Agent Skills by Emmanuel Prouveze
Showing 50 vetted skills indexed across 1 GitHub repositories.
eprouvezebattle
Benchmark AI model configurations on coding tasks to produce a leaderboard.
eprouvezefeature-branch-workflow
Guide Git feature-branch creation, naming, commits, and pull requests.
eprouvezeswarm
Run parallel Claude sessions in tmux panes for simultaneous task handling.
eprouvezecodex-write
Orchestrate Codex CLI code generation with Claude-led reviews and fixes.
eprouvezefreeze
Block Edit and Write operations outside a predefined directory per session.
eprouvezecareful
Intercept destructive Bash and Git commands and require confirmation before execution.
eprouvezeevaluate-plan
Compare implementation plans against source requirements to identify coverage gaps.
eprouvezerecall
Search memory stores via SQLite FTS5 index and return top 5 cited results.
eprouvezereview
Run parallel code reviews with Claude, Gemini CLI, and Codex CLI.
eprouvezetask
Create and queue autonomous agent tasks in the lex repository.
eprouvezedeslop
Detect and fix 22 AI-tell patterns in customer-facing text.
eprouvezebrief
Load project intel, failure atlas, decisions, and cross-project capabilities into context.
eprouvezepair-session
Coordinate AI pair programming sessions between Claude and Codex with human observation.
eprouvezesecond-opinion
Automate cross-LLM code reviews and adversarial testing via Codex CLI.
eprouvezeworkspace-cleanup
Remove temporary files and debugging artifacts after explicit user confirmation.
eprouvezevisualize-gaps
Generate a self-contained HTML dashboard visualizing plan coverage gaps.
eprouvezeretry-analysis
Retry failed Voice DNA Snapshot analyses via the admin API for a user identified by email.
eprouvezeresearch
Perform external web research and generate sourced markdown reports with citations.
eprouvezegeo-content
Assess a target domain for E-E-A-T signals and generate a structured GEO-CONTENT-ANALYSIS.md report.
eprouvezegeo-audit
Audit a website's AI citability, brand signals, content quality, technical accessibility, and schema completeness.
eprouvezelearn
Captures session learnings into persistent project memory via parallel sub-agents.
eprouvezekeyword-research
Query Google Trends for keyword interest, related queries, and regional insights.
eprouvezecouncil
Query Claude Opus, Gemini, and GPT-5.4 in parallel and synthesize responses into a dated session file.
eprouvezemode
Toggle single-LLM and multi-LLM delegation modes across Claude, Gemini, Codex, and Perplexity.