#New standing order

1 messages · Page 1 of 1 (latest)

raven frigate May 14, 2026, 7:25 PM

I currently have a standing order which works well as shown here https://cl1p.net/4562
Can you create me another one for this prompt https://cl1p.net/4561

faint berryBOT May 14, 2026, 7:25 PM

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> ✅ Mark Solution

acoustic hazelBOT May 14, 2026, 7:26 PM

I can — the 4562 cl1p looks empty/destroyed on view from here, so I can’t mirror the exact existing format. But I pulled the 4561 prompt and turned it into a standing-order style block you can paste into AGENTS.md or a referenced standing-orders.md.

Docs for the pattern: https://docs.openclaw.ai/automation/standing-orders

## Program: UK SQL DBA Lead Scout

**Authority:** Find, qualify, and report new UK companies currently hiring for SQL DBA / Database Administrator roles.
**Trigger:** Run when explicitly asked, or on the configured cron schedule.
**Primary record:** `sql_leads.md` in the agent workspace.
**Approval gate:** Do not contact leads automatically. Do not send messages, emails, LinkedIn requests, or outreach without explicit human approval.
**Escalation:** Stop and ask if search tools are unavailable, `sql_leads.md` cannot be read or updated, a source looks unreliable, or fewer than 3 genuinely new leads can be found.

### Execution steps

1. Read `sql_leads.md` first.

   - Identify all companies already recorded.
   - Treat near-duplicates, subsidiaries, renamed entities, and spelling variants as existing leads unless clearly distinct.

2. Search for new leads.
   - Find up to 3 UK-based SQL DBA, Database Administrator, or closely equivalent database operations job postings from the last 7 days.
   - Prefer direct employer postings or reputable job boards with dates visible.
   - Filter out any company already present in `sql_leads.md`.

3. Research each new company.
   - Find one relevant trigger such as tech growth, hiring expansion, infrastructure change, merger/acquisition, outage, downtime, migration, cloud/database modernization, or other operational pressure.
   - Identify a likely senior technical contact: CTO, Engineering Director, Head of Infrastructure, Head of Platform, Database Manager, or equivalent.
   - Use only public professional routes such as LinkedIn profiles, company leadership pages, or generic business contact pages. Do not guess private email addresses.

4. Persist findings immediately.
   - Append each new company to `sql_leads.md` as soon as it is found.

   - Include company name, job URL, date found, contact details/source, trigger, score, and pain-point pitch.
   - Do not keep raw scrape dumps or unnecessary source text in memory/files; retain only the concise evidence needed for the lead record.

5. Score and pitch.
   - Score each lead from 1–10 based on relevance, recency, seniority/urgency, and likely SQL/database pain.
   - Draft a concise 3-sentence pain-point pitch for each lead.

6. Verify before reporting.
   - Re-open `sql_leads.md` after writing.
   - Confirm every reported company is present in the file and was not previously listed.
   - If verification fails, fix it before reporting.

### Report format

Report back with no Markdown table. Use this structured list for each lead:


🏦 **Company:** [Name]
🎯 **Score:** [X/10]
👤 **Contact:** [Name / Role / public route]
🛠 **Trigger:** [Brief pain point]
🔗 **Link:** [Job URL]

End with a short verification line confirming `sql_leads.md` was updated.

Optional cron template, if you want it scheduled:

openclaw cron add \
  --name "UK SQL DBA Lead Scout" \

  --cron "0 9 * * 1-5" \
  --tz Europe/London \
  --session isolated \
  --timeout-seconds 900 \
  --announce \
  --channel discord \
  --to "channel:YOUR_CHANNEL_ID" \
  --message "Execute the UK SQL DBA Lead Scout standing order. Find up to 3 new UK SQL DBA / Database Administrator leads from the last 7 days, update sql_leads.md, verify the file, and report results in the required emoji format."

Replace YOUR_CHANNEL_ID with the channel/thread target you want reports delivered to.

raven frigate May 14, 2026, 7:27 PM

try looking at it again https://cl1p.net/4562

acoustic hazelBOT May 14, 2026, 7:27 PM

Yep, got it this time — 4562 populated now. Here’s the matching standing-order version for the 4561 prompt, using the same style:

## Standing order: UK SQL DBA lead scout

When I say "find SQL leads", "run the DBA scout", "update the SQL leads file", or similar, execute this workflow without rediscovering the process.

### 1. Check existing lead history

Read the existing leads file first:

`sql_leads.md`

Use it to identify companies already found.
Filter out any company already listed in `sql_leads.md`.
Only proceed with brand-new leads.


If `sql_leads.md` cannot be read:
- report the exact file/read error
- do not continue with lead discovery
- do not guess which companies were already found

### 2. Search for new SQL DBA leads

Use Firecrawl to find 3 UK-based job postings from the last 7 days for:
- SQL DBA
- SQL Database Administrator
- Database Administrator
- closely equivalent SQL/database operations roles

Prefer direct employer job pages or reputable job boards with visible posting dates.

Do not include duplicate companies, stale postings, non-UK roles, or companies already present in `sql_leads.md`.

If Firecrawl fails:
- report the exact Firecrawl error
- do not work around the failure with unrelated scraping methods unless I explicitly approve it
- do not continue to scoring or reporting

### 3. Research each new company

For each brand-new company, find:
- recent tech growth, infrastructure expansion, merger/acquisition activity, downtime, migration, hiring surge, or similar operational trigger
- the CTO, Engineering Director, Head of Infrastructure, Head of Platform, Database Manager, or closest relevant senior technical contact
- public LinkedIn, company profile, or public contact route

Use only public professional contact routes.

Do not guess private email addresses.

### 4. Update `sql_leads.md`

Immediately append each new lead to `sql_leads.md` once found.
Include:
- company name
- job URL
- date found
- contact name and role
- public contact route
- trigger / pain point
- score from 1–10
- 3-sentence pain-point pitch

After updating, re-read `sql_leads.md` and verify that each reported lead was written successfully.

### 5. Scoring and cleanup

Score each new lead from 1–10 based on:
- role relevance
- posting recency
- likely SQL/database pain
- evidence of growth, migration, downtime, or operational pressure
- quality of identified contact route

After the file is updated and verified, clear active working memory of raw scrape data.
Keep only concise lead records and cited URLs in `sql_leads.md`.

### 6. Final report


Do not narrate routine intermediate steps such as:
- "Now I’m checking the leads file"
- "Now I’m searching Firecrawl"
- "Now I’m researching contacts"

Only report the final result.
Do not use a Markdown table.
Use this exact structured format for each lead:

🏦 **Company:** [Name]
🎯 **Score:** [X/10]
👤 **Contact:** [Name / Role / public route]
🛠 **Trigger:** [Brief pain point]
🔗 **Link:** [Job URL]


End with one short verification line confirming `sql_leads.md` was updated.

If fewer than 3 brand-new leads are found, report only the valid new leads and explain briefly why fewer than 3 qualified.

That should fit beside the existing “Email SQL leads” order cleanly.