AI Slop Code Risk Monitor

HKUSTDial/Supervisor-Skills

SlopCodeMonitor badge for HKUSTDial/Supervisor-Skills Adjusted legacy signal; badge bands: 25 / 50 / 75 (different from dashboard bands).
8.5 Moderate pattern signal View on GitHub

Open-Source Code Quality, Security and Technical Debt Review

This report summarizes scanner evidence for HKUSTDial/Supervisor-Skills. SynthScan examined 19,629 lines of code across 138 source files, recording 89 pattern matches distributed across 7 syntactic categories. The legacy adjusted pattern signal is 8.5 (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.

8.5
Adjusted Signal
8.5
Raw Pattern Score
100%
Time Factor
—
Last Push
—
Stars
—
Language
19.6K
Lines of Code
138
Files
89
Pattern Hits
2026-10-31
Scan Date
0.04
HC Hit Rate

Risk Review · Payload v1

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

Payload schema: 1.0.0 · Engine: 2.0.0 · Scoring: heuristic-density-v1 · Scan date: 2026-10-31.

Cognitive Ownership Risk 33.6/100 · MEDIUM

Can maintainers explain intent, assumptions, and trade-offs? 84 finding(s).

Hallucinated Dependency & Supply Chain Risk 0.5/100 · LOW

Are imports declared and package/API names verified? 2 finding(s).

Agent Over-Engineering Ratio 1.5/100 · LOW

Are wrappers, guards, and repeated structures necessary? 5 finding(s).

PR Review Velocity Impact 27.6/100 · MEDIUM

Which changes need focused human review? 89 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

Run additional scans to build a history of the legacy pattern signal. Score changes are not a measure of AI adoption or code quality.

No multi-scan history yet — run the scanner again to build trend data.

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 6MEDIUM 4LOW 79

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 89 distinct pattern matches across 7 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.

Structural Annotation Overuse69 hits · 113 pts
SeverityFileLineSnippetContext
LOW⚡…/05_Vibe_Research/5.1_vibe-research-and-vibe-coding.md245### Step 1: Figure DesignCOMMENT
LOW⚡…/05_Vibe_Research/5.1_vibe-research-and-vibe-coding.md252### Step 2: Draft Figure GenerationCOMMENT
LOW⚡…/05_Vibe_Research/5.1_vibe-research-and-vibe-coding.md256### Step 3: Redraw as a Vector FigureCOMMENT
LOWskills/vibe-research-workflow/SKILL.md72### Step 1: Phase classificationCOMMENT
LOWskills/vibe-research-workflow/SKILL.md77### Step 2: Behavioural rules recapCOMMENT
LOWskills/vibe-research-workflow/SKILL.md104### Step 3: Phase-specific procedureCOMMENT
LOWskills/vibe-research-workflow/SKILL.md116### Step 4: Tool selectionCOMMENT
LOWskills/vibe-research-workflow/SKILL.md130### Step 5: Integrity gateCOMMENT
LOWskills/vibe-research-workflow/SKILL.md135### Step 6: OutputCOMMENT
LOWskills/benchmark-paper-template/SKILL.md90## Step 1: Five-pillar completeness tableCOMMENT
LOWskills/benchmark-paper-template/SKILL.md100## Step 2: Introduction six-part logic chainCOMMENT
LOWskills/benchmark-paper-template/SKILL.md111## Step 3: Section outline for §2 to §7COMMENT
LOWskills/benchmark-paper-template/SKILL.md115## Step 4: Pre-submission self-checkCOMMENT
LOW…ls/benchmark-paper-template/references/gap-analysis.md5## Step 1: Survey the Evaluation LandscapeCOMMENT
LOW…ls/benchmark-paper-template/references/gap-analysis.md23## Step 2: Identify the Blind SpotCOMMENT
LOW…ls/benchmark-paper-template/references/gap-analysis.md46## Step 3: Validate the GapCOMMENT
LOW…ls/benchmark-paper-template/references/gap-analysis.md57## Step 4: Articulate the Gap StatementCOMMENT
LOW…ls/benchmark-paper-template/references/gap-analysis.md68## Step 5: Derive Research QuestionsCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md53### Step 0: paradigm and venue fitCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md97### Step 1: Dimension 1 Macro logic reviewCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md143### Step 2: Dimension 2 Writing details reviewCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md155### Step 3: Dimension 3 English grammar reviewCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md171### Step 4: Dimension 4 LaTeX format reviewCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md187### Step 5: Dimension 5 Figure quality reviewCOMMENT
LOWskills/pre-submission-reviewer/SKILL.md202### Step 6: Banned-vocabulary and em-dash scanCOMMENT
LOW⚡skills/pre-submission-reviewer/SKILL.md221### Step 7: Section-by-section reviewCOMMENT
LOW⚡skills/pre-submission-reviewer/SKILL.md231### Step 8: Integrity gateCOMMENT
LOW⚡skills/pre-submission-reviewer/SKILL.md235### Step 9: OutputCOMMENT
LOWskills/deep-research/SKILL.md53## Step 0: freeze the research briefCOMMENT
LOWskills/deep-research/references/synthesis-framework.md13### Step 1: extractionCOMMENT
LOWskills/deep-research/references/synthesis-framework.md24### Step 2: thematic clustering and MECE taxonomyCOMMENT
LOWskills/deep-research/references/synthesis-framework.md42### Step 3: serial section synthesisCOMMENT
LOW…ills/paper-writer/references/verification-checklist.md13## Step 1: source recall checkCOMMENT
LOW…ills/paper-writer/references/verification-checklist.md26## Step 2: inline checksCOMMENT
LOWskills/rebuttal-guidance/SKILL.md46### Step 1: Inventory concernsCOMMENT
LOWskills/rebuttal-guidance/SKILL.md58### Step 2: Classify each concernCOMMENT
LOWskills/rebuttal-guidance/SKILL.md66### Step 3: Match reviewer mindset (X)COMMENT
LOWskills/rebuttal-guidance/SKILL.md77### Step 4: Strategy priorities for this mindset (Y)COMMENT
LOWskills/rebuttal-guidance/SKILL.md89### Step 5: Per-concern guidanceCOMMENT
LOWskills/rebuttal-guidance/SKILL.md108### Step 6: Integrity gateCOMMENT
LOWskills/rebuttal-guidance/SKILL.md118### Step 7: Output formatCOMMENT
LOWskills/intro-drafter/SKILL.md79### Step 1: paper-type positioning (internal)COMMENT
LOWskills/intro-drafter/SKILL.md90### Step 2: plan the six paragraphs (internal)COMMENT
LOWskills/intro-drafter/SKILL.md106### Step 3: the running example (internal)COMMENT
LOWskills/intro-drafter/SKILL.md117### Step 4: alignment checks (internal, before writing)COMMENT
LOWskills/intro-drafter/SKILL.md131### Step 5: write the proseCOMMENT
LOWskills/intro-drafter/SKILL.md163### Step 6: a short closing note (optional, three lines at most)COMMENT
LOWskills/tech-paper-template/SKILL.md57### Step 1: Paper-type positioningCOMMENT
LOWskills/tech-paper-template/SKILL.md70### Step 2: Fill the thinking templateCOMMENT
LOWskills/tech-paper-template/SKILL.md87### Step 3: Run four self-consistency checksCOMMENT
LOW⚡skills/tech-paper-template/SKILL.md109### Step 4: Generate methodology outlineCOMMENT
LOW⚡skills/tech-paper-template/SKILL.md118### Step 5: Integrity gateCOMMENT
LOW⚡skills/tech-paper-template/SKILL.md123### Step 6: OutputCOMMENT
LOWskills/idea-evaluator/SKILL.md58### Step 1: First impression and paper-type positioningCOMMENT
LOWskills/idea-evaluator/SKILL.md80### Step 2: Fatal-flaws audit (early gate)COMMENT
LOWskills/idea-evaluator/SKILL.md126### Step 3: Lifecycle and capability matchingCOMMENT
LOWskills/idea-evaluator/SKILL.md139### Step 4: Five-dimension scoringCOMMENT
LOWskills/idea-evaluator/SKILL.md173### Step 5: Paradigm-shift probeCOMMENT
LOWskills/idea-evaluator/SKILL.md194### Step 6: Feasibility checkCOMMENT
LOWskills/idea-evaluator/SKILL.md209### Step 7: Integrity gateCOMMENT
9 more matches not shown…
Synthetic Comment Markers6 hits · 32 pts
SeverityFileLineSnippetContext
HIGH…/05_Vibe_Research/5.1_vibe-research-and-vibe-coding.md60In the latest batch of startups, 25% of the companies reported that 95% of their code was generated by AI.CODE
HIGH⚡…/05_Vibe_Research/5.1_vibe-research-and-vibe-coding.md258Draft figures generated by Gemini / Nano Banana Pro are raster images (PNG) and cannot be directly used in the Paper.CODE
HIGH…/05_Vibe_Research/5.1_vibe-research-and-vibe-coding.md285- **Do not directly copy Paper content generated by AI / LLMs**. Students must verify the accuracy of content item by itCODE
HIGH…ook-en/05_Vibe_Research/5.2_liboyan-practical-notes.md37- **Current Scale**: The CEO of a world-famous startup incubator reported that in 25% of startups, 95% of the code is geCODE
HIGH…ook-en/05_Vibe_Research/5.2_liboyan-practical-notes.md98Use drawing tools to create a vector figure based on the draft (raster images generated by Gemini or Nano Banana cannot CODE
HIGH…ook-en/05_Vibe_Research/5.2_liboyan-practical-notes.md142| 20:57 | Importance of AI-assisted coding for research | 95% of code in 25% of global startups is generated by AI; VibeCODE
Modern AI Meta-Vocabulary3 hits · 9 pts
SeverityFileLineSnippetContext
MEDIUMskills/paper-polish/references/ai-tone-guardrails.md4# AI-tone guardrails and inflated-claim wordlistCOMMENT
MEDIUMskills/paper-writer/references/ai-tone-guardrails.md4# AI-tone guardrails and inflated-claim wordlistCOMMENT
MEDIUMskills/idea-evaluator/references/paradigm-elephant.md84## 5. Worked example: multi-agent collaboration for complex tasksCOMMENT
Deep Nesting4 hits · 4 pts
SeverityFileLineSnippetContext
LOWskills/drawio-reconstruction/scripts/crop_assist.py95CODE
LOWskills/drawio-reconstruction/scripts/check_drawio.py37CODE
LOWskills/drawio-reconstruction/scripts/check_drawio.py125CODE
LOWskills/drawio-reconstruction/scripts/check_drawio.py245CODE
Excessive Try-Catch Wrapping3 hits · 4 pts
SeverityFileLineSnippetContext
LOWskills/drawio-reconstruction/scripts/check_drawio.py257 except Exception as exc:CODE
MEDIUMskills/drawio-reconstruction/scripts/check_drawio.py8def _float_attr(element, name, default=0.0):CODE
LOWskills/drawio-reconstruction/scripts/batch_verify.py81 except Exception as exc:CODE
Unused Imports2 hits · 2 pts
SeverityFileLineSnippetContext
LOWscripts/check_shared_sync.py18CODE
LOWscripts/lint_skills.py17CODE
Hyper-Verbose Identifiers2 hits · 2 pts
SeverityFileLineSnippetContext
LOWskills/drawio-reconstruction/scripts/check_drawio.py37def _semantic_containment_failures(cells_by_id):CODE
LOWskills/drawio-reconstruction/scripts/check_drawio.py225def _complex_visual_svg_failures(cells_by_id):CODE