innovation

innovation is a skill for Claude Code from leewayworks/guochuang-gps. It costs 26 tokens per session (497 once invoked), scanned A, original, MIT.

A review skill for testing whether a Guochuang project’s technical claims are genuinely new, measurable, reproducible, and supported by fair comparisons.

In plain words
What is it for?
Use it to compare mechanisms and baselines, design validation tests, assess measured changes, and document the students’ contribution.
Why use it?
It separates a real improvement from a new label or unsupported claim and records the limits of the available evidence.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the guochuang-gps plugin — 9 skills shipped together

Good fit Use it to compare mechanisms and baselines, design validation tests, assess measured changes, and document the students’ contribution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leewayworks/guochuang-gps/innovation
Install

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.

Any agent
npx skills add leewayworks/guochuang-gps --skill innovation
Clone the repo
git clone --depth 1 https://github.com/leewayworks/guochuang-gps

Made for: Claude Code.

Or install guochuang-gps, the plugin that ships this one along with the rest of its 9 skills.

Wrote 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.

agentmods badge for innovation

README.md
[![agentmods](https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/innovation/github.svg)](https://agentmods.dev/skills/leewayworks/guochuang-gps/innovation)
Your own site
<a href="https://agentmods.dev/skills/leewayworks/guochuang-gps/innovation"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/innovation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for innovation

Your own site · 80×15
<a href="https://agentmods.dev/skills/leewayworks/guochuang-gps/innovation"><img src="https://agentmods.dev/badge/skills/leewayworks/guochuang-gps/innovation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00497
Opus 5 $0.00013 $0.00249
Sonnet 5 $0.00005 $0.00099
Haiku 4.5 $0.00003 $0.00050

Measured 12d ago against content hash 880161626056, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

innovation 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 12d 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.

skills/innovation/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Innovation

Apply the shared policies in gps-common. When saving a Markdown report, use the common project-name rule with topic 创新.

Test four separate questions: what changed, why it is difficult, what improved under which conditions, and what the students themselves contributed. Adding AI, a patent or a new label does not answer them.

Own this work

Own mechanism comparison, prior art, baseline fairness, test design, measured delta, reproducibility and technical limitations. positioning owns the final project advantage and selling-point ranking. Pass it evidence-bounded innovation candidates rather than taking over the whole narrative.

Build an innovation card

For each claim record:

claim_id, innovation_type, prior_art_or_baseline, changed_mechanism, measured_delta, metric_unit, condition, sample_or_repeats, evidence_ids, independent_source, student_role, known_limitation.

Classify an advantage candidate as:

  • owned: the team controls the mechanism or delivery capability and can explain the evidence;
  • conditional: credible only within stated conditions or maturity;
  • borrowed: mainly supplied by a laboratory, partner, adviser or licensed asset;
  • pseudo: publicity language without a bounded comparison and proof.

Use the validation ladder

  1. Mechanism: the team can explain what changed.
  2. Baseline: the comparison is named and fair.
  3. Measurement: metric, unit, condition, sample and repeats are recorded.
  4. Use: a real user, field trial or independent party observed the result.
  5. Transfer: the result survives beyond the selected example.

State the highest level the evidence reaches. A performance result is not itself an innovation; connect it to the changed mechanism and baseline.

Red-team the claim

Check for parameter tuning, borrowed IP, cherry-picked baselines, data leakage, missing controls, unsupported superlatives, weak student ownership and a result that cannot be reproduced. Treat first, internationally leading and similar claims as missing until an independent source defines the comparison scope.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 12d ago First seen · 46 lines · 26 tokens per session scan A 880161626056

Subscribe to this mod's changes

innovation is a skill published in the GitHub repository leewayworks/guochuang-gps (6 stars, last pushed 29d ago), licensed MIT. It adds 26 tokens to every session and 497 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens