Agent skill

Rebuild Skill Index

by hanamizuki in hanamizuki/solopreneur

Rebuild the per-machine, per-config extended skill index used by platform subagents.

MITAuto-check passedMobile

Install Rebuild Skill Index

skills CLI
$ npx skills add hanamizuki/solopreneur --skill rebuild-skill-index -a claude-code

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

GitHub CLI
$ gh skill install hanamizuki/solopreneur rebuild-skill-index --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/hanamizuki/solopreneur.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/solopreneur/rebuild-skill-index .claude/skills/rebuild-skill-index && 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
rebuild-skill-index
GitHub stars
152
Token cost
~4k tokens
SKILL.md length
1,235 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Rebuild the per-machine, per-config extended skill index used by platform subagents.

  • Works in 6 steps: Resolve base directory → Collect candidate skills → Read curated dedup lists → …
  • The user says rebuild skill index
  • SKILL.md covers Step 0: Resolve base directory, Step 1: Collect candidate skills, Step 2: Read curated dedup lists and Step 3: Classify each candidate, plus 3 more sections
  • Calls claude; reaches github.com

What it does

Rebuild Skill Index is an agent skill from hanamizuki/solopreneur. Rebuild the per-machine, per-config extended skill index used by platform subagents. Scans installed Claude Code skills, classifies each by platform relevance (iOS, Android, design, marketer, neo4j-dev, …) using the frontmatter description, and writes one file per platform under <base/solopreneur/skill-index/ where <base is $CLAUDECONFIGDIR or ~/.claude. Use when the user says "rebuild skill index", "refresh skill index", or after installing / removing platform-related skills.

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Mobile, covering Subagents. It works with Android, iOS and Neo4j. The repository describes itself as: Skills and agents for solopreneurs — ship, review, debug, and think through problems with AI. The licence is MIT.

When your agent uses it

  • The user says rebuild skill index
  • Refresh skill index
  • After installing / removing platform-related skills

Example prompts

  • “rebuild skill index”
  • “refresh skill index”
  • “/rebuild-skill-index”

Workflow steps

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

  1. Resolve base directory
  2. Collect candidate skills
  3. Read curated dedup lists
  4. Classify each candidate
  5. Write output files
  6. Report to the user

What it can do on your machine

Read from SKILL.md and the folder at commit f43f001. 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

    Shell commands in SKILL.md call:

    • claude

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    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

Rebuild Skill Index loads about 4k tokens when it runs. Until then it costs about 128 tokens; SKILL.md has 1,235 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~128
When it runs · the whole SKILL.md, loaded when a task matches
~4k

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 hanamizuki/solopreneur at commit f43f001, republished under its MIT licence (© hanamizuki). 1,235 words, ~4,049 tokens.

Download SKILL.mdSave it as .claude/skills/rebuild-skill-index/SKILL.md (or your agent's skills folder).
name
rebuild-skill-index
description
Rebuild the per-machine, per-config extended skill index used by platform subagents. Scans installed Claude Code skills, classifies each by platform relevance (iOS, Android, design, marketer, neo4j-dev, …) using the frontmatter description, and writes one file per platform under `<base>/solopreneur/skill-index/` where `<base>` is `$CLAUDE_CONFIG_DIR` or `~/.claude`. Use when the user says "rebuild skill index", "refresh skill index", or after installing / removing platform-related skills.

Rebuild Skill Index

Generate one index file per platform, specific to the current Claude Code config. Each file is the extended list of every platform-relevant skill installed on this machine that is not already in the curated list inside the matching agent's markdown file.

Outputs are consumed by the matching subagents (ios-dev, android-dev, designer, marketer, neo4j-dev) and any caller that dispatches them (/specialist-review, /plan-review, /todos-review).

Step 0: Resolve base directory

Either harness may be invoked with a non-default config home — CLAUDE_CONFIG_DIR on Claude Code, CODEX_HOME on Codex. Resolve the running session's base directory first via Bash:

bash
# Codex exports CODEX_THREAD_ID on every session, while CODEX_HOME exists only
# when the user sets one; anything that is not Codex keeps the Claude path.
if [ -n "${CODEX_THREAD_ID:-}" ]; then
  BASE="${CODEX_HOME:-$HOME/.codex}"
else
  BASE="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
fi
echo "$BASE"

Use the resolved absolute value in all subsequent read and write paths and in Path: metadata written into output files — readers should not have to re-resolve.

Step 1: Collect candidate skills

For each source below, read frontmatter only (the name: and description: fields). Do not read full SKILL.md bodies — that would burn unnecessary tokens. Use Read file_path=<path> limit=30 (30 lines covers any reasonable frontmatter).

Shared sources (used by every platform's classifier):

  1. User-level skills: Glob pattern: $BASE/skills/*/SKILL.md

Android-specific sources:

  • None beyond the shared user-level glob. All curated Android skills are vendored inside android-dev itself (under <plugin>/skills/) and excluded via the dedup list in Step 2.

iOS-specific sources:

  1. Axiom plugin skills (optional):
    bash
    ls "$BASE/plugins/cache/axiom-marketplace/axiom/" | sort -V | tail -1
    • If the directory exists, use the highest semver version returned above and glob: $BASE/plugins/cache/axiom-marketplace/axiom/<version>/skills/*/SKILL.md
    • If it does not exist, record a "missing" warning for the iOS output file.

Design-specific sources:

  1. frontend-design plugin (optional):

    bash
    ls -t "$BASE/plugins/cache/claude-plugins-official/frontend-design/" | head -1
    • This plugin uses hash directories, not semver; ls -t | head -1 picks the newest by mtime — matches "the one currently installed" even when multiple hash dirs coexist.
    • If present: $BASE/plugins/cache/claude-plugins-official/frontend-design/<hash>/skills/*/SKILL.md
    • If absent, record a "missing" warning for the design output file.
  2. ui-ux-pro-max-skill plugin (optional):

    bash
    ls "$BASE/plugins/cache/ui-ux-pro-max-skill/ui-ux-pro-max/" | sort -V | tail -1
    • If present: $BASE/plugins/cache/ui-ux-pro-max-skill/ui-ux-pro-max/<version>/skills/*/SKILL.md
    • If absent, record a "missing" warning for the design output file.

Marketer-specific sources:

  1. frontend-slides plugin (optional):

    bash
    ls "$BASE/plugins/cache/frontend-slides/frontend-slides/" | sort -V | tail -1
    • Slide-oriented skills — included in the marketer index because presentations are a content/brand output (the slide-design curated skill orchestrates them).
    • If present: $BASE/plugins/cache/frontend-slides/frontend-slides/<version>/skills/*/SKILL.md
    • If absent, skip silently (no warning — this is bonus, not required).
  2. revealjs plugin (optional):

    bash
    ls "$BASE/plugins/cache/revealjs/revealjs/" | sort -V | tail -1
    • Same rationale as frontend-slides — alternative slide engine used by slide-design.
    • If present: $BASE/plugins/cache/revealjs/revealjs/<version>/skills/*/SKILL.md
    • If absent, skip silently.

Neo4j-specific sources:

  • None beyond the shared user-level glob. All curated Neo4j skills are vendored inside neo4j-dev itself.

Step 2: Read curated dedup lists

Read each agent's markdown from the solopreneur marketplace plugins. Find the ## Curated Skills section. Extract skill names from every bullet line that looks like:

- `<skill-name>` — <description>

The section is subdivided by source (Plugin-bundled / Third-party / …). Collect names from all subsections — they form the per-agent dedup blacklist and should not be re-included in that agent's extended index. Names may be bare (asc-release-flow) or namespaced (ios-dev:ios-patterns, axiom:axiom-ios-ui) — strip any <plugin>: prefix before comparing against candidate skill names.

Agents to read (each lives in its own sub-plugin):

  • ios-dev.md (from ios-dev) → iOS dedup list
  • android-dev.md (from android-dev) → Android dedup list
  • designer.md (from designer) → design dedup list
  • marketer.md (from marketer) → marketer dedup list
  • neo4j-dev.md (from neo4j-dev) → neo4j-dev dedup list

Locate each agent file via Glob (widens across any marketplace name the user chose at claude plugin marketplace add --name):

Glob: $BASE/plugins/cache/*/<plugin>/*/agents/<name>.md

If multiple versions coexist, take the highest semver match.

If you can't find an agent file, ask the user where that sub-plugin is installed and continue with an empty dedup list for that platform (the extended file will have duplicates with curated, which is fine — costs one extra entry per dup).

Step 3: Classify each candidate

For each skill not in a given platform's dedup list, judge from name + description whether it is relevant to that platform. Each candidate can be classified into multiple platforms (e.g., a SwiftUI-specific design skill belongs in both ios.md and design.md).

Be inclusive but not sloppy.

iOS classification
  • Yes: Swift / SwiftUI / UIKit / Xcode / iOS / macOS / iPadOS / watchOS / tvOS / visionOS / Apple frameworks (CoreData, AVFoundation, CoreLocation, etc.) / Apple toolchain (lldb, Instruments, asc CLI, App Store Connect)
  • No: web (React, Vue, Next.js, CSS), Android (Kotlin, Compose, Room), Python, LLM/agent frameworks, generic design tools, infra/devops, prose helpers
  • Borderline (e.g. cross-platform performance audit, generic git workflow): exclude. Curated catches must-haves; extended is best-effort.
Android classification
  • Yes: Kotlin / Jetpack Compose / Android Gradle / Hilt / Room / Retrofit / Coroutines / Flow / WorkManager / KMP-on-Android / Material Design (Material 3, Material You) / AGP / R8 / ProGuard / Android Studio / adb / gradlew / Google Play Console (gplay-*, signing, release flows, in-app purchases) / Android-specific testing (Roborazzi, Espresso, Compose UI testing)
  • No: web (React, Vue, Next.js, CSS), iOS (Swift, SwiftUI, Xcode, asc CLI), Python, LLM/agent frameworks, generic design tools, infra/devops, prose helpers
  • Borderline (e.g. cross-platform performance audit, generic git workflow): exclude. Curated catches must-haves; extended is best-effort.
Show full SKILL.md (477 more words)Show less
Design classification
  • Yes: visual design / typography / color / spacing / layout / motion / component styling / design systems / design review / critique / UX copy / information architecture / mockup generation / responsive design / accessibility when it's about visual contrast or type
  • No: pure frontend implementation (React hooks, Next.js routing) without design framing, QA testing, backend, iOS/Android development patterns that aren't design-focused, devops, presentation slides (these go to marketer)
  • Borderline (polish / audit / harden / normalize and other "action verb" skills): include only when the description explicitly mentions UI / visual / design. When in doubt, skip — curated catches the must-haves.
Marketer classification
  • Yes: brand / GTM / positioning / messaging / naming / copywriting / content strategy / social writing (X/Twitter, LinkedIn, Threads) / newsletter / email marketing / SEO copy / AI-pattern removal / presentation slides / pitch decks / community management / launch playbooks
  • No: pure dev (any language), pure design (visual systems without brand voice), infra, QA testing
  • Borderline: skills that touch both brand and design (e.g. brand-aware presentation builder) — include in marketer. Slide-design tooling specifically goes here, not design.
Neo4j-dev classification
  • Yes: Cypher (read or write) / Neo4j drivers (Java, Python, Go, .NET, JS) / graph schema / graph data modelling / MERGE patterns / MATCH patterns / index & constraint design / vector indexes on graph / APOC / GDS (Graph Data Science) / Neo4j Aura / cypher-shell / neo4j-admin / knowledge graph / GraphRAG / text2cypher
  • No: relational SQL without graph aspects, document DBs (Mongo, Firestore), vector DBs without a graph layer (Pinecone, Weaviate without Neo4j), generic prose
  • Borderline: GraphRAG skills that span LLM + graph — include only in neo4j-dev. If the skill is explicitly about prompt orchestration rather than graph retrieval, it can also land in a future ai-engineer index.

Step 4: Write output files

bash
mkdir -p "$BASE/solopreneur/skill-index"

Write one file per platform. Expand $BASE to its absolute resolved value in all Path: lines so that consumers (agents that Read this file) can open each path directly without re-resolving the env var.

$BASE/solopreneur/skill-index/ios.md
markdown
# iOS Skills Index — Extended
Generated: <ISO 8601 timestamp with timezone>
Config: <resolved absolute $BASE>
Classified by: <model name running this skill>

## Auto-classified user skills
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Auto-classified Axiom plugin skills (axiom-marketplace v<version>)
- `<name>` — <description>
  Path: <$BASE resolved>/plugins/cache/axiom-marketplace/axiom/<version>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Missing
<empty if all good; otherwise warnings, e.g.:>
- Axiom plugin not installed. Install with: `claude plugin install axiom`
  (https://github.com/CharlesWiltgen/Axiom)
$BASE/solopreneur/skill-index/android.md
markdown
# Android Skills Index — Extended
Generated: <ISO 8601 timestamp with timezone>
Config: <resolved absolute $BASE>
Classified by: <model name running this skill>

## Auto-classified user skills
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Missing
<empty if all good; otherwise warnings>
$BASE/solopreneur/skill-index/design.md
markdown
# Design Skills Index — Extended
Generated: <ISO 8601 timestamp with timezone>
Config: <resolved absolute $BASE>
Classified by: <model name running this skill>

## Auto-classified user skills
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Auto-classified frontend-design plugin skills (v<hash>)
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/plugins/cache/claude-plugins-official/frontend-design/<hash>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Auto-classified ui-ux-pro-max plugin skills (v<version>)
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/plugins/cache/ui-ux-pro-max-skill/ui-ux-pro-max/<version>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Missing
<warnings for any optional source not found>
$BASE/solopreneur/skill-index/marketer.md
markdown
# Marketer Skills Index — Extended
Generated: <ISO 8601 timestamp with timezone>
Config: <resolved absolute $BASE>
Classified by: <model name running this skill>

## Auto-classified user skills
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Auto-classified frontend-slides plugin skills (v<version>)
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/plugins/cache/frontend-slides/frontend-slides/<version>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Auto-classified revealjs plugin skills (v<version>)
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/plugins/cache/revealjs/revealjs/<version>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Missing
<empty if all good; otherwise warnings>
$BASE/solopreneur/skill-index/neo4j-dev.md
markdown
# Neo4j Skills Index — Extended
Generated: <ISO 8601 timestamp with timezone>
Config: <resolved absolute $BASE>
Classified by: <model name running this skill>

## Auto-classified user skills
- `<name>` — <one-line description trimmed to ~120 chars>
  Path: <$BASE resolved>/skills/<name>/SKILL.md
- ... (alphabetical by name)

## Missing
<empty if all good; otherwise warnings>

Skip a section entirely if it would be empty (except ## Missing — always emit it for transparency).

Step 5: Report to the user

Print a short summary (one Wrote line per file actually written — skip platforms that had no sources available):

Wrote <$BASE resolved>/solopreneur/skill-index/ios.md
Wrote <$BASE resolved>/solopreneur/skill-index/android.md
Wrote <$BASE resolved>/solopreneur/skill-index/design.md
Wrote <$BASE resolved>/solopreneur/skill-index/marketer.md
Wrote <$BASE resolved>/solopreneur/skill-index/neo4j-dev.md

iOS:
- N user skills classified as iOS-relevant
- M Axiom skills classified as iOS-relevant (axiom v<version>)
- K curated skills excluded from extended index
- Warnings: <list, or "none">

Android:
- N user skills classified as Android-relevant
- K curated skills excluded from extended index
- Warnings: <list, or "none">

Design:
- N user skills classified as design-relevant
- M frontend-design plugin skills classified as design-relevant (v<hash>)
- L ui-ux-pro-max plugin skills classified as design-relevant (v<version>)
- K curated skills excluded from extended index
- Warnings: <list, or "none">

Marketer:
- N user skills classified as marketer-relevant
- S frontend-slides plugin skills classified as marketer-relevant (v<version>)
- R revealjs plugin skills classified as marketer-relevant (v<version>)
- K curated skills excluded from extended index
- Warnings: <list, or "none">

Neo4j:
- N user skills classified as Neo4j-relevant
- K curated skills excluded from extended index
- Warnings: <list, or "none">

Notes

  • This skill is manual. There is no auto-rebuild on subagent invocation or on plugin update.
  • Output is per-machine and per-config. Each Claude Code config (CLAUDE_CONFIG_DIR) gets its own index because each config has its own set of installed plugins and user skills.
  • The plugin git repo only ships the curated lists inside each agents/<name>.md.
  • A single candidate skill can land in multiple platform indexes (design + iOS overlap is common for SwiftUI-focused visual skills; brand + design overlap exists too, but slide tooling specifically routes to marketer).
  • Classification is LLM judgment, not regex. Output may shift slightly between runs at the margin; that's acceptable because the curated list is the deterministic top-priority layer.
  • The ai-engineer agent does not yet read an extended index file. If its curated list grows beyond what's manageable, add an ai-engineer.md output here following the same pattern.

© hanamizuki, MIT. 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 skills/solopreneur/rebuild-skill-index of hanamizuki/solopreneur.

Open the folder on GitHubat commit f43f001

Compare with similar skills

Rebuild Skill Index 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.

Rebuild Skill Index compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rebuild Skill Index this skillhanamizuki/solopreneur152—~4kAutomated safety check: PassMIT
Engine Whats Newflutter/flutter180k—~978Automated safety check: PassBSD-3-Clause
App Store Screenshots GeneratorParthJadhav/app-store-screenshots7.2k—~16kAutomated safety check: PassMIT
Mobilerun Docs Referencedroidrun/mobilerun9.6k—~943Automated safety check: PassMIT
Rnn Codebasewix/react-native-navigation13k—~2kAutomated safety check: PassMIT
Building Native UICherryHQ/cherry-studio-app4k8 repos~2.6kAutomated safety check: PassMIT

Similar skills

  • Engine Whats New

    flutter/flutter

    Generates the "what's new" release summary and diff file for changes in the Flutter engine (//engine/src/flutter) between two releases (e.g., 3.47 vs 3.44).

    180k GitHub stars~978 tokensUpdated today
    MobileAuto-check passed
  • App Store Screenshots Generator

    ParthJadhav/app-store-screenshots

    Scaffolds a Next.js editor for designing App Store and Google Play screenshots as ads and exporting them at every required size, for iOS, Mac and Android.

    7.2k GitHub stars~16k tokensUpdated 2 days ago
    MobileAuto-check passed
  • Mobilerun Docs Reference

    droidrun/mobilerun

    Answers questions about Mobilerun, the LLM-agent framework for automating Android and iOS devices, by pointing the agent to the right page of its v5 documentation.

    9.6k GitHub stars~943 tokensUpdated yesterday
    MobileAuto-check passed
  • Rnn Codebase

    wix/react-native-navigation

    Official

    Navigate and work with the react-native-navigation (RNN) codebase.

    13k GitHub stars~2k tokensUpdated 5 days ago
    MobileAuto-check passed
  • Building Native UI

    CherryHQ/cherry-studio-app

    Complete guide for building beautiful apps with Expo Router.

    4k GitHub starsUsed in 8 repos~2.6k tokens
    MobileAuto-check passed
  • Sim Use

    lycorp-jp/sim-use

    Drive iOS Simulator, Android emulator/device, and physical iPhone/iPad screens for AI agents.

    1.4k GitHub stars~3.4k tokensUpdated 2 days ago
    MobileAuto-check passed

More from hanamizuki/solopreneur

All 31 skills in this repo
  • Preview

    hanamizuki/solopreneur

    Create an interactive HTML preview of any proposal, plan, idea, doc, brief, or spec and land it in the browsable local Preview Library by default (opens under file:// with a catalog sidebar and…

    152 GitHub stars~5.2k tokensUpdated 15 days ago
    Auto-check passed
  • iOS Patterns

    hanamizuki/solopreneur

    A skill your agent uses when building iOS/macOS apps with SwiftUI — covers localization (String Catalogs), date/time formatting, JSON date decoding, Previews, state management, sheet/navigation…

    152 GitHub stars~2.3k tokensUpdated 15 days ago
    Auto-check: notes
  • Linkedin Growth

    hanamizuki/solopreneur

    LinkedIn organic growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized 90-day growth plan.

    152 GitHub stars~3.7k tokensUpdated 15 days ago
    Auto-check passed
  • Perspective

    hanamizuki/solopreneur

    Switch perspectives to think through problems using the mental models of ten iconic thinkers: Elon Musk, Richard Feynman, Charlie Munger, Naval Ravikant, Steve Jobs, Nassim Taleb, Ilya Sutskever…

    152 GitHub stars~971 tokensUpdated 15 days ago
    Auto-check passed
  • Slide Design

    hanamizuki/solopreneur

    Create brand-aware presentations using frontend-slides or reveal.js.

    152 GitHub stars~3.9k tokensUpdated 15 days ago
    Auto-check passed
  • X Growth

    hanamizuki/solopreneur

    X/Twitter growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized growth plan.

    152 GitHub stars~3.8k tokensUpdated 15 days ago
    Auto-check passed

Works with

Categories

Questions about Rebuild Skill Index

What does Rebuild Skill Index do?

Rebuild the per-machine, per-config extended skill index used by platform subagents. Rebuild Skill Index is an agent skill from hanamizuki/solopreneur. Rebuild the per-machine, per-config extended skill index used by platform subagents.

When should I use Rebuild Skill Index?

Rebuild Skill Index fits situations like: the user says rebuild skill index; refresh skill index; after installing / removing platform-related skills.

How do I install Rebuild Skill Index in Claude Code?

Run `npx skills add hanamizuki/solopreneur --skill rebuild-skill-index -a claude-code`. Or copy the skill folder (skills/solopreneur/rebuild-skill-index in hanamizuki/solopreneur) into .claude/skills/rebuild-skill-index in your project. Claude Code loads it when a task matches its description.

How do I install Rebuild Skill Index in Codex?

Run `npx skills add hanamizuki/solopreneur --skill rebuild-skill-index -a codex`. Or copy the skill folder (skills/solopreneur/rebuild-skill-index in hanamizuki/solopreneur) into .agents/skills/rebuild-skill-index in your project. Codex loads it when a task matches its description.

Can I use Rebuild Skill Index 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 hanamizuki/solopreneur --skill rebuild-skill-index -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rebuild-skill-index, .gemini/skills/rebuild-skill-index, .github/skills/rebuild-skill-index and .opencode/skills/rebuild-skill-index in your project.

What does Rebuild Skill Index need to run?

Going by SKILL.md and its folder, Rebuild Skill Index needs the command-line tools its instructions call (claude).

Does Rebuild Skill Index access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Rebuild Skill Index 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 Rebuild Skill Index use?

Rebuild Skill Index is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Rebuild Skill Index use?

About 4k tokens (SKILL.md is roughly 16k 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 Rebuild Skill Index?

Skills that share tags, products or a category with Rebuild Skill Index: Engine Whats New (flutter/flutter, 180k stars), App Store Screenshots Generator (ParthJadhav/app-store-screenshots, 7.2k stars), Mobilerun Docs Reference (droidrun/mobilerun, 9.6k stars) and Rnn Codebase (wix/react-native-navigation, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rebuild Skill Index?

hanamizuki (a GitHub user) maintains it in hanamizuki/solopreneur, which has 152 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on September 26, 2026.

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