Agent skill

Explore

by mirumee in mirumee/nimara-ecommerce

Ways to explore llm-wiki and answer from it. An agent skill from mirumee/nimara-ecommerce.

BSD-3-ClauseAuto-check passedKnowledge Management

Install Explore

skills CLI
$ npx skills add mirumee/nimara-ecommerce --skill explore -a claude-code

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

GitHub CLI
$ gh skill install mirumee/nimara-ecommerce explore --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/mirumee/nimara-ecommerce.git skills-src && mkdir -p .claude/skills && cp -r skills-src/llm-wiki/.claude/skills/explore .claude/skills/explore && 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
explore
GitHub stars
129
Token cost
~436 tokens
SKILL.md length
225 words
Files
2 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Ways to explore llm-wiki and answer from it. An agent skill from mirumee/nimara-ecommerce.

  • Works in 4 steps: The router → Crosslinks → Semantic search → …
  • The user asks to find
  • SKILL.md covers 1. The router, 2. Crosslinks, 3. Semantic search and 4. Plain search
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Explore is an agent skill from mirumee/nimara-ecommerce. Ways to explore llm-wiki and answer from it. Use when the user asks to find, explain, compare, or cite anything the wiki already holds — product state, flows, integrations, operations, PRDs, RFCs, ADRs, implementation evidence, strategy, personas, QA knowledge, or source notes. Read-only: it never writes to the wiki.

Its SKILL.md is about 440 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/semantic-search.md`).

It sits in Knowledge Management, covering LLM wikis, Architecture decision records and PRD writing. It works with shadcn/ui. The repository describes itself as: Headless, composable ecommerce storefront built with Next.js, Typescript, and shadcn/ui. The licence is BSD-3-Clause.

When your agent uses it

  • The user asks to find
  • Cite anything the wiki already holds — product state
  • Implementation evidence

Example prompts

  • “/explore”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. The router
  2. Crosslinks
  3. Semantic search
  4. Plain search

What it can do on your machine

Read from SKILL.md and the folder at commit b883dec. 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

Explore loads about 436 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 225 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~436
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

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 mirumee/nimara-ecommerce at commit b883dec, republished under its BSD-3-Clause licence (© mirumee). 225 words, ~436 tokens.

Download SKILL.mdSave it as .claude/skills/explore/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
explore
description
Ways to explore llm-wiki and answer from it. Use when the user asks to find, explain, compare, or cite anything the wiki already holds — product state, flows, integrations, operations, PRDs, RFCs, ADRs, implementation evidence, strategy, personas, QA knowledge, or source notes. Read-only: it never writes to the wiki.

Explore

Three ways in, in the order that usually costs least, and a fourth for moving between records once you are already holding one. Read-only throughout: this skill answers questions and cites files.

1. The router

llm-wiki/index.md lists every note once, grouped by record type, with a one-line hook. Start here when you know roughly what kind of thing you are after. It is the only file guaranteed to mention everything.

Concepts here reference each other with ordinary Markdown links. Once you hold one record, following its links is cheaper than searching again: its neighbourhood is already declared.

qmd is a local index over the same Markdown. Reach for it when the question is a phrase rather than a location, and you do not know which record would hold the answer.

Read references/semantic-search.md before using it. It covers checking that the index describes this checkout — a stale one silently answers about another worktree — plus which of query, search, and get fits, and the failure modes that make a miss look like an absence.

Grep and glob still beat everything for an exact token: a record ID, a field name, a commit SHA, an env var. The tree is 90-odd files; reading three of them in full is often cheaper than one semantic round trip.

Start from index.md.

© mirumee, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in llm-wiki/.claude/skills/explore of mirumee/nimara-ecommerce.

  • SKILL.md
  • references/semantic-search.md

Open the folder on GitHubat commit b883dec

Compare with similar skills

Explore 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.

Explore compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Explore this skillmirumee/nimara-ecommerce129—~436Automated safety check: PassBSD-3-Clause
Doc Co-Authoring WorkflowshareAI-lab/Kode-CLI5.2k—~977Automated safety check: PassApache-2.0
Run Assert Evalresponsibleai/ASSERT327—~11kAutomated safety check: NotesMIT
Schematicblader/schematic239—~2.2kAutomated safety check: PassMIT
Shep Workstreamsshep-ai/shep264—~2.5kAutomated safety check: PassMIT
Foreman Grill DocsVisionForge-OU/foreman444—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Doc Co-Authoring Workflow

    shareAI-lab/Kode-CLI

    Guides a three-stage workflow for turning partial context into a clear PRD, RFC or design doc: capture context, draft section by section, then test with a fresh reader.

    5.2k GitHub stars~977 tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Run Assert Eval

    responsibleai/ASSERT

    Run an ASSERT evaluation against a described risk. An agent skill from responsibleai/ASSERT.

    327 GitHub stars~11k tokensUpdated yesterday
    SecurityAuto-check: notes
  • Schematic

    blader/schematic

    Reverse engineer a detailed product and technical specification document from a git branch's implementation.

    239 GitHub stars~2.2k tokensUpdated 7 mo ago
    Product & Project ManagementAuto-check passed
  • Shep Workstreams

    shep-ai/shep

    A skill your agent uses when a large body of work (a version milestone, an epic, a roadmap, a set of PRDs/design docs) needs to be broken into parallel workstreams and executed with the shep CLI.

    264 GitHub stars~2.5k tokensUpdated 2 days ago
    Product & Project ManagementAuto-check passed
  • Foreman Grill Docs

    VisionForge-OU/foreman

    Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory.

    444 GitHub stars~1.6k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Write new TiDB documentation or update existing TiDB documentation from code changes, PRs, issues, design docs, product specs, rough drafts, existing docs, or short feature descriptions.

    616 GitHub stars~2.3k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from mirumee/nimara-ecommerce

All 12 skills in this repo
  • Project Guidelines

    mirumee/nimara-ecommerce

    Guide for working with Nimara's layered monorepo architecture.

    129 GitHub stars~4.8k tokensUpdated yesterday
    Auto-check passed
  • Prd Modeling

    mirumee/nimara-ecommerce

    A skill your agent uses when creating, rewriting, refining, or stress-testing a Product Requirements Document (PRD), including turning an initiative or feature brief into product requirements.

    129 GitHub stars~824 tokensUpdated yesterday
    Auto-check passed
  • Rfc Modeling

    mirumee/nimara-ecommerce

    A skill your agent uses when designing, drafting, refining, or stress-testing an RFC for an approved PRD, including requests for a design doc, solution design, or how to build it.

    129 GitHub stars~920 tokensUpdated yesterday
    Auto-check passed
  • Ucp Agent

    mirumee/nimara-ecommerce

    Operate Nimara's UCP REST commerce API. An agent skill from mirumee/nimara-ecommerce.

    129 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Show Me

    mirumee/nimara-ecommerce

    Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.

    129 GitHub starsUsed in 7 repos~809 tokens
    Auto-check passed
  • Bug Retest Triage

    mirumee/nimara-ecommerce

    Retest a reported defect on the live Nimara board (Jira project MS, board 74) and give it an evidence-backed verdict — still reproduces → Open, fixed → Done, blocked → leave In testing and ask.

    129 GitHub stars~888 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Explore

What does Explore do?

Ways to explore llm-wiki and answer from it. An agent skill from mirumee/nimara-ecommerce. Explore is an agent skill from mirumee/nimara-ecommerce. Ways to explore llm-wiki and answer from it.

When should I use Explore?

Explore fits situations like: the user asks to find; cite anything the wiki already holds — product state; implementation evidence.

How do I install Explore in Claude Code?

Run `npx skills add mirumee/nimara-ecommerce --skill explore -a claude-code`. Or copy the skill folder (llm-wiki/.claude/skills/explore in mirumee/nimara-ecommerce) into .claude/skills/explore in your project. Claude Code loads it when a task matches its description.

How do I install Explore in Codex?

Run `npx skills add mirumee/nimara-ecommerce --skill explore -a codex`. Or copy the skill folder (llm-wiki/.claude/skills/explore in mirumee/nimara-ecommerce) into .agents/skills/explore in your project. Codex loads it when a task matches its description.

Can I use Explore 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 mirumee/nimara-ecommerce --skill explore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/explore, .gemini/skills/explore, .github/skills/explore and .opencode/skills/explore in your project.

What does Explore need to run?

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

Does Explore 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 Explore 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 Explore use?

Explore is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Explore use?

About 436 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Explore?

Skills that share tags, products or a category with Explore: Doc Co-Authoring Workflow (shareAI-lab/Kode-CLI, 5.2k stars), Run Assert Eval (responsibleai/ASSERT, 327 stars), Schematic (blader/schematic, 239 stars) and Shep Workstreams (shep-ai/shep, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Explore?

mirumee (a GitHub organization) maintains it in mirumee/nimara-ecommerce, which has 129 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 6, 2026.

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