\"AI commerce 最新动态\"、\"agent shopping 本周新产品\" 等关键词\n- 用户说类似 \"帮我看看 agentic commerce 这周有什么新动态\" 的话\n- 用户要求设置定时任务推送 agentic commerce 动态\n\n## Scheduling（定时任务）\n\n支持三种运行方式，根据你的环境选择：\n\n| 环境 | 命令 | 说明 |\n|------|------|------|\n| Claude Code 当前会话 | `CronCreate` 工具 | 会话内定时，不持久化 |\n| Claude Code 持久化 | `/schedule` skill | 在 claude.ai 云端运行，长期生效 |\n| OpenClaw | `openclaw cron add` | 7×24 后台运行 |\n\n### 示例：每天早上 8 点定时推送（Claude Code）\n\n对 Claude 说：\n> 设置一个定时任务，每天早上 8 点运行 agentic-commerce-news 推送给我\n\nClaude 会用 `CronCreate` 创建 `\"3 8 * * *\"` 规则（8:03am，避开整点）。\n\n### 示例：OpenClaw 持久化定时\n\n```bash\nopenclaw cron add \\\n  --name \"Agentic Commerce Daily\" \\\n  --cron \"3 8 * * *\" \\\n  --tz \"Asia/Shanghai\" \\\n  --message \"运行 agentic-commerce-news skill，搜索过去一周 agentic commerce 领域的最新动态\" \\\n  --channel <your-channel> \\\n  --to \"<your-id>\"\n```\n\n## Quality Gates\n\n- 只收录过去 7 天的动态\n- 必须有大V / 机构背书（VC 投资、推文推荐、官方报告、平台合作）\n- 必须附原文链接\n- 最少 5 条（淡周可少，严禁用旧新闻充数）\n- 排除纯广告 / PR 内容\n\n## Output Format\n\n```\n## Agentic Commerce 周报（4月8日 - 4月15日）\n> 本周 8 条值得关注的动态\n\n### 融资动态\n### ProductName（融资 $XM）— 一句话摘要\n**时间：** 4月12日\n**背书：** 谁投的\n**核心内容：**\n- 要点 1\n- 要点 2\n**所属层级：** Payment Infrastructure\n原文链接：https://...\n\n### 产品发布\n...\n\n### 大V观点\n...\n\n## 本周速览\n\n| 日期 | 公司/人物 | 事件类型 | 一句话摘要 | 层级 |\n|------|----------|----------|-----------|------|\n| ... | ... | ... | ... | ... |\n\n## 本周趋势\n1. ...\n2. ...\n```\n\n## Installation\n\n### Option A: 本地手动安装（Claude Code）\n\n```bash\n# 克隆到 ~/.claude/skills/\ncp -r agentic-commerce-news ~/.claude/skills/\n\n# 验证 frontmatter\ncat ~/.claude/skills/agentic-commerce-news/SKILL.md | head -5\n```\n\n重启 Claude Code 会话后即可使用。\n\n### Option B: 从 .skill 包安装\n\n```bash\n# 解压 .skill 文件到 skills 目录\nunzip agentic-commerce-news.skill -d ~/.claude/skills/\n```\n\n### Option C: 发布到 ClawHub（OpenClaw 生态）\n\n```bash\n# 确保 openclaw CLI 已安装并登录\nopenclaw auth login\n\n# 发布\nopenclaw publish ./agentic-commerce-news\n```\n\n发布前请确保：\n- `SKILL.md` 的 `name` 字段和目录名一致\n- `description` 字段清晰描述触发场景\n- README.md 包含使用示例\n\n## Dependencies\n\n- Claude Code ≥ 1.0（需要 `WebSearch` 工具）\n- （可选）`CronCreate` 工具或 `openclaw cron` — 定时任务场景\n- **无需** API key 或外部依赖\n\n## Customization\n\n如果你想调整搜索策略：\n\n1. 修改 `SKILL.md` 的 Phase 1 部分，增加/替换 WebSearch 查询模板\n2. 修改 Phase 3 的分类表，增加行业细分\n3. 修改 Phase 4 的卡片格式，调整输出风格\n\n如果你想调整时间窗口（比如改成 3 天或 30 天）：\n\n- 修改 `## Time Window` 章节的 \"past 7 days\" 描述\n- 调整搜索查询中的 `this week` / `today` 等时间关键词\n\n## License\n\nMIT — 可自由使用、修改、分发。\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7d2dhgbt152nj3ywh93f507h84xk7w\",\n  \"slug\": \"agentic-commerce-news\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776237647366\n}","readmeExcerpt":"Skill: Agentic Commerce News Owner: xuxinmaxen Summary: Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,... Tags: agentic-commerce:1.1.0, ai-commerce:1.1.0, latest:1.2.0, news:1.1.0, research:1.1.0, scheduling:1.1.0 Version history: v1.2.0 | 2026-07-03T03:39:53.352Z | user Cross-week dedup: reads the most recen","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"## Agentic Commerce Weekly Briefing ({date_range})\n> {N} noteworthy signals from the past week"},{"language":"text","snippet":"### ProductName (Event type: Funding / Product launch / Endorsement / Partnership / Opinion) — one-line summary\n\n**Date:** specific date\n**Endorsement:** who said it / who invested / who partnered\n\n**Key points:**\n- point 1\n- point 2\n- point 3\n\n**Layer:** xxx\n\nSource: https://..."},{"language":"text","snippet":"| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| 4/12 | Wildcard | Product launch | Launched ChatGPT Shopping optimization tool v2 | Brand Discovery |\n| ... | ... | ... | ... | ... |"},{"language":"bash","snippet":"openclaw cron add \\\n  --name \"Agentic Commerce Daily\" \\\n  --cron \"3 8 * * *\" \\\n  --tz \"America/New_York\" \\\n  --message \"Run the agentic-commerce-news skill to surface the past week's agentic commerce activity\" \\\n  --channel <your-channel> \\\n  --to \"<your-id>\""},{"language":"text","snippet":"## Agentic Commerce Weekly Briefing (Apr 8 – Apr 15)\n> 8 noteworthy signals from the past week\n\n### Funding\n### ProductName (raised $XM) — one-line summary\n**Date:** Apr 12\n**Endorsement:** who invested\n**Key points:**\n- point 1\n- point 2\n**Layer:** Payment Infrastructure\nSource: https://...\n\n### Product Launches\n...\n\n### Founder / VC Opinions\n...\n\n## At a Glance\n\n| Date | Company / Person | Event Type | One-line Summary | Layer |\n|------|------------------|-----------|-------------------|-------|\n| ... | ... | ... | ... | ... |\n\n## Weekly Takeaways\n1. ...\n2. ..."},{"language":"bash","snippet":"git clone https://github.com/xuxinmaxen/agentic-commerce-news.git \\\n  ~/.claude/skills/agentic-commerce-news"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: agentic-commerce-news\ndescription: \"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.\"\nallowed-tools: WebSearch, WebFetch\n---\n\n# Agentic Commerce News\n\nYou are a news analyst covering the agentic commerce beat. Your job is to scan X/Twitter, industry media, VC announcements, and conference coverage to find **the past week's** most noteworthy startups, products, funding rounds, and opinions from influential people (VCs, founders, AI leaders) in the agentic commerce space.\n\nThink of yourself as a weekly newsletter editor: what happened this week that someone building in agentic commerce absolutely needs to know?\n\n## Why this matters\n\nAgentic commerce — where AI agents shop, compare, and buy on behalf of humans — is a rapidly forming market ($135B in 2025, projected $1.7T by 2030). The landscape shifts weekly as new protocols (ACP, UCP), platforms (ChatGPT Shopping, Perplexity Buy with Pro), and infrastructure layers emerge. The user needs a curated, credible, **timely** signal — not stale noise.\n\n## Time Window\n\n**All searches must focus on the past 7 days.** This is a news product, not a research report.\n\nWhen constructing search queries, always include date-scoping keywords to get fresh results:\n- Use \"this week\", \"today\", \"yesterday\", or the specific date range (e.g., \"April 8-15 2026\")\n- Use the current year and month explicitly\n- If a search returns mostly older results, add the current month name or specific dates to narrow it down\n\nOlder context (e.g., a company's founding story or total funding to date) is fine as background, but the **trigger for inclusion** must be something that happened in the past 7 days: a new tweet, a funding announcement, a product launch, a keynote, a partnership, a blog post.\n\n## Scheduling Support\n\nThis skill supports scheduled execution. When the user asks to set up a recurring job, handle it based on their environment:\n\n**Claude Code — Session-scoped (CronCreate):**\nIf the user says something like \"set up a daily digest at 8am\" or \"push it to me every morning\", and they're running in Claude Code:\n\nUse the `CronCreate` tool with:\n- `cron`: an appropriate expression that avoids the :00 mark (e.g., `\"3 8 * * *\"` for ~8am daily, nudge a few minutes off the round hour to avoid API pile-ups)\n- `prompt`: `\"Run the agentic-commerce-n"},{"path":"briefings/README.md","content":"# Briefing Archive\n\nPublished output of this skill — one file per week, newest first.\n\nEach briefing is generated by running `/agentic-commerce-news` in Claude Code, then committed here verbatim (sources and all). If you want to judge whether the skill is worth installing, read one of these first: the archive **is** the demo.\n\n| Week | File |\n|------|------|\n| Jun 26 – Jul 3, 2026 | [2026-06-29.md](./2026-06-29.md) |\n\n## Format\n\nEvery file follows the structure defined in [`SKILL.md`](../SKILL.md):\n\n- Cards grouped by event type — **Funding / Product Launches / Founder & VC Opinions / Partnerships / Reports**\n- Every item: date, endorsement (who backed or amplified it), key points, [9-layer stack](../SKILL.md) classification, and a source link\n- An **At a Glance** table plus 2–3 **Weekly Takeaways**\n\n## Contributing a week\n\nRun the skill yourself and open a PR adding `YYYY-MM-DD.md` (the Monday of that week). Briefings must pass the skill's quality gates — 7-day window, credible endorsement, source link per item, no PR fluff."},{"path":"README.md","content":"# agentic-commerce-news\n\n> Agentic Commerce Weekly Briefing — scans the past 7 days of X/Twitter, industry media, and VC announcements for startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing.\n\n### 📰 [Read the latest briefing](./briefings/2026-06-29.md) · [archive](./briefings/)\n\nEvery week's output is published in [`briefings/`](./briefings/) — read one before installing; the archive **is** the demo.\n\n## What it does\n\nA news aggregation skill focused on **agentic commerce** — the rapidly evolving space where AI agents shop, compare, check out, and pay on behalf of humans. On every invocation, it:\n\n1. Launches 10+ parallel WebSearch queries across different angles, scoped to the past 7 days\n2. Filters results to items with credible VC / institutional / platform endorsement\n3. Classifies each item into the 9-layer Agentic Commerce Stack (Brand Discovery → Payments → Consumer Agent → Full-Stack Platform)\n4. Generates cards grouped by event type (funding / product launch / founder quote / partnership / report)\n5. Appends a summary table and weekly trend takeaways\n\n## When it triggers\n\n- User types `/agentic-commerce-news`\n- User mentions keywords like \"agentic commerce news\", \"AI commerce updates\", \"agent shopping this week\"\n- User asks things like \"what's new in agentic commerce this week?\" or \"who's funding AI shopping startups?\"\n- User asks to set up a scheduled/recurring digest on agentic commerce\n\n## Scheduling\n\nThree ways to run this on a schedule, depending on your environment:\n\n| Environment | Command | Notes |\n|-------------|---------|-------|\n| Claude Code (session) | `CronCreate` tool | In-session only, not persisted across restarts |\n| Claude Code (persistent) | `/schedule` skill | Runs on claude.ai infrastructure, survives restarts |\n| OpenClaw | `openclaw cron add` | 24/7 background execution |\n\n### Example: Daily 8am digest in Claude Code\n\nSay to Claude:\n> \"Set up a daily task to run agentic-commerce-news at 8am.\"\n\nClaude will use `CronCreate` with `\"3 8 * * *\"` (8:03am — nudged a few minutes off the round hour to avoid API pile-ups).\n\n### Example: OpenClaw persistent schedule\n\n```bash\nopenclaw cron add \\\n  --name \"Agentic Commerce Daily\" \\\n  --cron \"3 8 * * *\" \\\n  --tz \"America/New_York\" \\\n  --message \"Run the agentic-commerce-news skill to surface the past week's agentic commerce activity\" \\\n  --channel <your-channel> \\\n  --to \"<your-id>\"\n```\n\n## Quality Gates\n\n- Only items from the past 7 days qualify\n- Every item must have credible endorsement (VC investment, public recommendation by a recognized figure, inclusion in a major report, or official platform partnership)\n- Every item must include a source link\n- Minimum 5 items (a quiet week is OK — do not pad with stale news)\n- Exclude pure PR / sponsored content\n- Publish dates of top items are confirmed on the source page, not inferred from search snippets\n"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7d2dhgbt152nj3ywh93f507h84xk7w\",\n  \"slug\": \"agentic-commerce-news\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1783049993352\n}"},{"path":"briefings/2026-06-29.md","content":"# Agentic Commerce Weekly Briefing (Jun 26 – Jul 3, 2026)\n\n> Generated by the [agentic-commerce-news](https://github.com/xuxinmaxen/agentic-commerce-news) Claude Code skill on 2026-07-03.\n\n> 7 noteworthy signals from the past week\n\n## Funding\n\nNo qualifying funding rounds this week. The closest miss was Seltz's $12.5M seed (agent-native web search infrastructure, led by Speedinvest and B Capital), announced June 24 — two days before this briefing's window opened ([Fortune](https://fortune.com/2026/06/24/exclusive-seltz-a-startup-rebuilding-web-search-for-ai-agents-raises-12-5-million-in-seed-funding/)). Rather than pad with stale deals, we're calling it honestly: agentic commerce venture money took a breather this week, even as strategic capital moved massively (see Open USD below).\n\n## Product Launches\n\n### Salesforce Agentforce Commerce (Event type: Product launch) — Salesforce ships its \"biggest Agentforce Commerce release yet,\" wiring merchant catalogs directly into ChatGPT and Google AI surfaces\n\n**Date:** Late June 2026 (week of Jun 29; ChatGPT channel GA lands July 2026)\n**Endorsement:** Official platform partnerships with OpenAI (ChatGPT catalog integration GA July 2026) and Google (AI Mode + Gemini app GA summer 2026); announced by Nitin Mangtani, EVP & GM of Agentforce Commerce\n\n**Key points:**\n- Agentic Commerce Channels sync merchant product catalogs from Business Manager directly into ChatGPT (GA July 2026) and Google Search AI Mode / Gemini app (GA summer 2026) — no extra software or third-party connectors; the merchant stays merchant of record and orders land on their existing platform\n- Ships a workforce of ready-to-deploy agents: Shopper Agent (discovery-to-checkout-to-service on brand properties), Buyer Agent (B2B via WhatsApp/SMS), and Merchant Agent (catalog and merchandising in plain language), plus GA of Storefront Next and an Agentic B2C Developer Toolkit (CLI, MCP server, IDE extension)\n- Salesforce's supporting data: AI influenced 20% of global online sales ($262B) this past holiday season, and retailers running their own shopper agents grew sales 59% faster than those without. Mangtani's thesis: \"The brands that win will have their Shopper Agent live on their own properties for the 2026 shopping season\"\n\n**Layer:** Full-Stack Platform\n\nSource: https://www.salesforce.com/news/stories/agentforce-commerce-announcement/ (see also [CX Today](https://www.cxtoday.com/crm/salesforce-agentforce-commerce-generally-available/))\n\n## Founder / VC Opinions\n\n### Signifyd — Nicole Jass (Event type: Opinion) — \"Agentic commerce is moving both faster and slower than the buzz\": LLM referrals up 600%+ YoY, but agent-executed purchases still under 1% of orders\n\n**Date:** June 30, 2026\n**Endorsement:** Nicole Jass, SVP of Enterprise Strategy at Signifyd, backed by Signifyd's live merchant network data\n\n**Key points:**\n- Online orders from LLM referrals are up more than 600% year over year across Signifyd's network — the discovery shift is rea"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,... Skill: Agentic Commerce News Owner: xuxinmaxen Summary: Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds,... Tags: agentic-commerce:1.1.0, ai-commerce:1.1.0, latest:1.2.0, news:1.1.0, research:1.1.0, scheduling:1.1.0 Version history: v1.2.0 | 2026-07-03T03:39:53.352Z | user Cross-week dedup: reads the most recen","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1920,"uniquenessScore":46,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T11:25:19.765Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T11:25:19.765Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T14:16:05.230Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}