Loading...
Loading...
Found 2,038 Skills
Evaluate the reproducibility of technical articles. Dispatch a subagent to simulate a first-time reader reproducing the work locally and list missing information. Use as the final check on a draft before publication.
Use this skill when gathering knowledge at scale before making decisions - technology evaluation, SOTA analysis, codebase archaeology, competitive analysis, or any investigation requiring multiple sources. Activates on mentions of research, investigate, evaluate options, what's the best, compare alternatives, state of the art, deep dive, explore the landscape, or find out how.
Creates structured hiring scorecards for any role. Takes job title, requirements, and team context. Generates comprehensive scorecard with weighted scoring rubric, interview questions per competency, evaluation matrix, red/green flags, and reference check questions.
Apply real options analysis to value managerial flexibility embedded in investment decisions. Use this skill when the user needs to evaluate projects with significant uncertainty and flexibility, assess the value of deferring or expanding investments, compare traditional NPV with expanded NPV, or when they ask 'should we wait to invest', 'what is the option to abandon worth', or 'why does NPV undervalue this project'.
Generate objective reference check reports about the user from real AI collaboration data — session history, git logs, GitHub profile, and memory files. Like a colleague writing a professional reference, but grounded in actual shared work. Use whenever the user asks to evaluate them as a developer, wants a reference letter, work style analysis, introduced by my agents content, interview prep from collaboration history, or blog topics from past discussions. Triggers on: write a reference, analyze my work patterns, what do you think of me, 나에 대한 레퍼런스 써줘, 내 작업 스타일 분석해줘. Not for general code review, architecture docs, cover letters, or codebase-only analysis.
Repeatable execution process for producing clear explanations. Covers Subject and Situational frameworks, depth scaling, and relatability tools.
Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture", "agent orchestration", "generator-evaluator", "long-running app", "harness design", "agent pipeline", "quality evaluation loop", "sprint contract", "build app with agents", "Claude Agent SDK architecture", or when building complex full-stack apps that need planning → generation → evaluation cycles. Also use when discussing context degradation, self-evaluation bias, or assumption testing in AI workflows.
Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.
Conducts comprehensive frontend design reviews covering UI/UX design quality, design system validation, accessibility compliance, responsive design patterns, component library architecture, and visual design consistency. Evaluates design specifications, Figma/Sketch files, design tokens, interaction patterns, and user experience flows. Identifies usability issues, accessibility violations, design system deviations, and provides actionable recommendations for improvement. Produces detailed design review reports with severity-rated findings, visual examples, and implementation guidelines. Use when reviewing frontend designs, validating design systems, ensuring accessibility compliance, evaluating component libraries, assessing responsive designs, or when users mention design review, UI/UX review, Figma review, design system validation, accessibility audit, or frontend design quality.
Expert in Jungian analytical psychology, depth psychology, shadow work, archetypal analysis, dream interpretation, active imagination, addiction/recovery through Jungian lens, and the individuation process - grounded in primary sources and clinical frameworks. Activate on 'Jung', 'Jungian', 'shadow work', 'archetypes', 'dream interpretation', 'active imagination', 'individuation', 'anima', 'animus', 'collective unconscious', 'addiction', 'recovery', 'spiritus contra spiritum'. NOT for therapy or diagnosis (only licensed analysts diagnose), active psychosis, severe dissociation, or replacing the relational container of actual Jungian analysis.
Convert an existing codebase in the current working directory into a ShinkaEvolve task directory by snapshotting the relevant code, adding evolve blocks, and generating `evaluate.py` plus Shinka runner/config files. Use when the user wants to optimize existing code with Shinka instead of creating a brand-new task from a natural-language description.
Simulate and detect software supply chain attacks including typosquatting detection via Levenshtein distance, dependency confusion testing against private registries, package hash verification with pip, and known vulnerability scanning with pip-audit.