원클릭으로
thomas
thomas에는 Calvin-Corbett에서 수집한 skills 48개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
Implement async service initialization, lifecycle startup, dependency graph ordering, concurrency-limited initializers, rollback/disposal on failure, idempotent initialization, and circular dependency handling for DI containers or resource registries.
Use when implementing incremental caches, cache invalidation, cache stats, cache summary, list/import/export/prune/clear cache CLI modes, or CLI side-effect/reporting paths where normal analysis output and diagnostic output must not interfere.
Use when implementing analyzer or linter suppression directives such as nosec, nosec-begin/nosec-end, nosec-next-line, noqa, ignore-next-line, disable/enable regions, per-rule selectors, inline comments, warning filters, or line-based suppression for multi-line AST statements and metrics.
Implement JSON Schema parsers with recursive $ref, $defs, dependencies, dependentRequired, dependentSchemas, if/then/else, anyOf/allOf composition, and deep enum/const equality without stack overflows or shallow-only tests.
Use when implementing static taint/dataflow analysis, interprocedural taint tracking, vulnerability analyzer plugins, Bandit-like checks, B620/B621/B622/B623/B624 rules, or source-to-sink rules for SQL injection, shell injection, path traversal, SSRF, XSS, request.args/form/cookies, sys.argv, input(), os.environ, import aliases, nested functions, f-strings, percent formatting, .format(), or Python walrus/NamedExpr propagation.
Implement multipart HTTP response parsing APIs with Content-Type boundary validation, MIME delimiter framing, CRLF/LF/CR streaming chunks, part headers, continuations, duplicate headers, DecodingError, StreamConsumed, sync iter_multipart, async aiter_multipart, and raw response stream closure.
Implement partial_structure APIs, PartialResult value/is_complete, structured_fields, failed_fields, errors, error_map, refine, attrs/dataclasses/TypedDict, forbid_extra_keys, detailed_validation, defaults, nested fields, collections, and init=False recovery behavior.
Harden serializer, deserializer, schema, alias, field metadata, and generated-code changes with cross-feature regression matrices.
Detect repeated multi-step workflows and turn them into reusable Thomas-native skill bundles with validation and maintenance notes.
Plan and execute CapCut-oriented edits for short-form marketing, promo, explainer, and caption-heavy videos with fast iteration in mind.
Deploy applications and infrastructure to Cloudflare Workers, Pages, and related services with environment and routing checks.
Guide DaVinci Resolve-style finishing work for edits that need stronger color, audio, timing, and delivery control.
Iterate on HTML or JavaScript web games with a tight browser-test loop, focused interactions, and visual verification.
Create, edit, and validate `.docx` documents with attention to formatting fidelity, structure, and rendered output.
Translate specific Figma nodes into production-ready UI with close visual fidelity and project-aware implementation decisions.
Pull design context from Figma and translate it into Thomas-native implementation or analysis steps.
Work through GitHub review comments and issue feedback on the current PR with clear fixes, replies, and verification.
Diagnose failing GitHub checks, isolate the concrete breakage, and land the smallest defensible fix with targeted verification.
Direct Higgsfield-oriented cinematic product video work around a real app, site, or launch concept.
Generate, edit, or refine images for product, concept, or marketing work with explicit prompt and output control.
Scaffold and refine Jupyter notebooks for experiments, tutorials, and exploratory workflows with clear narrative structure.
Read, create, and update Linear issues or project context with clean operational summaries and ownership details.
Deploy sites and apps to Netlify with build, environment, and preview-vs-production clarity.
Capture conversations and decisions into structured Notion knowledge artifacts with useful titles, summaries, and links.
Prepare agendas, pre-reads, and context briefs for meetings using Notion-based research and stakeholder-aware framing.
Research across Notion sources and synthesize the result into structured documentation with traceable context.
Turn Notion product or technical specs into implementation plans, tasks, and execution tracking artifacts.
Use official OpenAI documentation and Thomas-native product guidance when implementing or answering OpenAI API questions.
Read, create, and validate PDFs where rendered layout, extraction quality, and review fidelity matter.
Use a real browser to navigate, verify, extract, and reproduce UI behavior through deterministic scripted steps.
Prepare and deploy applications to Render with service definitions, environment checks, and operational handoff details.
Capture desktop, window, or region screenshots when browser-level capture is unavailable or the user explicitly wants OS-level evidence.
Perform targeted secure-by-default reviews and propose concrete remediation steps for supported stacks.
Map repository ownership and bus-factor risk for security-sensitive code using git history and structural hotspots.
Build concise repository-grounded threat models covering assets, boundaries, attacker capabilities, abuse paths, and mitigations.
Inspect Sentry issues, event streams, and recent production failures with operational summaries and next steps.
Design and refine Thomas-native skills with explicit workflows, validation rules, and small reusable bundles.
Recreate external skills into Thomas-native drafts from explicit local references without copying foreign code or long text verbatim.
Plan and run Sora video generation, remix, polling, and download workflows with clear prompt and asset control.
Generate text-to-speech output for narration, prompts, accessibility, or voiceover tasks with clear voice and delivery choices.