notque/vexjoy-agent - Page 3

markdown-converter

Convert PDF, Office, HTML, data, media, ZIP to Markdown.

news-collection

Collect, filter, and freshness-qualify news items.

roast

Constructive critique via 5 HackerNews personas with claim validation.

video-transcript

Extract video transcripts: yt-dlp subtitles to clean paragraphs.

systematic-code-review

4-phase code review: UNDERSTAND, VERIFY, ASSESS risks, DOCUMENT findings.

sapcc-audit

Full-repo SAP CC Go compliance audit against review standards.

agent-comparison

A/B test agent variants for quality and token cost.

security-review

Local security review of git changes: deterministic scan + Security reviewer over the diff. No API key, no SDK.

e2e-testing

Playwright-based end-to-end testing workflow.

condense

Maximize information density: preserve all instructions, remove prose filler.

joy-check

Validate content framing on joy-grievance spectrum.

publish

Blog publishing, blueprint to upload: post outlines, pre-publish checks, SEO, bulk frontmatter edits, link/image/taxonomy audits, WordPress upload.

skill-eval

Evaluate skills: trigger testing, A/B benchmarks, structure validation, head-to-head bake-offs.

sapcc-review

Gold-standard SAP CC Go code review: 10 parallel domain specialists.

explanation-traces

Query and display structured decision traces from routing, agent selection, and skill execution.

enterprise-search

Enterprise search: relevance tuning, query understanding, index management, search quality, ranking optimization, schema design.

opensearch-detection-engineer

OpenSearch SIEM detection: SIGMA, query DSL, MITRE ATT&CK mapping, anomaly/correlation rules, alert validation, SOC escalation.

wordpress-live-validation

Validate published WordPress posts in browser via Playwright.

condition-based-waiting

Polling, retry, and backoff patterns.

quick

Tracked lightweight execution with composable rigor flags: --trivial, --discuss, --research, --full. Covers zero-ceremony inline fixes (typo, spelling fix, small mistake in a single file, ≤3 edits) through contained multi-file changes.

testing-agents-with-subagents

Test agents via subagents: known inputs, captured outputs, verification.

testing-preferred-patterns

Identify and fix testing mistakes: flaky, brittle, over-mocked tests.

code-cleanup

Detect stale TODOs, unused imports, and dead code.

python-quality-gate

Python quality checks: ruff, pytest, mypy, bandit in deterministic order.

generate-claudemd

Generate project-specific CLAUDE.md from repo analysis.

reference-enrichment

Analyze agent/skill reference depth and generate missing domain-specific reference files.

forensics

Post-mortem diagnostic analysis of failed workflows.

repo-value-analysis

Analyze external repositories for adoptable ideas and patterns.

integration-checker

Verify cross-component wiring and data flow.

install

Verify VexJoy Agent installation, diagnose issues, and guide first-time setup.

read-only-ops

Read-only exploration, inspection, and reporting without modifications. Explore and report on code/config/state without writing or modifying anything.

workflow-help

Interactive guide to workflow system: agents, skills, routing, execution patterns.

code-linting

Run Python (ruff) and JavaScript (Biome) linting.

comment-quality

Review and fix temporal references in code comments.

universal-quality-gate

Multi-language code quality gate with auto-detection and linters.

decision-helper

Weighted decision scoring for architectural choices.

typescript-check

TypeScript type checking via tsc --noEmit with actionable error output.

learn

Manually teach error pattern and solution to learning database.

pair-programming

Collaborative coding with enforced micro-steps and user-paced control.

plant-seed

Capture forward-looking idea as a seed for future feature design.