Skip to content

BdM-15/capture-insights / skills/data-analyzer

data-analyzer

Verified

Advanced data analysis, pattern detection, and insight generation from structured and unstructured datasets. Use when the user wants to analyze data, perform statistical analysis, find insights, detect patterns, identify anomalies, compare segments, test hypotheses, or generate data-driven recommendations. Triggers on phrases like 'analyze data', 'data analysis', 'find insights', 'analyze dataset', 'statistical analysis', 'find patterns', 'compare groups', 'test hypothesis', 'correlation analysis', or 'trend analysis'.

FileKindSize
SKILL.mdskill md8.6 KB
assets/report_template.mdmarkdown1.7 KB
evals/evals.jsonconfig2.0 KB
references/pitfalls.mdmarkdown4.0 KB
references/statistical-methods.mdmarkdown4.8 KB
references/visualization-guide.mdmarkdown3.6 KB

evals/evals.json

View on GitHub
{
  "skill_name": "data-analyzer",
  "evals": [
    {
      "id": 1,
      "prompt": "Here is a CSV with monthly sales data for 3 product lines over 2 years. Analyze it: find trends, identify which product line is growing fastest, check for seasonality, and flag any anomalies. Give me the key findings.\n\nProduct,Month,Revenue\nWidget-A,2024-01,45200\nWidget-A,2024-02,43800\nWidget-A,2024-03,51200\nWidget-B,2024-01,12400\nWidget-B,2024-02,18600\nWidget-B,2024-03,22100\nWidget-C,2024-01,98000\nWidget-C,2024-02,95500\nWidget-C,2024-03,88200",
      "expected_output": "EDA covering trend direction per product line, growth rate comparison, note on Widget-C declining while Widget-B accelerates, check for seasonality pattern, summary statistics, and at least one anomaly flag or clean bill of health with reasoning."
    },
    {
      "id": 2,
      "prompt": "I have employee survey data. Group A (new process, n=45) had satisfaction scores: mean=7.2, std=1.4. Group B (old process, n=48) had scores: mean=6.5, std=1.6. Test whether the new process actually improved satisfaction or if this could be random chance.",
      "expected_output": "Formulates H0/H1, selects independent-samples t-test, checks assumptions (normality, equal variance), computes or estimates t-statistic and p-value, calculates effect size (Cohen's d), interprets both statistical and practical significance, states conclusion in plain language."
    },
    {
      "id": 3,
      "prompt": "Compare these three customer segments by revenue and churn rate. Tell me which segment to focus on and why.\n\nSegment | Avg Revenue | Churn Rate | Count\nEnterprise | $42,000 | 4% | 120\nMid-Market | $8,500 | 11% | 580\nSMB | $1,200 | 28% | 2400",
      "expected_output": "Calculates total revenue contribution per segment, lifetime value estimate factoring churn, identifies the highest-leverage segment, provides a driver analysis, and recommends a specific focus with quantified expected impact — not just 'it depends'."
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall