Loading...
Loading...
Found 6 Skills
Senior Code Architect & Quality Assurance Engineer for 2026. Specialized in context-aware AI code reviews, automated PR auditing, and technical debt mitigation. Expert in neutralizing "AI-Smells," identifying performance bottlenecks, and enforcing architectural integrity through multi-job red-teaming and surgical remediation suggestions.
Audits AI-implemented work for honest completion. Runs independent-evaluator checks against task artifacts, transcripts, tests, CI evidence, requirement-to-test mapping, status front matter, and quality gates; flags skipped tests, weakened assertions, mock-only confidence, snapshot drift, happy-path-only coverage, flaky retries, and status/evidence mismatches. Use when validating completed Compozy tasks, AI-authored PRs, or codex-loop iterations. Do not use for real-user QA, persona/journey testing, exploratory charters, or product usability sessions; use qa-execution for those.
Audit and annotate an AI-generated implementation plan for requirements traceability, YAGNI compliance, and assumption risks. Use when reviewing, validating, or auditing an implementation plan or design proposal produced by an AI agent.
Apply AI ethics frameworks (fairness, accountability, transparency, privacy) to evaluate AI systems for algorithmic bias, explainability gaps, and value alignment failures. Use this skill when the user needs to audit an AI system for ethical risks, design fairness constraints, assess explainability requirements, or when they ask 'is this AI system fair', 'how do we detect algorithmic bias', 'what are the ethical implications of this AI deployment', or 'how do we make this model explainable to stakeholders'.
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local web viewer. Use when (1) scaffolding a new knowledge base for any research topic, (2) ingesting articles/papers/PDFs/web pages into raw/, (3) compiling or restructuring wiki articles from existing raw material, (4) answering questions against the wiki and filing durable answers back, (5) running lint passes for dead links / orphan pages / coverage gaps / audit shape, (6) processing human feedback from the audit/ directory and applying corrections. Not for general note-taking, daily journals, or non-wiki Obsidian use.
Check the consistency and authenticity risks of citations and references in NSFC proposal text (read-only): Verify the existence of bibkey, format issues such as BibTeX fields and DOI, and generate structured input for the host AI to evaluate item-by-item whether the text expression actually cites the literature; by default, only an audit report is output, and the proposal or .bib file is not directly modified (unless the user explicitly requests it).