Repository Analysis

JimLiu/baoyu-skills

4.4 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of JimLiu/baoyu-skills, a TypeScript project with 23,580 GitHub stars. SynthScan v2.0 examined 103,773 lines of code across 682 source files, recording 320 pattern matches distributed across 7 syntactic categories. The overall adjusted score of 4.4 places this repository in the Likely human-written band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

4.4
Adjusted Score
4.4
Raw Score
100%
Time Factor
2026-07-04
Last Push
23.6K
Stars
TypeScript
Language
103.8K
Lines of Code
682
Files
320
Pattern Hits
2026-07-14
Scan Date
0.01
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 9MEDIUM 2LOW 309

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 320 distinct pattern matches across 7 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Structural Annotation Overuse117 hits · 182 pts
SeverityFileLineSnippetContext
LOW.claude/skills/release-skills/SKILL.md46### Step 1: Detect Project ConfigurationCOMMENT
LOW.claude/skills/release-skills/SKILL.md118### Step 2: Analyze Changes Since Last TagCOMMENT
LOW.claude/skills/release-skills/SKILL.md146### Step 3: Determine Version BumpCOMMENT
LOW.claude/skills/release-skills/SKILL.md156### Step 4: Generate Multi-language ChangelogsCOMMENT
LOW.claude/skills/release-skills/SKILL.md246### Step 5: Group Changes by Skill/ModuleCOMMENT
LOW.claude/skills/release-skills/SKILL.md272### Step 6: Commit Each Skill/Module SeparatelyCOMMENT
LOW.claude/skills/release-skills/SKILL.md311### Step 7: Generate Changelog and Update VersionCOMMENT
LOW.claude/skills/release-skills/SKILL.md337### Step 8: User ConfirmationCOMMENT
LOW.claude/skills/release-skills/SKILL.md374### Step 9: Create Release Commit and Annotated TagCOMMENT
LOW.claude/skills/release-skills/SKILL.md403### Step 10: Publish Release Artifacts and GitHub ReleaseCOMMENT
LOWskills/baoyu-xhs-images/SKILL.md310### Step 0: Load EXTEND.md ⛔ BLOCKINGCOMMENT
LOWskills/baoyu-xhs-images/SKILL.md326### Step 1: Analyze Content → `analysis.md`COMMENT
LOWskills/baoyu-xhs-images/SKILL.md334### Step 2: Smart Confirm ⚠️ REQUIREDCOMMENT
LOWskills/baoyu-xhs-images/SKILL.md367### Step 3: Generate ImagesCOMMENT
LOWskills/baoyu-xhs-images/SKILL.md396### Step 4: Completion ReportCOMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md191### Step 0: Resolve Style Preset (if `--preset` used)COMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md202### Step 1: Load Style DefinitionCOMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md226### Step 2: Load LayoutCOMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md238### Step 3: Format ContentCOMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md246### Step 4: Add Watermark (if applicable)COMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md251### Step 5: Visual Consistency — Reference Image ChainCOMMENT
LOW…oyu-xhs-images/references/workflows/prompt-assembly.md261### Step 6: CombineCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts122 // Step 1: Find and click "写文章" buttonCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts161 // Step 2: Fill titleCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts217 // Step 3: Fill summary (导语)COMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts271 // Step 4: Insert HTML content into ProseMirror editorCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts385 // Step 5: Insert content imagesCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts706 // Step 6: Set cover imageCOMMENT
LOWskills/baoyu-infographic/SKILL.md212### Step 1: Setup & AnalyzeCOMMENT
LOWskills/baoyu-infographic/SKILL.md245### Step 2: Generate Structured Content → `structured-content.md`COMMENT
LOWskills/baoyu-infographic/SKILL.md257### Step 3: Recommend CombinationsCOMMENT
LOWskills/baoyu-infographic/SKILL.md267### Step 4: Confirm OptionsCOMMENT
LOWskills/baoyu-infographic/SKILL.md280### Step 5: Generate Prompt → `prompts/infographic.md`COMMENT
LOWskills/baoyu-infographic/SKILL.md295### Step 6: Generate ImageCOMMENT
LOWskills/baoyu-infographic/SKILL.md311### Step 7: Output SummaryCOMMENT
LOWskills/baoyu-cover-image/SKILL.md152### Step 0: Load Preferences ⛔ BLOCKINGCOMMENT
LOWskills/baoyu-cover-image/SKILL.md169### Step 1: Analyze ContentCOMMENT
LOWskills/baoyu-cover-image/SKILL.md187### Step 2: Confirm Options ⚠️COMMENT
LOWskills/baoyu-cover-image/SKILL.md200### Step 3: Create PromptCOMMENT
LOWskills/baoyu-cover-image/SKILL.md211### Step 4: Generate ImageCOMMENT
LOWskills/baoyu-cover-image/SKILL.md224### Step 5: Completion ReportCOMMENT
LOW…oyu-cover-image/references/workflow/confirm-options.md1# Step 2: Confirm OptionsCOMMENT
LOW…oyu-cover-image/references/workflow/prompt-template.md1# Step 3: Prompt TemplateCOMMENT
LOW…oyu-cover-image/references/workflow/prompt-template.md177### Step 1: Analyze ReferencesCOMMENT
LOW…oyu-cover-image/references/workflow/prompt-template.md185### Step 2: Embed in Prompt ⚠️ CRITICALCOMMENT
LOWskills/baoyu-wechat-summary/SKILL.md104### Step 1: Parse the user's requestCOMMENT
LOWskills/baoyu-wechat-summary/SKILL.md125### Step 2: Find the group + resolve folder pathCOMMENT
LOWskills/baoyu-wechat-summary/SKILL.md157### Step 3: Fetch messagesCOMMENT
LOWskills/baoyu-wechat-summary/SKILL.md369### Step 7: Save the digest file(s)COMMENT
LOWskills/baoyu-wechat-summary/SKILL.md383### Step 8: Save history (two files)COMMENT
LOWskills/baoyu-wechat-summary/SKILL.md457### Step 9: Backfill (user-triggered)COMMENT
LOWskills/baoyu-post-to-wechat/SKILL.md140### Step 0: Load PreferencesCOMMENT
LOWskills/baoyu-post-to-wechat/SKILL.md144### Step 1: Determine Input TypeCOMMENT
LOWskills/baoyu-post-to-wechat/SKILL.md158### Step 2: Select Publishing Method and ConfigureCOMMENT
LOWskills/baoyu-post-to-wechat/SKILL.md172### Step 3: Resolve Theme/Color and Validate MetadataCOMMENT
LOWskills/baoyu-post-to-wechat/SKILL.md189### Step 4: PublishCOMMENT
LOWskills/baoyu-post-to-wechat/SKILL.md225### Step 5: Completion ReportCOMMENT
LOWskills/baoyu-format-markdown/SKILL.md67### Step 1: Read & Detect Content TypeCOMMENT
LOWskills/baoyu-format-markdown/SKILL.md103### Step 2: Analyze Content (Reader's Perspective)COMMENT
LOWskills/baoyu-format-markdown/SKILL.md156### Step 3: Check/Create Frontmatter, Title & SummaryCOMMENT
57 more matches not shown…
Hyper-Verbose Identifiers175 hits · 180 pts
SeverityFileLineSnippetContext
LOWpackages/baoyu-chrome-cdp/src/index.ts137export function resolveSharedChromeProfileDir(options: ResolveSharedChromeProfileDirOptions = {}): string {CODE
LOWpackages/baoyu-chrome-cdp/src/index.ts211export async function findExistingChromeDebugPort(options: FindExistingChromeDebugPortOptions): Promise<number | null> {CODE
LOWpackages/baoyu-chrome-cdp/src/index.ts237export function getDefaultChromeUserDataDirs(channels: ChromeChannel[] = ["stable"]): string[] {CODE
LOWpackages/baoyu-chrome-cdp/src/index.ts277export async function discoverRunningChromeDebugPort(options: DiscoverRunningChromeOptions = {}): Promise<DiscoveredChroCODE
LOWpackages/baoyu-fetch/src/adapters/youtube/utils.ts123export function parseYouTubeDescriptionChapters(description?: string | null): YouTubeChapter[] {CODE
LOWpackages/baoyu-fetch/src/adapters/youtube/utils.ts169function renderDescriptionMarkdown(description: string): string {CODE
LOWpackages/baoyu-fetch/src/adapters/youtube/utils.ts183export function renderYouTubeTranscriptMarkdown({CODE
LOWpackages/baoyu-fetch/src/adapters/youtube/utils.ts238export function buildYouTubeThumbnailCandidates(videoId: string, listedUrls: string[]): string[] {CODE
LOWpackages/baoyu-fetch/src/adapters/youtube/transcript.ts101export async function extractYouTubeTranscriptDocument(CODE
LOWpackages/baoyu-fetch/src/adapters/hn/index.ts239function extractUnixSecondsFromAge(element: Element | null): number | undefined {CODE
LOWpackages/baoyu-fetch/src/adapters/x/article.ts407export function extractArticleDocumentFromPayload(CODE
LOWpackages/baoyu-fetch/src/adapters/x/payloads.ts4export function getRelevantXThreadEntries(context: AdapterContext) {CODE
LOWpackages/baoyu-fetch/src/adapters/x/payloads.ts17export async function prefetchRelevantXThreadBodies(context: AdapterContext): Promise<void> {CODE
LOWpackages/baoyu-fetch/src/adapters/x/shared.ts259function getVideoVariantContentType(variant: JsonObject): string {CODE
LOWpackages/baoyu-fetch/src/adapters/x/shared.ts264export function resolveBestXVideoVariantUrl(mediaInfo: unknown): string | undefined {CODE
LOWpackages/baoyu-fetch/src/adapters/x/session.ts28export function hasRequiredXSessionCookies(cookieMap: Record<string, string>): boolean {CODE
LOWpackages/baoyu-fetch/src/adapters/x/single.ts4export function extractSingleTweetDocumentFromPayload(CODE
LOWpackages/baoyu-fetch/src/adapters/x/index.ts24function extractDocumentFromPayloads(CODE
LOWpackages/baoyu-fetch/src/adapters/x/thread.ts64function collectTweetFromItemContent(CODE
LOWpackages/baoyu-fetch/src/adapters/x/thread.ts232export function extractThreadTweetsFromPayloads(CODE
LOWpackages/baoyu-fetch/src/adapters/x/thread.ts285export function extractThreadDocumentFromPayloads(CODE
LOWpackages/baoyu-fetch/src/browser/page-snapshot.ts101export async function captureNormalizedPageSnapshot(CODE
LOWpackages/baoyu-fetch/src/browser/interaction-gates.ts16export function detectInteractionGateFromSnapshot(snapshot: GateSnapshot): WaitForInteractionRequest | null {CODE
LOWpackages/baoyu-fetch/src/browser/profile.ts34export function resolveSharedChromeProfileDir(CODE
LOWpackages/baoyu-fetch/src/browser/profile.ts70export function shouldRetryChromeLaunchRecovery(options: {CODE
LOWpackages/baoyu-fetch/src/browser/profile.ts77export function findChromeProcessUsingProfile(profileDir: string): boolean {CODE
LOWpackages/baoyu-fetch/src/browser/profile.ts163export async function findExistingChromeDebugPort(CODE
LOWpackages/baoyu-fetch/src/commands/convert.ts87export function shouldKeepBrowserOpenAfterInteraction(options: {CODE
LOWpackages/baoyu-fetch/src/commands/convert.ts94export function shouldAutoContinueForceWait(CODE
LOWpackages/baoyu-fetch/src/commands/convert.ts194async function isInteractionSessionReady(CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts147export function extractTitleFromMarkdownDocument(markdown: string): string | undefined {CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts476function shouldCompareWithFallback(markdown: string): boolean {CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts481function hasMeaningfulMarkdownStructure(markdown: string): boolean {CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts496function shouldTryRemoteMarkdownFallback(CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts508function shouldPreferRemoteMarkdown(CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts524function buildRemoteFallbackReason(current: HtmlToMarkdownResult, html: string): string {CODE
LOWpackages/baoyu-fetch/src/extract/html-to-markdown.ts629function convertHtmlFragmentToMarkdown(html: string): string {CODE
LOWpackages/baoyu-fetch/src/media/media-utils.ts71export function resolveExtensionFromContentType(contentType: string): string | undefined {CODE
LOWpackages/baoyu-fetch/src/media/media-utils.ts75export function resolveKindFromContentType(contentType: string): MediaKind | undefined {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts95function formatMarkdownDestination(url: string): string {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts120function isParagraphWithSingleText(node: MarkdownAstNode | undefined, expectedValue: string): boolean {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts129function getSingleImageFromParagraph(node: MarkdownAstNode | undefined): MarkdownAstNode | null {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts137function extractBrokenLinkedImageDestination(node: MarkdownAstNode | undefined): string | null {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts161function collectLinkedImageReplacements(CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts184function collectBrokenLinkedImageReplacements(CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts241function normalizeLinkedImageMarkdown(markdown: string): string {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts255export function normalizeMarkdownMediaLinks(markdown: string): string {CODE
LOWpackages/baoyu-fetch/src/media/markdown-media.ts409export function rewriteMarkdownMediaLinks(CODE
LOWpackages/baoyu-md/src/mermaid-preprocess.ts48export async function preprocessMermaidInMarkdown(CODE
LOWpackages/baoyu-md/src/images.ts17export function replaceMarkdownImagesWithPlaceholders(CODE
LOWpackages/baoyu-md/src/images.ts150function parseObsidianImageWikilink(target: string): {CODE
LOWpackages/baoyu-md/src/images.ts167function hasExplicitImageExtension(value: string): boolean {CODE
LOWpackages/baoyu-md/src/images.ts261function buildAttachmentFallbackPath(imagePath: string, baseDir: string): string | undefined {CODE
LOWpackages/baoyu-md/src/document.ts74export function buildMarkdownDocumentMeta(CODE
LOWpackages/baoyu-md/src/renderer.ts91function parseFrontMatterAndContent(markdownText: string): ParseResult {CODE
LOWskills/baoyu-youtube-transcript/scripts/transcript.ts112function splitSnippetAtPunctuation(snippet: Snippet): { text: string; start: number; end: number }[] {CODE
LOWskills/baoyu-youtube-transcript/scripts/youtube.ts236export async function fetchTranscriptWithFallback(CODE
LOWskills/baoyu-youtube-transcript/scripts/youtube.ts327export function buildTranscriptListFromYtDlp(info: YtDlpInfo): TranscriptInfo[] {CODE
LOWskills/baoyu-post-to-weibo/scripts/weibo-utils.ts67export async function findExistingChromeDebugPort(profileDir: string): Promise<number | null> {CODE
LOWskills/baoyu-post-to-weibo/scripts/copy-to-clipboard.ts128function getMacSwiftClipboardSource(): string {CODE
115 more matches not shown…
Cross-Language Confusion (JS/TS)9 hits · 65 pts
SeverityFileLineSnippetContext
HIGHpackages/baoyu-fetch/src/utils/logger.ts15 print("info", message);CODE
HIGHpackages/baoyu-fetch/src/utils/logger.ts18 print("warn", message);CODE
HIGHpackages/baoyu-fetch/src/utils/logger.ts21 print("error", message);CODE
HIGHpackages/baoyu-fetch/src/utils/logger.ts25 print("debug", message);CODE
HIGH…ls/baoyu-danger-x-to-markdown/scripts/markdown.test.ts52print('hello from x article')CODE
HIGH…ills/baoyu-url-to-markdown/scripts/lib/utils/logger.ts15 print("info", message);CODE
HIGH…ills/baoyu-url-to-markdown/scripts/lib/utils/logger.ts18 print("warn", message);CODE
HIGH…ills/baoyu-url-to-markdown/scripts/lib/utils/logger.ts21 print("error", message);CODE
HIGH…ills/baoyu-url-to-markdown/scripts/lib/utils/logger.ts25 print("debug", message);CODE
Verbosity Indicators8 hits · 14 pts
SeverityFileLineSnippetContext
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts122 // Step 1: Find and click "写文章" buttonCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts161 // Step 2: Fill titleCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts217 // Step 3: Fill summary (导语)COMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts271 // Step 4: Insert HTML content into ProseMirror editorCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts385 // Step 5: Insert content imagesCOMMENT
LOWskills/baoyu-post-to-weibo/scripts/weibo-article.ts706 // Step 6: Set cover imageCOMMENT
LOWskills/baoyu-image-gen/scripts/providers/jimeng.ts459 // Step 1: Submit taskCOMMENT
LOWskills/baoyu-image-gen/scripts/providers/jimeng.ts462 // Step 2: Poll for result (returns image data directly)COMMENT
Fake / Example Data7 hits · 7 pts
SeverityFileLineSnippetContext
LOW…ls/baoyu-infographic/references/styles/ui-wireframe.md23- Placeholder "Lorem ipsum"CODE
LOWskills/baoyu-post-to-wechat/scripts/md-to-wechat.ts132 "placeholder": "WECHATIMGPH_1",CODE
LOWskills/baoyu-post-to-x/references/articles.md144 "placeholder": "XIMGPH_1",CODE
LOW…ls/baoyu-image-gen/scripts/providers/dashscope.test.ts267 useEnv(t, { DASHSCOPE_API_KEY: "fake-key" });CODE
LOW…ls/baoyu-image-gen/scripts/providers/dashscope.test.ts306 useEnv(t, { DASHSCOPE_API_KEY: "fake-key" });CODE
LOW…ls/baoyu-image-gen/scripts/providers/dashscope.test.ts344 useEnv(t, { DASHSCOPE_API_KEY: "fake-key" });CODE
LOWskills/baoyu-markdown-to-html/SKILL.md194 "placeholder": "MDTOHTMLIMGPH_1",CODE
Modern AI Meta-Vocabulary2 hits · 5 pts
SeverityFileLineSnippetContext
MEDIUMskills/baoyu-wechat-summary/SKILL.md3description: Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://gitCODE
MEDIUMskills/baoyu-wechat-summary/references/profiles.md234## 5. Privacy guardrailsCOMMENT
Over-Commented Block2 hits · 2 pts
SeverityFileLineSnippetContext
LOWpackages/baoyu-md/src/code-themes/agate.min.css1pre code.hljs{display:block;overflow-x:auto;padding:1em}code.hljs{padding:3px 5px}/*!COMMENT
LOWskills/baoyu-post-to-x/scripts/md-to-html.ts141// `marked`'s emphasis tokenizer treats a closing `**`/`*` directly followed by aCOMMENT