SkillNet is infrastructure for finding, creating, evaluating, combining, and coordinating reusable capabilities for AI agents. Agent developers use it as a searchable and installable library of skills and as a system for selecting skills for particular tasks. The catalogue contains skills that can be discovered, installed, or used with SkillNet.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zjunlp/skillnet/webshop-initial-searchnpx skills add zjunlp/SkillNet --skill webshop-initial-searchgit clone --depth 1 https://github.com/zjunlp/SkillNetWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zjunlp/skillnet/webshop-initial-search)<a href="https://agentmods.dev/skills/zjunlp/skillnet/webshop-initial-search"><img src="https://agentmods.dev/badge/skills/zjunlp/skillnet/webshop-initial-search.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.00486 |
| Opus 5 | $0.00045 | $0.00243 |
| Sonnet 5 | $0.00018 | $0.00097 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
webshop-initial-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Instructions
-
Parse Requirements: Extract the core product criteria from the user's instruction. Focus on:
- Quantity & Packaging: (e.g., "24 pack")
- Size: (e.g., "7.5 ounce bottles")
- Key Attributes: (e.g., "non-gmo", "classic tonic")
- Price Constraint: (e.g., "price lower than 50.00 dollars") - This is for validation later, not for the initial search query.
-
Formulate Search Query: Combine the extracted criteria into a concise, natural-language search string. Prioritize specificity to filter results effectively.
- Example: For "i would like to get a 24 pack of 7.5 ounce bottles of non-gmo classic tonic", the query should be:
24 pack of 7.5 ounce bottles of non-gmo classic tonic - Do not include the price constraint in the search keywords.
- Example: For "i would like to get a 24 pack of 7.5 ounce bottles of non-gmo classic tonic", the query should be:
-
Execute Search: Use the platform's
search[<keywords>]action with your formulated query.- The action output will be the initial search results page observation.
-
Next Steps: After executing this skill, proceed to evaluate the search results. The next actions will typically involve clicking on a promising product listing or refining the search.
Example
User instruction: "I would like to find a 24 pack of 7.5 ounce bottles of non-gmo classic tonic, and target price lower than 50.00 dollars"
Thought: I need to search for the product using the key attributes. I will omit the price constraint from the search keywords.
Action: search[24 pack of 7.5 ounce bottles of non-gmo classic tonic]
Observation: The platform returns the initial search results page with matching product listings.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 30 lines · 90 tokens per session scan A b158f8ed3cec
webshop-initial-search is a skill published in the GitHub repository zjunlp/SkillNet (1,253 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 486 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
ddr-globem-analysis
Analyze a specific participant's longitudinal passive-sensing and psychological data in the GLOBEM digital depression research dataset. Use this skill whenever the task involves: analyzing a user's mental health or behavioral data from wearables/smartphones, generating QA pairs about behavioral/psychological changes…
applicable-fee-ids
Solve questions about which fee IDs apply to a payment merchant, transaction characteristics, or time period in the dabstep dataset. Use this skill for any question asking "which fee IDs apply to X", "what are the applicable fee IDs for merchant Y", "which merchants are affected by fee Z", or any query involving…
Fee_Delta_and_Impact_Simulation
Solve dabstep FeeDeltaandImpactSimulation questions: computing fee deltas when a fee's rate changes, and identifying which merchants are affected by fee rule changes. Use when asked about fee impact, delta payments, rate changes, or which merchants would be affected by modifying a fee rule.
Total_Fees_Calculation
Skill for computing total payment processing fees for a merchant over a specific day, date range, or month in the dabstep dataset. Use this skill whenever the question asks for "total fees", "fees paid", or "fees charged" for a merchant over some time period. The computation requires matching each transaction to a fee…
mimic-iv-patient-analysis
Comprehensive strategy for analyzing individual patient records in MIMIC-IV EHR database and generating high-quality, diverse QA pairs. Use this skill whenever the task involves analyzing a specific patient's clinical data from MIMIC-IV (or similar EHR databases), querying across hospital and ICU tables, and…