- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add notque/vexjoy-agent --skill data -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add notque/vexjoy-agent --skill data -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add notque/vexjoy-agent --skill data -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add notque/vexjoy-agent --skill data -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/notque/vexjoy-agent/tree/HEAD/skills/analysis/dataFrom the publisher
Two modes. Match the request to a section.
Every analysis starts with the decision it supports, works backward to evidence required, then touches the data. Analysis without a decision is arithmetic.
Establish what decision this analysis supports.
analysis-frame.md.Gate: Decision identified, options enumerated, evidence requirements saved.
Lock metric definitions before loading data. Defining after seeing data enables cherry-picking.
For each metric: name, exact formula (numerator/denominator), population (included/excluded), time window, segments. For comparisons: define groups and verify fairness.
Save metric-definitions.md. Definitions are locked once Phase 3 starts. If data reveals a definition is unworkable, return here, update, and document the change.
Gate: All metrics defined with formulas and populations.
Load data. Assess quality. No interpretation.
import pandas; fall back to csv.DictReader + statistics.references/rigor-gates.md Gate 1):data-quality-report.md.Gate: Data loaded, quality assessed, failures documented as limitations.
Compute metrics per Phase 2 definitions. Report confidence intervals, not point estimates.
references/rigor-gates.md Gate 2).analysis-results.md.Gate: All metrics computed. Rigor gates applied.
Lead with insights. Return to the decision.
analysis-report.md (load references/output-templates.md for analysis-type templates).Gate: Report saved with headline, limitations, recommendation tied to decision.
Enrich agent/skill reference files from Level 0-2 to Level 3+, or decompose bloated body files by extracting domain content into references.
--decompose or "extract references")Extract domain-heavy content from a bloated SKILL.md into reference files.
python3 scripts/detect-decomposition-targets.py --skill {name} (or --agent).cp {path} /tmp/decomp-before-{name}.md.python3 scripts/validate-decomposition.py --before /tmp/decomp-before-{name}.md --after {path} --refs {refs_dir}/.python3 scripts/validate-references.py --check-size (reference sizes and empty references/ dirs; there is no per-skill mode).Load references/decomposition-prompt.md for the autonomous decomposition prompts.
Gate: Validation passes. Body reduced. All extracted content in references.
python3 scripts/gap-analyzer.py --agent {name} (or --skill).Gate: At least one gap identified. If Level 3 already, stop.
For each gap: identify version-specific patterns, failure modes with detection commands (grep -rn "pattern"), error-fix mappings, project conventions. Dispatch up to 5 parallel research agents per sub-domain.
Gate: Each gap has 10+ concrete findings (version numbers, function names, grep patterns). Generic advice does not count.
Create one reference file per sub-domain (max 500 lines) following references/reference-file-template.md. Include: overview, pattern table with version ranges, failure mode table with detection commands, error-fix mappings.
Do-pairing rule: every failure mode needs a "Do instead" counterpart. No bare negative blocks.
Validate: python3 scripts/validate-references.py --agent {name} and --check-do-framing. Both must exit 0. Then run condense on each file.
Gate: Each file 80-500 lines. Both validations pass.
Tier 1: python3 scripts/audit-reference-depth.py --agent {name} --json. Level must be 3.
Tier 2: Apply references/quality-rubric.md. For each pattern: detection command present? Would a reviewer using only this file produce Level 3 output?
Gate: Both tiers pass. Max 2 loops per gap before flagging for manual review.
python3 scripts/validate-references.py --agent {name} and python3 -m pytest scripts/tests/test_reference_loading.py -k {name} -v.Gate: Validation passes. Report level change (was N, now M) and new file list.
All references are >100 lines of domain-specific content. Load as directed by sections above.
Data analysis and reference enrichment.
---name: datadescription: Data analysis and reference enrichment.---# skills/analysis/data/SKILL.mdFAQ
Download skills/analysis/data/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/notque/vexjoy-agent.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.