Results for “cohere”

Use when reviewing or auditing a library of Claude Code skills, agents, slash commands, and workflows — frontmatter correctness, routing quality, tool allowlists, command arg-hints, workflow meta/phase coherence, cross-reference coherence, single-responsibility, file structure, and anti-pattern detection. Triggers on mentions of "review skills", "audit agents", "skill library", "agent definition review", "review this command", "review this workflow", "is this skill right", or when iterating on `.claude/skills/`, `.claude/agents/`, `.claude/commands/`, or `.claude/workflows/` directories. For code review of source code see code-review-and-quality.

The English summary is being prepared. Showing the original description.

Protocol for auditing API surface coherence and type safety. Trigger when: - Evaluating API designs, interface type safety, or design elegance. - Prompt contains: /api-audit, API surface, API coherence, type safety.

The English summary is being prepared. Showing the original description.

Goal-directed review of git history for change coherence. Trigger when: - Analyzing project history, reviewing diffs, or checking commit messages for alignment. - Prompt contains: /git-review, git history, commit log, change coherence.

The English summary is being prepared. Showing the original description.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

The English summary is being prepared. Showing the original description.

Reduce changes on your own branch before opening or updating a pull request. Review added architecture and tests, remove unnecessary complexity, and verify that the smaller change still fixes the original problem and preserves supported behavior.

• Trim changes before opening a pull request
• Remove duplicate architecture after a large repair
• Keep tests that catch distinct failures

Plan a consistent visual direction for music videos and short edits in angelcore, cloud-trance, and hyperpop styles. Define color, lighting, camera movement, and beat-synced cuts, then coordinate footage generation and editing through companion skills.

• Plan the visual direction of a music video
• Give AI-generated supporting footage a consistent look
• Design cuts that follow the song's beat

Repeat candidate searches and comparisons while keeping an append-only decision log. Record evidence, compare results with earlier winners, and check replay, freshness, and approval requirements before moving to live trading or production actions.

• Comparing candidates through repeated trials
• Keeping an evidence trail for decisions
• Reassessing earlier winners with fresh information

Find bottlenecks in large data transfers, imports, transformations, and historical data catch-up. Benchmark alternative processing methods, turn the fastest correct approach into a repeatable workflow, and verify file counts, row counts, and timestamps after execution.

• Speeding up large data imports and exports
• Reducing the time needed to load historical data
• Comparing batch sizes and worker counts

Rework a messy startup presentation into a coherent HTML slide deck for decision makers. Organize the narrative and evidence, then apply a consistent visual system of pastel-neon blocks, bold black borders, and coordinated layouts.

• Rework a startup deck for a board meeting
• Create agency credentials slides
• Present a brand redesign for review

Compare an implementation with its OpenSpec specifications, tasks, and design decisions before archiving the change. Get a report on completion, requirement coverage, and consistency, with prioritized issues, actionable recommendations, and explicit limits where evidence is missing.

• Check for unfinished tasks before archiving a change
• Find gaps between specifications and implementation
• Review scenario tests and adherence to design decisions

Revise an existing OpenSpec change plan and reconcile related planning documents. Incorporate new decisions, identify contradictions or gaps, and apply proposed document edits after confirmation, while leaving implementation code untouched.

• Incorporating new decisions into an existing change plan
• Checking planning documents for contradictions
• Reconciling related documents after an edit

Research a topic across multiple sources and turn the findings into a readable report. The skill coordinates separate research agents to compare options, examine markets or trends, and synthesize literature into a coherent narrative.

• Comparing products or services
• Researching markets and industry trends
• Reviewing studies on a topic

Design practice lessons around learners’ actual attempts, using the zone of proximal development: learning supported by a teacher or experienced peer. Plan targeted help, fresh independent tasks, and evidence-based next steps, or run a single practice cycle in chat.

• Designing a lesson that connects assessment and practice
• Offering hints based on a learner’s actual answer
• Checking independent performance after removing hints

Create a consistent company story for employees, investors, customers, candidates, and partners. Shape the same facts for each audience, check messages for contradictions, and prepare company updates or crisis communications.

• Aligning investor updates with employee communications
• Preparing a company-wide meeting
• Checking recruiting messages against company reality

Structure board presentations and investor updates using financial, sales, product, and people perspectives. Turn supplied metrics into a coherent account of progress, explain missed targets, and make decisions and requests explicit, with placeholders for missing figures.

• Preparing a quarterly board presentation
• Drafting a monthly investor update
• Structuring a fundraising narrative

Review an OpenSpec implementation against its specifications, tasks, and design decisions. The skill checks for missing work, uncovered scenarios, and inconsistencies, then produces a prioritized report with concrete recommendations and code references where available.

• Review an implementation before archiving
• Find incomplete tasks and missing requirement implementations
• Check whether scenarios have implementation and test coverage

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.

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

Helps design semantic search and RAG, where an AI answers using retrieved documents. Covers embeddings, numerical representations of content, plus document splitting, search indexes, keyword search combinations, and evaluation of retrieval quality.

• Design document retrieval for AI answers
• Compare embedding models and document splitting strategies
• Combine semantic search with keyword search

Turn ePub books into training examples for models that reproduce an author's writing style. Covers text extraction, coherent segmentation, varied instructions, model training, and checks for copied phrases and style transfer to new scenarios.

• Build training datasets from ePub books
• Train a model on an author's writing style
• Check for copied phrases in generated prose

Review Agent-Native Research Artifacts, structured research packages for agents, across six dimensions of research quality. Produce a JSON report with scores, strengths, severity-ranked findings, practical improvements, and an overall acceptance or rejection recommendation.

• Reviewing an ARA before publication
• Checking whether evidence supports research claims
• Assessing experimental methods and research records

Design and implement RAG systems, which retrieve documents to inform AI answers. Get document preparation strategies, vector database comparisons, combined keyword and meaning-based search, result reranking, and an evaluation plan for retrieval quality.

• Design an AI application that answers using internal documents
• Compare vector databases and document splitting strategies
• Improve search through keyword matching and result reranking

Turn books, transcripts, courses, and interviews into reusable agent skills. Extract practical frameworks and procedures, verify their source support, test representative tasks, and compile the results into a single entry or a skill pack.

• Turning a book's methods into reusable agent skills
• Extracting practical procedures from course or podcast transcripts
• Creating a single entry for studying and consulting source material

Create static technical drawings from object descriptions, photographs, or CAD models. Produce consistent views that explain shape or assembly, plus a viewer with zoom, editable colors, and downloads in SVG, PNG, and PDF formats.

• Creating an exploded view to explain an assembly
• Drawing aligned views from supplied dimensions
• Illustrating an object's shape from photographs

Research an unfamiliar topic or turn a collection of sources into structured notes, a reference article, or a publish-ready draft. The workflow connects sections to evidence, makes conflicting claims visible, and guides revision before publication.

• Research an unfamiliar field using primary sources
• Compile supplied materials into a coherent article
• Build reference notes without drafting an article