'contributions' 검색 결과

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions

Coordinate multiple agents to maintain context-mode, from sorting GitHub issues and reviewing pull requests to preparing releases and announcements. Workflows require reproduced bugs, source evidence, test-first changes, and checks across supported platforms.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating reported bugs and their history
• Reviewing contributor pull requests
• Preparing releases and compatibility checks

Evaluate prospective business partners using evidence of their customer relationships and sales contributions. Recommend a partnership tier, build a 90-day joint sales plan, and compare revenue sharing with direct-sale margins, including conditions for ending the partnership.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluating a prospective reseller or OEM partner
• Designing partnership tiers and qualification criteria
• Planning the first 90 days of joint sales

Examine strategic decisions through a structured meeting of AI agents representing executive roles. Gather independent recommendations, challenge assumptions, summarize disagreements, and record approved decisions with action owners and deadlines after the founder reviews the proposal.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluate market expansion from several executive perspectives
• Compare views on product direction or pricing
• Review hiring plans and organizational choices

Develop independent solutions to a defined problem, compare them against shared requirements, and combine useful contributions into a coherent recommendation. An independent assessment and evidence checks support the selection, while unresolved tradeoffs and verification needs remain explicit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing concrete solutions to a defined problem
• Developing rough options before choosing an approach
• Comparing architectural or product proposals

Guides review of pull requests from external forks, covering code ownership, contribution terms, security-sensitive changes, and tests tied to the reviewed commit. It produces a review record and supports moving changes to a maintainer branch when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing external contributions before approval
• Checking code provenance and contribution terms
• Verifying security reviews and tests for a specific commit

Check that changes to existing PEFT methods still work with saved training checkpoints. The skill guides compatibility tests, configuration checks, benchmark comparisons, and reporting, including comparisons of model outputs before and after a change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking compatibility after a forward method rewrite
• Changing state_dict structure while supporting old checkpoints
• Reviewing defaults for new configuration fields

Build, improve, review, or troubleshoot Agent Zero plugins for local use or community distribution. Follow plugin structure and installation rules, verify behavior in the target runtime, and prepare repository and Plugin Index contributions when requested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an Agent Zero plugin for local use
• Reviewing an existing plugin's structure and behavior
• Investigating plugins that fail to load or run

Turn a vague research approach into a concrete method proposal with focused contributions and minimal validation experiments. Ground the plan in relevant papers, then refine it through GPT-6-Astra reviews while preserving the original problem and resource constraints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a rough research idea into an implementable method
• Simplify a proposal with too many components
• Clarify novelty against related research

Find related papers across local PDFs, research notes, and web sources, then summarize their key contributions and relevance. Use existing collections as a starting point, remove duplicates, and search for literature that fills gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find related work for a research topic
• Summarize relevant papers already stored locally
• Combine Zotero highlights with Obsidian research notes

Maintain a collection of architecture decision record templates, examples, translations, and tool links. It explains which files to update for each contribution and how to review pull requests for completeness, consistent formatting, and relevant content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add an ADR template to the collection
• Add a worked decision record example
• Update links to ADR tools and pull request checks

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions

Navigate Apache Beam contributions from finding an issue to submitting a pull request, a proposed code change, and responding to reviews. Covers environment setup, tests, formatting, licensing requirements, and closer evaluation of changes to core components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a first Apache Beam contribution
• Organize a pull request and its related issue
• Check tests and formatting before submission

Prepare external contributions to gentle-ai through approved issues, accurate pull request descriptions, and plans for splitting large changes. Check claims against test results and GitHub state while respecting contributor and maintainer permissions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a contribution through the approved issue workflow
• Audit pull request claims against GitHub state
• Plan a sequence of related pull requests

Writes expert academic paper summaries for social science research, particularly political science and applied statistics. Use when asked to summarize, review, or create a reading summary of an academic paper, PDF, or research article. Accepts a file (PDF or text format) or a directory of papers. Produces a structured markdown summary — approximately 400–600 words — covering primary contributions, major questions and answers with point estimates, methods and data, and limitations and robustness. Includes BibTeX citation retrieved from Google Scholar and keyword metadata.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Assesses a research paper outline (.qmd file) against structured criteria from Kosuke Imai's empirical research guide. Evaluates the abstract and section outline for: research question clarity, stated contributions, hypotheses and testable implications, data description, planned results and inferential approach, and robustness checks. Detects causal papers from the abstract and conditionally assesses identification strategy only when causal framing is present. Produces a structured markdown report with PASS/PARTIAL/FAIL assessments and actionable suggestions. Use when asked to assess, evaluate, review, or check a paper outline, abstract-and-outline, or research plan in a .qmd file.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Skeptical review of outside contributions to public repos. Use when reviewing, ranking, or replying to public GitHub pull requests or issues from outside contributors, or when the user says "larp-detector".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

How to develop, modify, and extend the Claude Code codebase following its established programming style, patterns, and conventions. Use this skill whenever working on the claude-code source — adding tools, commands, utils, components, types, hooks, services, or fixing bugs. Also use when the user asks about claude-code architecture, coding standards, file organization, or wants to understand how the codebase works. This skill ensures all contributions match the existing codebase style exactly.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Resolve conflicts and merges when several branches are open against one repo at the same time — the hotspot files every change must touch (registry manifests, a single version field, shared tool config, one aggregated test module, tracked build output), union-vs-recompute-vs-rebuild as three different correct resolutions, generated artifacts that must never be merged, non-deterministic serialization that makes every branch conflict, renumbered identifiers that git cannot show you, and why a clean auto-merge is not a passing test. Use when rebasing or merging a long-lived branch, resolving conflict markers, reviewing a merge commit, deciding what a repo should commit vs generate, or setting up a repo that will take parallel contributions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when determining author order on research manuscripts, assigning CRediT contributor roles for transparency, documenting individual contributions to collaborative projects, or resolving authorship disputes in multi-institutional research. Generates fair and transparent auth...

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Drafts journal-ready cover letters for manuscript submission. Use when preparing a submission package, communicating the manuscript's contributions and journal fit to editors, or tailoring the novelty framing for a specific journal's scope. Also triggers on "write a cover letter for my paper", "draft a submission cover letter", "help me write to the editor", or "cover letter for [journal name]".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft and review contributions to existing MEX project knowledge in the repo wiki. Use when the user wants to capture a team decision, convention, or architecture note, propose an addition or correction for team review, or invokes /mex-inbox or $mex-inbox. Also supports existing Spec proposals. Keywords: mex, project memory, CLAUDE.md, team memory, drift, inbox. Do not activate for brainstorming alone, routine GROW upkeep, email inboxes, session logs, or handoffs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft and review contributions to existing MEX project knowledge. Use when the user asks to capture a discussion or decision in project knowledge, propose an addition or correction for team review, or explicitly invokes /mex-inbox or $mex-inbox. Also supports existing Spec proposals. Do not activate for brainstorming alone, routine GROW upkeep, email inboxes, session logs, or handoffs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build and deliver a raise request that actually works — the evidence, the number, the timing, and the exact words — instead of hoping it gets noticed. Use when asked how do I ask for a raise, I deserve more money, prepare me to ask for a raise, or negotiate a pay increase at my job. Produces a value case built on your actual contributions and market rate, a specific target number with justification, the right timing and person, a script for the conversation, and responses to the likely pushbacks — turning 'I want more' into a business case your manager can say yes to.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.