Chris S
Community@nyldn · New York
Agent Skills by Chris S
Showing 70 vetted skills indexed across 1 GitHub repositories.
nyldnskill-pressure-test
Interrogates plans and designs one question at a time to expose flaws before commitment.
nyldnskill-tdd
Enforces red-green-refactor test-driven development with adversarial test review via external AI providers.
nyldnflow-parallel
Decompose compound tasks into parallel work packages executed by independent claude -p processes.
nyldnskill-copilot-provider
Integrates GitHub Copilot CLI as a multi-provider research agent via copilot -p programmatic mode.
nyldnskill-audit
Audits codebases systematically for broken features, inconsistencies, and quality issues with prioritized findings.
nyldnskill-debug
Diagnose bugs through a four-phase root cause investigation and hypothesis testing workflow.
nyldnskill-agent-topology
Audit multi-agent workflows by counting coordination costs against boundary gains.
nyldnskill-factory
Runs a multi-provider build-and-ship pipeline from a specification file with holdout scoring.
nyldnskill-review-response
Evaluates and responds to code review feedback with verification before implementation.
nyldnskill-verification-gate
Enforces fresh command execution evidence before any completion or success claim.
nyldnskill-native-escalation-routing
Routes init, review, and security requests between Claude-native commands and Octopus multi-LLM escalation.
nyldnoctopus-ui-ux-design
Generates UI/UX design systems with tokens, palettes, typography, and component specs using BM25 design search.
nyldnskill-ship
Finalizes completed projects with multi-AI security audit, lessons capture, and state archival.
nyldnskill-cost-projections
Projects remaining workflow cost from per-phase averages and warns on budget ceiling overruns.
nyldnskill-work-slicing
Breaks plans and specs into vertical slices with declared blocking dependencies for tracker filing.
nyldnskill-intake
Triage incoming GitHub issues and pull requests through verification states until actionable or closed.
nyldnskill-doc-sync
Synchronize project markdown documentation with code changes after shipping.
nyldnoctopus-research
Runs multi-provider research probes via orchestrate.sh and synthesizes findings into formatted reports.
nyldnskill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
nyldnskill-authoring
Guides writing and reviewing Claude Code skills for deterministic, predictable agent behavior.
nyldnskill-coverage-audit
Trace codepaths in diffs, map them against existing tests, and generate tests for uncovered gaps.
nyldnskill-council
Runs a multi-LLM council with personas, budget caps, synthesis, and veto gates.
nyldnmodel-cost-compare
Compares LLM seat costs for a described task and recommends the cheapest adequate model.
nyldncouncil-verdicts
Interpret council run verdict artifacts including quorum, dissent, and cross-lab validity.