Skip to main content

Influence Tactics Analysis Results

2
Influence Tactics Score
out of 100
81% confidence
Low manipulation indicators. Content appears relatively balanced.
Optimized for English content.
Analyzed Content
X (Twitter)

itshan on X

https://t.co/BJAdISHgyb just same idea. pic.twitter.com/gEzza8OG8N

Posted by itshan
View original →

Perspectives

Both Red and Blue Teams strongly agree the content is a neutral, technical GitHub README for an open-source macOS app, exhibiting no manipulation tactics, emotional appeals, or urgency; only mild, standard promotional phrasing. Blue Team emphasizes verifiability, while Red notes proportionate omissions—overall, evidence overwhelmingly supports authenticity with negligible suspicion.

Key Points

  • Unanimous agreement on absence of emotional manipulation, logical fallacies, tribalism, or urgency across both analyses.
  • Content aligns with open-source norms: technical instructions, feature tables, and mild hype (e.g., 'one click') are standard and balanced by verifiable details.
  • Strong verifiability via GitHub links and commands supports legitimacy, with no evidence of suppression, selective data, or incentives.
  • Minor issues like omitted security notes are common in dev repos and non-critical.

Further Investigation

  • Verify repo existence/activity: Clone https://github.com/tddworks/SkillsManager.git and check commit history, stars, issues for genuine usage.
  • Test skills paths (e.g., ~/.claude/skills, ~/.codex/skills) on macOS with actual Claude/Codex installs to confirm functionality.
  • Scan for security: Run malware checks on releases and review code for risks like arbitrary code execution in skill installs.
  • Cross-check linked repos (e.g., anthropics/skills) for consistency and official status.

Analysis Factors

Confidence
False Dilemmas 1/5
No binary choices presented; options like local/remote repos are inclusive.
Us vs. Them Dynamic 1/5
No us-vs-them dynamics; technical content for macOS/AI users without division.
Simplistic Narratives 1/5
No good-vs-evil framing; balanced feature list and setup instructions.
Timing Coincidence 1/5
Timing appears organic amid early January 2026 interest in Claude/Codex skills tools, with no links to major events like immigration protests or Syria conflicts.
Historical Parallels 1/5
No resemblance to propaganda playbooks; searches reveal no patterns matching this neutral app description.
Financial/Political Gain 1/5
Appears as genuine open-source promo by tddworks developer; no political or financial beneficiaries identified beyond potential GitHub reputation gains.
Bandwagon Effect 1/5
No claims of widespread agreement or popularity; simply describes app features without social proof.
Rapid Behavior Shifts 1/5
No pressure for quick opinion change or manufactured momentum; general AI skills discussion exists without focus on this app.
Phrase Repetition 1/5
Unique GitHub README excerpt; no identical phrasing across sources, with independent mentions only.
Logical Fallacies 1/5
No flawed reasoning; instructional content without arguments.
Authority Overload 1/5
No experts or authorities cited; self-contained GitHub project info.
Cherry-Picked Data 1/5
No data presented selectively; features and paths listed straightforwardly.
Framing Techniques 2/5
Mild promotional tone in phrases like 'Install skills to Claude Code and/or Codex with one click,' but mostly neutral technical language.
Suppression of Dissent 1/5
No mention of critics or dissent; purely descriptive.
Context Omission 2/5
Omits security notes for GitHub installs or compatibility details beyond 'macOS 15+'; otherwise comprehensive.
Novelty Overuse 1/5
No 'unprecedented' or shocking claims; features like 'Multi-Repository Support' and 'Search & Filter' are presented factually without hype.
Emotional Repetition 1/5
No repeated emotional triggers; text focuses on straightforward functionality without emphatic language.
Manufactured Outrage 1/5
No outrage expressed or manufactured; remains technical, e.g., table of providers and paths like '~/.claude/skills'.
Urgent Action Demands 1/5
No demands for immediate action; instructions are optional, such as 'Download the latest release from GitHub Releases' or build commands.
Emotional Triggers 1/5
Content lacks fear, outrage, or guilt language, using neutral descriptions like 'Browse and manage skills from GitHub repositories' and feature lists.

Identified Techniques

Loaded Language Name Calling, Labeling Repetition Black-and-White Fallacy Appeal to Authority
Was this analysis helpful?
Share this analysis
Analyze Something Else