Official agent skill

Search Discovery

by anthropics in anthropics/commerce-agents

Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick.

OfficialApache-2.0Auto-check passed

Install Search Discovery

skills CLI
$ npx skills add anthropics/commerce-agents --skill search-discovery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/commerce-agents search-discovery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/commerce-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/shopping-agent/skills/search-discovery .claude/skills/search-discovery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
search-discovery
GitHub stars
3.2k
Token cost
~802 tokens
SKILL.md length
479 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick.

  • SKILL.md covers Read the request and phrase…, Shortlist and recommendation and When the item is for someone…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Search Discovery is an agent skill from anthropics/commerce-agents, published by the product's own GitHub organization. Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick. Not needed when one search for the thing the customer named answers the request, or when the customer wants to learn what matters in a category first (purchase-research).

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. The licence is Apache-2.0.

Example prompts

  • “/search-discovery”

What it can do on your machine

Read from SKILL.md and the folder at commit fd4d592. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Search Discovery loads about 802 tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 479 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~802

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/commerce-agents at commit fd4d592, republished under its Apache-2.0 licence (© anthropics). 479 words, ~802 tokens.

Download SKILL.mdSave it as .claude/skills/search-discovery/SKILL.md (or your agent's skills folder).
name
search-discovery
description
Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick. Not needed when one search for the thing the customer named answers the request, or when the customer wants to learn what matters in a category first (purchase-research).

Search and discovery

Below, "item" means whatever this catalog sells: a product, a stay, a plan, or a seat.

Turn the need the customer described into a few options and a recommendation, in as few turns as the request allows.

  • Take the budget, the recipient, dates, sizes, intended use, and dealbreakers out of the message and apply them; let the results show that you did instead of reading them back.
  • Search by default; a budget, a size, or a recipient you were not given narrows the shortlist and is asked about beside the results. Ask first only when the search cannot be run without the missing fact (a stay with no dates), and then ask that one question, with the likely answers as chips.
  • Apply what the profile you were given already holds (household, saved limits, what they own) without asking about it again.
  • Word the query in the catalog's vocabulary and leave the customer's phrasing behind.
  • Run one search per distinct thing the request names, all in the same round. Put a constraint the customer stated in a filter; put a guess about what they might also want in the query wording.

Shortlist and recommendation

  • Show three to six options in present_products with the one you recommend first. Each pick's reason is one clause naming the customer's own constraint it meets. When the options differ in a way that matters, name that trade-off in the text.
  • When the customer has narrowed to two to four finalists, use present_comparison on the dimensions they raised instead of another row of cards.
  • Answer a question the results do not cover with get_product_details, or with web_search where one is registered; when neither settles it, say it is unknown.
  • Before saying that several options fit under a figure, add up their prices. When the sum is over, give the sum, and offer no chip for a bundle the sum rules out.
  • Show an item the store cannot supply right now as unavailable, and introduce whatever you offer in its place as a stand-in.
  • Keep the text before the component to one to three sentences of guidance.
Show full SKILL.md (120 more words)Show less

When the item is for someone else

  • Take the recipient's age, interests, and the budget from the request, the profile you were given, or a recall result about this recipient; a fact saved about a different person does not transfer. When none of the three says who the recipient is, ask the one question, or show a varied set and say their tastes are unknown.
  • Where a spread helps, include one dependable pick, one meant to delight, and one that costs less.
  • Surface the practicalities the attributes carry (sizing, batteries, noise, the age marking) where they matter for this recipient. Read an age marking against the recipient's age: leave a mismatched item off, or show it with the mismatch stated.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in shopping-agent/skills/search-discovery of anthropics/commerce-agents.

Open the folder on GitHubat commit fd4d592

Compare with similar skills

Search Discovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Search Discovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Search Discovery this skillanthropics/commerce-agents3.2k—~802Automated safety check: PassApache-2.0
Gift Up AutomationComposioHQ/awesome-claude-skills77k3 repos~730Automated safety check: PassNone
Turn This Into A Threadsickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT
Daily Giftsickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT-0
Relsa Severity AssessmentK-Dense-AI/scientific-agent-skills48k1 repos~5.2kAutomated safety check: NotesMIT
Wobbling Ty Constraint Orderastral-sh/ruff50k—~838Automated safety check: PassMIT

Similar skills

  • Gift Up Automation

    ComposioHQ/awesome-claude-skills

    Automate Gift Up tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~730 tokens
    Productivity & AutomationAuto-check passed
  • Turn This Into A Thread

    sickn33/agentic-awesome-skills

    Turn a long idea, transcript, article or draft into a Twitter/X thread where every tweet stands alone.

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Writing & ContentAuto-check passed
  • Daily Gift

    sickn33/agentic-awesome-skills

    Relationship-aware daily gift engine with five-stage creative pipeline — editorial judgment, synthesis, concept generation, visual strategy, and rendering in H5, image, or video

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Relsa Severity Assessment

    K-Dense-AI/scientific-agent-skills

    Supports multivariate severity assessment and exploratory endpoint-time score forecasting for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast…

    48k GitHub starsUsed in 1 repo~5.2k tokens
    Data & AnalyticsAuto-check: notes
  • Official

    A skill your agent uses when a user asks to wobble ty constraint ordering, check constraint-set or TDD ordering determinism, test reversed constraint/typevar IDs, or investigate nondeterministic ty…

    50k GitHub stars~838 tokensUpdated today
    Testing & QAAuto-check passed
  • Constraint-Driven Development

    addyosmani/agent-skills

    Records a project's quality bar in CONSTRAINTS.md and watches diffs for signs an agent quietly weakened it, such as suppressions, skipped tests or lowered thresholds.

    104k GitHub starsUsed in 2 repos~5.2k tokens
    DevelopmentAuto-check passed

More from anthropics/commerce-agents

All 16 skills in this repo
  • Commerce Evals

    anthropics/commerce-agents

    Official

    Authoring and running behavioral evals for a shopping or merchant agent, covering the case shape, authoring rules, code graders and judges, the run pattern, and poisoned fixtures.

    3.2k GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed
  • Catalog Listings

    anthropics/commerce-agents

    Official

    Creating and improving listing content, covering titles, descriptions, attribute completeness, categorization fixes, image callouts written as text, edits written from material the operator…

    3.2k GitHub stars~1k tokensUpdated 8 days ago
    Auto-check passed
  • Commerce Architecture

    anthropics/commerce-agents

    Official

    How the reference commerce agents of either role are structured, covering the loop, where each rule lives, skills, the backend interface, delegates, and model fields.

    3.2k GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed
  • Commerce Merchant Operations

    anthropics/commerce-agents

    Official

    The reference merchant agent, covering its flows, staged changes and host approval, metrics grounding, the analysis delegate, store memory, components, and marketplace rules.

    3.2k GitHub stars~2.1k tokensUpdated 8 days ago
    Auto-check passed
  • Commerce Prompt Caching

    anthropics/commerce-agents

    Official

    The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are…

    3.2k GitHub stars~2k tokensUpdated 8 days ago
    Auto-check passed
  • Commerce Trust Safety

    anthropics/commerce-agents

    Official

    The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules.

    3.2k GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed

Questions about Search Discovery

What does Search Discovery do?

Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick. Search Discovery is an agent skill from anthropics/commerce-agents, published by the product's own GitHub organization. Turning a described need (several constraints, a gift, a choice between candidates already in view, a search that came back empty or sold out) into a shortlist and a pick.

How do I install Search Discovery in Claude Code?

Run `npx skills add anthropics/commerce-agents --skill search-discovery -a claude-code`. Or copy the skill folder (shopping-agent/skills/search-discovery in anthropics/commerce-agents) into .claude/skills/search-discovery in your project. Claude Code loads it when a task matches its description.

How do I install Search Discovery in Codex?

Run `npx skills add anthropics/commerce-agents --skill search-discovery -a codex`. Or copy the skill folder (shopping-agent/skills/search-discovery in anthropics/commerce-agents) into .agents/skills/search-discovery in your project. Codex loads it when a task matches its description.

Can I use Search Discovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/commerce-agents --skill search-discovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search-discovery, .gemini/skills/search-discovery, .github/skills/search-discovery and .opencode/skills/search-discovery in your project.

What does Search Discovery need to run?

SKILL.md names no scripts, command-line tools or credentials: Search Discovery is instructions for the agent only.

Does Search Discovery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Search Discovery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Search Discovery use?

Search Discovery is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Search Discovery use?

About 802 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Search Discovery?

Skills that share tags, products or a category with Search Discovery: Gift Up Automation (ComposioHQ/awesome-claude-skills, 77k stars), Turn This Into A Thread (sickn33/agentic-awesome-skills, 47k stars), Daily Gift (sickn33/agentic-awesome-skills, 47k stars) and Relsa Severity Assessment (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Search Discovery?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/commerce-agents, which has 3,198 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 2, 2026.

Source: anthropics/commerce-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.