Agent skill

Navigator

by leewayworks in leewayworks/guochuang-gps

A skill your agent uses when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan.

MITAuto-check passedBusiness, Finance & HR

Install Navigator

skills CLI
$ npx skills add leewayworks/guochuang-gps --skill navigator -a claude-code

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

GitHub CLI
$ gh skill install leewayworks/guochuang-gps navigator --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/leewayworks/guochuang-gps.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/navigator .claude/skills/navigator && 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
navigator
GitHub stars
106
Token cost
~1.3k tokens
SKILL.md length
668 words
Files
4 (incl. references)
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan.

  • Works in 4 steps: Inventory the files in scope. Record… → Extract only supported facts about… → Separate verified, user_asserted,… → …
  • A user asks for a GPS review of a Guochuang project folder
  • SKILL.md covers Choose a mode, Inspect before asking, Route by primary intent and Lock rules and evidence, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Navigator is an agent skill from leewayworks/guochuang-gps. Use when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/material-schema.md`, `references/rubrics-2025.json` and `references/rules-2026.md`).

It sits in Business, Finance & HR. The repository describes itself as: GPS (Guochuang Preparation Skills) — A multi-agent AI toolkit for competition planning, proposal review, pitch deck optimization, defense coaching, and award-level assessment. The licence is MIT.

When your agent uses it

  • A user asks for a GPS review of a Guochuang project folder
  • Wants a readiness diagnosis and next-step plan

Example prompts

  • “/navigator”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Inventory the files in scope. Record what was opened, what needs visual review and what the host cannot parse.
  2. Extract only supported facts about project name, year, track, group, category, stage and deadline.
  3. Separate verified, user_asserted, inferred_for_routing and unknown.
  4. Ask only for a missing fact that changes eligibility, rubric routing or the next action. Continue read-only inspection while an answer is…

What it can do on your machine

Read from SKILL.md and the folder at commit 07892d1. 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

Navigator loads about 1.3k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 668 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.1k

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 leewayworks/guochuang-gps at commit 07892d1, republished under its MIT licence (© leewayworks). 668 words, ~1,276 tokens.

Download SKILL.mdSave it as .claude/skills/navigator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
navigator
description
Use when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan.

GPS navigator

Act as the user-facing coordinator for GPS. Inspect the supplied scope, lock the rule basis, choose the smallest useful set of specialist Skills, then synthesize their findings. Do not replace specialist judgment with a generic review.

Apply the shared policies in gps-common. Load only the references needed for the current route.

Choose a mode

ModeUse it whenOutput
Full diagnosisThe user supplies a project folder or asks for an overall strategy, advantages and rubric gapsEleven-section report below
Quick triageMaterials are thin or the deadline is closeRule basis, strongest supported point, largest blocker and next three actions
Narrow specialistThe user asks only about positioning, innovation, market, evidence, proposal, deck or defenseThe owning Skill's adaptive contract, without padding it into a full report

Inspect before asking

  1. Inventory the files in scope. Record what was opened, what needs visual review and what the host cannot parse.
  2. Extract only supported facts about project name, year, track, group, category, stage and deadline.
  3. Separate verified, user_asserted, inferred_for_routing and unknown.
  4. Ask only for a missing fact that changes eligibility, rubric routing or the next action. Continue read-only inspection while an answer is pending.

Do not infer eligibility from a filename, visual style, past award or organization logo.

Route by primary intent

Primary intentOwnerRequired companion
Overall review, rule lock, synthesisnavigatorevidence
Essence, core advantages, selling points, innovation framing, market opportunitypositioningevidence; add innovation or business when needed
Technical novelty, baseline and validationinnovationevidence
Customer, transaction, finance and scalebusinessevidence
Claim audit and contradictionsevidencenone
Project bookproposalevidence when claims are reviewed
Slidesdeckevidence when claims are reviewed
Questions and rehearsaldefenseevidence for answer cards

If two Skills could own the task, route by the requested deliverable. positioning owns what the project should be known for. innovation tests a technical claim. business tests the transaction and delivery logic.

Lock rules and evidence

Read references/rules-2026.md for the current notice boundary and references/rubrics-2025.json for the seven supported scoring cards. Resolve year + track + group before producing rubric alignment.

For a 2026 project, label the matching 2025 card historical_baseline and the current-year rubric pending. For 2025, label that card official_hard. If the route is unknown, ask a routing question and do not score.

Normalize materials with references/material-schema.md. A local evidence path earns no credit until the file exists relative to the project data file and is inspected. A number also needs a claim link and locator or condition.

Run scripts/gps_score.py only after the route and normalized fields are available. Report rubric_alignment_score, GPS readiness, evidence coverage, gates, caps and source status separately. These are preparation diagnostics, not judging results.

Show full SKILL.md (220 more words)Show less

Full diagnosis contract

Use exactly these headings for a full diagnosis:

  1. Snapshot
  2. Eligibility and rubric basis
  3. Project essence
  4. Core advantages
  5. Top 3 selling points
  6. Innovation and opportunity
  7. Rubric gap matrix
  8. MAP ledger summary
  9. GOLD gap
  10. Next 3 actions
  11. Open questions

Tag each material conclusion as verified, supported, conditional, hypothesis, missing or contradicted. If fewer than three selling points are defensible, show the empty slots and the evidence needed to fill them.

Each next action uses owner + artifact + due date + acceptance check. If the deadline is within 72 hours, prefer a rescue plan that protects eligibility, the strongest claim and the answer evidence.

Saved report naming

Follow the saved Markdown report rules in gps-common. Use the full-diagnosis, quick-triage or specialist filename for the selected mode. A user-supplied filename or destination always takes precedence.

Hard stops

  • Do not create a number, customer result, patent status, experiment result or team contribution.
  • Do not call a performance result an innovation without the changed mechanism and comparison baseline.
  • Do not turn a historical case, old scoring card or training slide into a current rule.
  • Do not use award names as readiness bands or claim that GPS predicts an award.
  • Do not copy or commit user project materials without explicit permission.

References: references/rules-2026.md, references/material-schema.md, references/rubrics-2025.json.

© leewayworks, MIT. 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 3 other files (references) in skills/navigator of leewayworks/guochuang-gps.

  • SKILL.md
  • references/material-schema.md
  • references/rubrics-2025.json
  • references/rules-2026.md

Open the folder on GitHubat commit 07892d1

Compare with similar skills

Navigator 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.

Navigator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Navigator this skillleewayworks/guochuang-gps106—~1.3kAutomated safety check: PassMIT
Technical Analysttradermonty/claude-trading-skills3k4 repos~4.6kAutomated safety check: PassMIT
Theme Detectortradermonty/claude-trading-skills3k2 repos~4.9kAutomated safety check: PassMIT
Creating Financial ModelsChen-zexi/open-ptc-agent7293 repos~1.3kAutomated safety check: PassMIT
Stock APIzhangxiangliang/stock-api2k—~507Automated safety check: PassMIT
Itr Walakaranb192/itr-wala871—~3.6kAutomated safety check: PassMIT

Similar skills

  • Technical Analyst

    tradermonty/claude-trading-skills

    This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.

    3k GitHub starsUsed in 4 repos~4.6k tokens
    Business, Finance & HRAuto-check passed
  • Theme Detector

    tradermonty/claude-trading-skills

    Detect and analyze trending market themes across sectors. An agent skill from tradermonty/claude-trading-skills.

    3k GitHub starsUsed in 2 repos~4.9k tokens
    Business, Finance & HRAuto-check passed
  • Creating Financial Models

    Chen-zexi/open-ptc-agent

    This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

    729 GitHub starsUsed in 3 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Stock API

    zhangxiangliang/stock-api

    Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.

    2k GitHub stars~507 tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Itr Wala

    karanb192/itr-wala

    File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27.

    871 GitHub stars~3.6k tokensUpdated 6 days ago
    Business, Finance & HRAuto-check passed
  • Tushare Data

    zillionare/zillionare

    面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

    322 GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed

More from leewayworks/guochuang-gps

All 9 skills in this repo
  • Deck

    leewayworks/guochuang-gps

    A skill your agent uses when outlining, reviewing, or rehearsing a Guochuang pitch deck, project-book presentation, slide narrative, or visual evidence sequence.

    106 GitHub stars~546 tokensUpdated 1 mo ago
    Auto-check passed
  • Gps Common

    leewayworks/guochuang-gps

    A skill your agent uses when routing, sourcing, or wording a GPS diagnosis that involves track alignment, evidence status, historical comparisons, or readiness conclusions.

    106 GitHub stars~618 tokensUpdated 1 mo ago
    Auto-check passed
  • Positioning

    leewayworks/guochuang-gps

    A skill your agent uses when a Guochuang project needs its essence, core advantages, three selling points, innovation framing, market or beneficiary opportunity, historical-method comparison, or…

    106 GitHub stars~773 tokensUpdated 1 mo ago
    Auto-check passed
  • Proposal

    leewayworks/guochuang-gps

    A skill your agent uses when drafting, restructuring, or auditing a Chinese International College Students' Innovation Competition project book, business plan, executive summary, or claim-to-section…

    106 GitHub stars~661 tokensUpdated 1 mo ago
    Auto-check passed
  • Business

    leewayworks/guochuang-gps

    A skill your agent uses when a Guochuang project needs its customer, market, transaction, pricing, finance, delivery, scale, risk or social-value logic examined.

    106 GitHub stars~612 tokensUpdated 1 mo ago
    Auto-check passed
  • Defense

    leewayworks/guochuang-gps

    A skill your agent uses when simulating Guochuang roadshows, expert questions, rebuttals, speaker scripts, or a final readiness drill for school, provincial, or national rounds.

    106 GitHub stars~533 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Navigator

What does Navigator do?

A skill your agent uses when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan. Navigator is an agent skill from leewayworks/guochuang-gps. Use when a user asks for a GPS review of a Guochuang project folder or materials, needs track or group routing, or wants a readiness diagnosis and next-step plan.

When should I use Navigator?

Navigator fits situations like: A user asks for a GPS review of a Guochuang project folder; wants a readiness diagnosis and next-step plan.

How do I install Navigator in Claude Code?

Run `npx skills add leewayworks/guochuang-gps --skill navigator -a claude-code`. Or copy the skill folder (skills/navigator in leewayworks/guochuang-gps) into .claude/skills/navigator in your project. Claude Code loads it when a task matches its description.

How do I install Navigator in Codex?

Run `npx skills add leewayworks/guochuang-gps --skill navigator -a codex`. Or copy the skill folder (skills/navigator in leewayworks/guochuang-gps) into .agents/skills/navigator in your project. Codex loads it when a task matches its description.

Can I use Navigator 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 leewayworks/guochuang-gps --skill navigator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/navigator, .gemini/skills/navigator, .github/skills/navigator and .opencode/skills/navigator in your project.

What does Navigator need to run?

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

Does Navigator 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 Navigator 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 Navigator use?

Navigator 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 Navigator use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 3.8k tokens, read only when the agent opens those files.

What are the alternatives to Navigator?

Skills that share tags, products or a category with Navigator: Technical Analyst (tradermonty/claude-trading-skills, 3k stars), Theme Detector (tradermonty/claude-trading-skills, 3k stars), Creating Financial Models (Chen-zexi/open-ptc-agent, 729 stars) and Stock API (zhangxiangliang/stock-api, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Navigator?

leewayworks (a GitHub user) maintains it in leewayworks/guochuang-gps, which has 106 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 13, 2026.

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