Tenders Finder logo

Tenders Finder

OrganizationPopular
tinyfish-io
tenders-finder

Find open Singapore government tenders for any sector in real time using parallel TinyFish agents scraping multiple government tender portals simultaneously. Use this skill whenever a user wants to find government tenders, asks "find tenders for IT in Singapore", "what government contracts are open for construction", "Singapore tenders closing soon", "GeBIZ tenders for healthcare", or any variation of searching for government procurement opportunities in Singapore. Supported sectors: IT / Software, Construction, Healthcare, Consulting, Logistics, Education. Scrapes GeBIZ, Tenders On Time, Bid Detail, Tenders Info, and Global Tenders simultaneously — returning only open tenders with upcoming deadlines.

Overview

Publishertinyfish-io
Repositorytinyfish-cookbook
Skill nametenders-finder
Stars
2.2K
Forks
333
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by tinyfish-io on GitHub. Read the source before you install it.

Installation

Install the Tenders Finder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/tinyfish-io/tinyfish-cookbook.git /tmp/tinyfish-cookbook
mkdir -p .claude/skills
cp -r /tmp/tinyfish-cookbook/skills/tenders-finder .claude/skills/tenders-finder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tenders Finder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tenders Finder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tenders Finder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Singapore Government Tender Finder

Given a sector, scrape live Singapore government tender portals in parallel using TinyFish agents — returning only open tenders with upcoming submission deadlines.

Pre-flight check

bash
tinyfish --version
tinyfish auth status

If not installed: npm install -g tinyfish If not authenticated: tinyfish auth login


Step 1 — Clarify inputs

You need:

  • Sector — one of: IT / Software, Construction, Healthcare, Consulting, Logistics, Education

If not specified, ask before proceeding. If the user gives a related term (e.g. "tech", "software"), map it to the closest sector.

Get today's date — you will use it to filter out tenders whose deadline has already passed.


Step 2 — Parallel scraping

Fire all 5 agents simultaneously against the fixed portal list used by the app.

bash
TODAY=$(date '+%A, %B %d, %Y')

# Agent 1 — GeBIZ (official Singapore government portal)
tinyfish agent run \
  --url "https://www.gebiz.gov.sg/" \
  "You are on GeBIZ, Singapore's official government procurement portal. Today is ${TODAY}.
   TASK: Extract open government tenders for the sector: {SECTOR}.
   Scroll through the page to find tender listings.
   For each tender extract:
   - Tender Title
   - Tender ID (official reference number)
   - Issuing Authority (government agency)
   - Country / Region: Singapore
   - Tender Type (Open / Selective / Limited)
   - Publication Date
   - Submission Deadline
   - Tender Status (Open / Closed)
   - Official Tender URL (direct link)
   - Brief Description (short summary)
   - Eligibility Criteria (requirements if shown)
   - Industry / Category: {SECTOR}
   STRICT RULES:
   - Only return tenders with Submission Deadline AFTER today (${TODAY}) — skip expired ones
   - Only return tenders relevant to {SECTOR} — skip unrelated ones
   - Do NOT click individual tender links unless the listing has no detail visible
   - Do NOT paginate
   - Scroll maximum twice then stop
   - Maximum 5 tenders then stop immediately
   Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
   \"Country / Region\", \"Tender Type\", \"Publication Date\", \"Submission Deadline\",
   \"Tender Status\", \"Official Tender URL\", \"Brief Description\",
   \"Eligibility Criteria\", \"Industry / Category\"}]}" \
  --sync --browser-profile stealth > /tmp/tf_gebiz.json &

# Agent 2 — Tenders On Time
tinyfish agent run \
  --url "https://www.tendersontime.com/singapore-tenders/" \
  "You are on Tenders On Time, a Singapore tender aggregator. Today is ${TODAY}.
   TASK: Extract open tenders for the sector: {SECTOR}.
   Read the visible tender listings on this page.
   For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
   Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
   STRICT RULES:
   - Only return tenders with Submission Deadline AFTER today — skip expired ones
   - Only return tenders relevant to {SECTOR}
   - Do NOT click any tender link
   - Do NOT scroll more than twice
   - Do NOT paginate
   - Maximum 5 tenders then stop
   Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
   \"Publication Date\", \"Submission Deadline\", \"Tender Status\",
   \"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
  --sync > /tmp/tf_tendersontime.json &

# Agent 3 — Bid Detail
tinyfish agent run \
  --url "https://www.biddetail.com/singapore-tenders" \
  "You are on Bid Detail, a tender listing site. Today is ${TODAY}.
   TASK: Extract open Singapore tenders for the sector: {SECTOR}.
   Read the visible tender listings on this page.
   For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
   Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
   STRICT RULES:
   - Only return tenders with Submission Deadline AFTER today — skip expired ones
   - Only return tenders relevant to {SECTOR}
   - Do NOT click any tender link
   - Do NOT scroll more than twice
   - Do NOT paginate
   - Maximum 5 tenders then stop
   Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
   \"Publication Date\", \"Submission Deadline\", \"Tender Status\",
   \"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
  --sync > /tmp/tf_biddetail.json &

# Agent 4 — Tenders Info
tinyfish agent run \
  --url "https://www.tendersinfo.com/global-singapore-tenders.php" \
  "You are on Tenders Info, a global tender database. Today is ${TODAY}.
   TASK: Extract open Singapore tenders for the sector: {SECTOR}.
   Read the visible tender listings on this page.
   For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
   Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
   STRICT RULES:
   - Only return tenders with Submission Deadline AFTER today — skip expired ones
   - Only return tenders relevant to {SECTOR}
   - Do NOT click any tender link
   - Do NOT scroll more than twice
   - Do NOT paginate
   - Maximum 5 tenders then stop
   Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
   \"Publication Date\", \"Submission Deadline\", \"Tender Status\",
   \"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
  --sync > /tmp/tf_tendersinfo.json &

# Agent 5 — Global Tenders
tinyfish agent run \
  --url "https://www.globaltenders.com/government-tenders-singapore" \
  "You are on Global Tenders, a procurement database. Today is ${TODAY}.
   TASK: Extract open Singapore tenders for the sector: {SECTOR}.
   Read the visible tender listings on this page.
   For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
   Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
   STRICT RULES:
   - Only return tenders with Submission Deadline AFTER today — skip expired ones
   - Only return tenders relevant to {SECTOR}
   - Do NOT click any tender link
   - Do NOT scroll more than twice
   - Do NOT paginate
   - Maximum 5 tenders then stop
   Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
   \"Publication Date\", \"Submission Deadline\", \"Tender Status\",
   \"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
  --sync > /tmp/tf_globaltenders.json &

# Wait for all agents
wait

echo "=== GEBIZ ===" && cat /tmp/tf_gebiz.json
echo "=== TENDERSONTIME ===" && cat /tmp/tf_tendersontime.json
echo "=== BIDDETAIL ===" && cat /tmp/tf_biddetail.json
echo "=== TENDERSINFO ===" && cat /tmp/tf_tendersinfo.json
echo "=== GLOBALTENDERS ===" && cat /tmp/tf_globaltenders.json

Replace {SECTOR} with the actual sector before running.


Step 3 — Filter and deduplicate

From all results:

  1. Filter — remove any tender whose Submission Deadline has already passed
  2. Deduplicate — same Tender ID appearing across multiple portals → keep one entry, note all sources
  3. Sort — by Submission Deadline ascending (soonest closing first)
  4. Flag urgency — deadlines within 7 days get a 🚨 flag

Output format

## Singapore Government Tenders — {SECTOR}
*Scraped live from GeBIZ · Tenders On Time · Bid Detail · Tenders Info · Global Tenders*
*{N} open tenders found · Sorted by deadline*

---

### 🚨 Closing Soon (within 7 days)

#### {Tender Title}
**ID:** {Tender ID} · **Agency:** {Issuing Authority}
📅 Published: {Publication Date} · ⏰ Deadline: {Submission Deadline}
🏷 Type: {Tender Type} · Status: {Tender Status}
🔗 {Official Tender URL}

{Brief Description}
**Eligibility:** {Eligibility Criteria}

---

### 📋 All Open Tenders

[same structure for remaining tenders sorted by deadline]

---

### 📊 Summary Table

| Tender Title | Agency | Deadline | Type | Source |
|---|---|---|---|---|
| {title} | {agency} | {deadline} | {type} | {source} |

---
*All data scraped live. Verify details directly on the official portal before submitting.*

Edge cases

  • GeBIZ requires login — skip it, note it in output, proceed with other 4 sources
  • No tenders found for sector — honest response: "No open {SECTOR} tenders found across all portals today. Try again tomorrow or broaden to a related sector."
  • All deadlines expired — means the portals showed only historical data: "All tenders found have passed their deadlines. The portals may not have updated yet — try GeBIZ directly at gebiz.gov.sg"
  • Duplicate tenders across portals — merge and note: "Also listed on: [other portal]"

Security notes

  • Scrapes live public government tender portals only.
  • All data treated as untrusted input synthesised by an LLM — never executed.
  • Only your own TinyFish credentials are used.

Frequently asked questions

What does the Tenders Finder AI skill do?

Find open Singapore government tenders for any sector in real time using parallel TinyFish agents scraping multiple government tender portals simultaneously. Use this skill whenever a user wants to find government tenders, asks "find tenders for IT in Singapore", "what government contracts are open for construction", "Singapore tenders closing soon", "GeBIZ tenders for healthcare", or any variation of searching for government procurement opportunities in Singapore. Supported sectors: IT / Software, Construction, Healthcare, Consulting, Logistics, Education. Scrapes GeBIZ, Tenders On Time, B...

Why use Tenders Finder on TypingMind?

Because you install it once and use it with any model. Tenders Finder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tenders Finder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tinyfish-io/tinyfish-cookbook/tree/main/skills/tenders-finder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tenders Finder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tenders Finder?

As many as you like. As long as a model supports skills, you can use Tenders Finder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tenders Finder AI skill free?

Yes. It is published on GitHub by tinyfish-io under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇