Home / jnMetaCode / superpowers-zh
AI Slop Code RIsk Monitor

jnMetaCode/superpowers-zh

🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

5.5 Moderate pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for jnMetaCode/superpowers-zh, a JavaScript project with 8,292 GitHub stars. SynthScan examined 31,217 lines of code across 208 source files, recording 96 pattern matches distributed across 12 syntactic categories. The legacy adjusted pattern signal is 5.5 (Moderate pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

5.5
Adjusted Signal
5.5
Raw Pattern Score
100%
Time Factor
2026-10-08
Last Push
8.3K
Stars
JavaScript
Language
31.2K
Lines of Code
208
Files
96
Pattern Hits
2026-10-12
Scan Date
0.00
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 17.4/100 · LOW

Can maintainers explain intent, assumptions, and trade-offs? 76 finding(s).

Hallucinated Dependency & Supply Chain Risk 0.6/100 · LOW

Are imports declared and package/API names verified? 4 finding(s).

Agent Over-Engineering Ratio 9.9/100 · LOW

Are wrappers, guards, and repeated structures necessary? 34 finding(s).

PR Review Velocity Impact 22.5/100 · LOW

Which changes need focused human review? 96 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 0HIGH 1MEDIUM 29LOW 66

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 96 distinct pattern matches across 12 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. 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 configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Decorative Section Separators13 hits · 39 pts
SeverityFileLineSnippetContext
MEDIUMscripts/audit.sh52#==============================================================================COMMENT
MEDIUMscripts/audit.sh54#==============================================================================COMMENT
MEDIUMscripts/audit.sh112#==============================================================================COMMENT
MEDIUMscripts/audit.sh115#==============================================================================COMMENT
MEDIUMscripts/audit.sh169#==============================================================================COMMENT
MEDIUMscripts/audit.sh171#==============================================================================COMMENT
MEDIUMscripts/audit.sh347#==============================================================================COMMENT
MEDIUMscripts/audit.sh349#==============================================================================COMMENT
MEDIUMscripts/audit.sh399#==============================================================================COMMENT
MEDIUMscripts/audit.sh401#==============================================================================COMMENT
MEDIUMscripts/audit.sh505#==============================================================================COMMENT
MEDIUMscripts/audit.sh507#==============================================================================COMMENT
MEDIUMscripts/audit.sh567#==============================================================================COMMENT
Self-Referential Comments10 hits · 30 pts
SeverityFileLineSnippetContext
MEDIUMtests/claude-code/test-document-review-system.sh31# Create a spec document WITH INTENTIONAL ERRORS for the reviewer to catchCOMMENT
MEDIUMtests/claude-code/test-helpers.sh128# Create a temporary test project directoryCOMMENT
MEDIUMtests/claude-code/test-helpers.sh144# Create a simple plan file for testingCOMMENT
MEDIUM…e-code/test-subagent-driven-development-integration.sh47# Create a simple implementation planCOMMENT
MEDIUMtests/explicit-skill-requests/run-test.sh44# Create a minimal project directory for the testCOMMENT
MEDIUMtests/explicit-skill-requests/run-test.sh48# Create a dummy plan file for mid-conversation testsCOMMENT
MEDIUMtests/explicit-skill-requests/run-haiku-test.sh33# Create a dummy plan fileCOMMENT
MEDIUMtests/explicit-skill-requests/run-multiturn-test.sh29# Create a dummy plan fileCOMMENT
MEDIUM…ts/explicit-skill-requests/run-claude-describes-sdd.sh23# Create a planCOMMENT
MEDIUMtests/opencode/setup.sh54# Create a project directory for project-level skill testsCOMMENT
Over-Commented Block24 hits · 24 pts
SeverityFileLineSnippetContext
LOWindex.js1// Root entrypoint for OpenCode v2 directory-form plugin registration.COMMENT
LOWbin/superpowers-zh.js41const SKILLS_SRC = resolve(__dirname, '..', 'skills');COMMENT
LOWbin/superpowers-zh.js61 // Codex 各层级扫的都是 .agents/skills，**从不扫 .codex/skills**。官方文档COMMENT
LOWbin/superpowers-zh.js81 // custom 默认被 gitignore，无需任何配置。容器内挂到 /mnt/skills/。COMMENT
LOWbin/superpowers-zh.js101 已经由 Trae 这一条覆盖，请直接用：COMMENT
LOWbin/superpowers-zh.js121 // 项目级：.windsurf/skills/<skill-name>/COMMENT
LOWbin/superpowers-zh.js141 { name: 'OpenCode', dir: '.opencode/skills', detect: '.opencode', global: { dir: '.COMMENT
LOWbin/superpowers-zh.js161 // 记忆文件 ~/.codebuddy/CODEBUDDY.md 与 项目根 CODEBUDDY.md（两处等价）COMMENT
LOWbin/superpowers-zh.js181 // docs 里写明了别重复装，否则 Crush 会加载两份。COMMENT
LOWbin/superpowers-zh.js1301 return realpathSync(p) === realpathSync(home);COMMENT
LOW.opencode/plugins/superpowers.js141};COMMENT
LOWtests/claude-code/test-worktree-native-preference.sh1#!/usr/bin/env bashCOMMENT
LOWtests/brainstorm-server/windows-lifecycle.test.sh1#!/usr/bin/env bashCOMMENT
LOWscripts/make-og-image.sh1#!/usr/bin/env bashCOMMENT
LOWscripts/verify-release.sh1#!/usr/bin/env bashCOMMENT
LOWscripts/verify-release.sh281if curl -sS -o /dev/null --max-time 5 https://github.com 2>/dev/null; thenCOMMENT
LOWscripts/audit.sh1#!/usr/bin/env bashCOMMENT
LOWscripts/audit.sh261 # 本插件在 .claude-plugin/plugin.json 里叫 superpowers-zh，Claude Code 按COMMENT
LOWscripts/audit.sh361# 4b. Skill 间引用完整性COMMENT
LOWscripts/audit.sh401#==============================================================================COMMENT
LOWscripts/audit.sh501if [ "$tools_tested" = "$EXPECTED_TOOLS" ]; then ok; elseCOMMENT
LOW…ystematic-debugging/condition-based-waiting-example.ts141// ---------------COMMENT
LOWskills/chinese-code-review/SKILL.md101COMMENT
LOWskills/brainstorming/scripts/start-server.sh1#!/usr/bin/env bashCOMMENT
Redundant / Tautological Comments16 hits · 24 pts
SeverityFileLineSnippetContext
LOWtests/claude-code/test-helpers.sh31# Check if output contains a patternCOMMENT
LOWtests/claude-code/test-helpers.sh50# Check if output does NOT contain a patternCOMMENT
LOWtests/claude-code/test-helpers.sh69# Check if output matches a countCOMMENT
LOWtests/claude-code/test-helpers.sh95# Check if pattern A appears before pattern BCOMMENT
LOWtests/claude-code/run-skill-tests.sh18# Check if Claude Code is availableCOMMENT
LOWtests/explicit-skill-requests/run-test.sh81# Check if skill was triggered (look for Skill tool invocation)COMMENT
LOWtests/explicit-skill-requests/run-test.sh97# Check if Claude took action BEFORE invoking the skill (the failure mode)COMMENT
LOWtests/explicit-skill-requests/run-test.sh105 # Check if any non-Skill, non-system tools were invoked before the first Skill invocationCOMMENT
LOWtests/explicit-skill-requests/run-multiturn-test.sh89# Check if skill was triggered in Turn 3COMMENT
LOWtests/skill-triggering/run-test.sh58# Check if skill was triggered (look for Skill tool invocation)COMMENT
LOWtests/opencode/test-priority.sh89# Check if opencode is available for integration testsCOMMENT
LOWtests/opencode/test-tools.sh17# Check if opencode is availableCOMMENT
LOWtests/opencode/test-tools.sh48# Check if personal test skill was foundCOMMENT
LOWscripts/bump-version.sh88 # Check if all versions matchCOMMENT
LOWscripts/bump-version.sh149 # Check if this file is in the declared listCOMMENT
LOWskills/systematic-debugging/find-polluter.sh53 # Check if pollution appearedCOMMENT
Hyper-Verbose Identifiers18 hits · 18 pts
SeverityFileLineSnippetContext
LOWbin/superpowers-zh.js258function generateTraeBootstrapRule(projectDir) {CODE
LOWbin/superpowers-zh.js303function generateClineBootstrapRule(projectDir) {CODE
LOWbin/superpowers-zh.js345function generateKiroSteeringIndex(projectDir) {CODE
LOWbin/superpowers-zh.js409function generateKiloCodeBootstrapRule(projectDir) {CODE
LOWbin/superpowers-zh.js496function generateAntigravityBootstrap(baseDir, isGlobal) {CODE
LOWbin/superpowers-zh.js877function generateClaudeCodeBootstrap(baseDir, isGlobal) {CODE
LOWbin/superpowers-zh.js930function generateReasonixBootstrap(projectDir) {CODE
LOWbin/superpowers-zh.js980function generateDeepSeekHarnessBootstrap(baseDir, isGlobal) {CODE
LOWbin/superpowers-zh.js1025function generateCodeBuddyBootstrap(baseDir, isGlobal) {CODE
LOWtests/brainstorm-server/branding.test.js77function createPackagedServerFixture(version) {CODE
LOWtests/brainstorm-server/branding.test.js157function assertBrandedFallbackText(html, version = PACKAGE_VERSION) {CODE
LOWtests/brainstorm-server/branding.test.js173function assertLogoKeepsTransparentBackground(html) {CODE
LOWtests/brainstorm-server/branding.test.js208function assertFramedLogoSupportsDarkTheme(html) {CODE
LOWtests/brainstorm-server/branding.test.js215function assertFramedScreenUsesBrandHeader(html) {CODE
LOWtests/brainstorm-server/branding.test.js227function assertHeaderAvoidsNarrowOverlap(html) {CODE
LOWtests/brainstorm-server/server.test.js93function assertStartedOnExpectedPort(out) {CODE
LOWtests/brainstorm-server/auth.test.js116function assertStartedOnExpectedPort(out) {CODE
LOW.pi/extensions/superpowers.ts115function firstNonCompactionSummaryIndex(messages: unknown[]): number {CODE
AI Slop Vocabulary3 hits · 14 pts
SeverityFileLineSnippetContext
MEDIUM⚡skills/brainstorming/scripts/start-server.sh153# Resolve the harness PID (grandparent of this script).COMMENT
MEDIUM⚡skills/brainstorming/scripts/start-server.sh154# $PPID is the ephemeral shell the harness spawned to run us — it diesCOMMENT
MEDIUM⚡skills/brainstorming/scripts/start-server.sh155# when this script exits. The harness itself is $PPID's parent.COMMENT
Modern AI Meta-Vocabulary2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMtests/subagent-driven-dev/go-fractals/scaffold.sh3# Usage: ./scaffold.sh /path/to/target/directoryCOMMENT
MEDIUMtests/subagent-driven-dev/svelte-todo/scaffold.sh3# Usage: ./scaffold.sh /path/to/target/directoryCOMMENT
Empty Error Handlers1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHtests/claude-code/analyze-token-usage.py67except Exception:CODE
Fake / Example Data4 hits · 4 pts
SeverityFileLineSnippetContext
LOWtests/claude-code/test-document-review-system.sh63git config user.email "test@test.com"CODE
LOWtests/claude-code/test-requesting-code-review.sh50git config user.email "test@test.com"CODE
LOW…e-code/test-subagent-driven-development-integration.sh109git config user.email "test@test.com"CODE
LOWskills/brainstorming/visual-companion.md246<div class="placeholder">占位区域</div>CODE
Excessive Try-Catch Wrapping2 hits · 3 pts
SeverityFileLineSnippetContext
LOWtests/claude-code/analyze-token-usage.py67 except Exception:CODE
MEDIUMtests/claude-code/analyze-token-usage.py91 print(f"Error: Session file not found: {main_session_file}")CODE
Example Usage Blocks2 hits · 3 pts
SeverityFileLineSnippetContext
LOWtests/brainstorm-server/windows-lifecycle.test.sh15# Usage:COMMENT
LOWscripts/bump-version.sh6# Usage:COMMENT
Deep Nesting1 hit · 1 pts
SeverityFileLineSnippetContext
LOWtests/claude-code/analyze-token-usage.py12CODE