Assess startup engineering operations across delivery, hiring, team structure, and production practices. Use delivery metrics, hiring conversion rates, and staffing data to identify bottlenecks, estimate candidate needs, and plan management roles and operational improvements.
- Find where development work waits before release
- Estimate candidate volume needed for hiring goals
- Review team structure and manager hiring needs
alirezarezvani/claude-skills☆ 28.4KUpdated Aug 30, 2026
Turn survey responses, interviews, and other research data into three distinct user personas. Each profile explains the outcome users seek, their main difficulties, desired benefits, an unexpected behavioral insight, and how well the product meets their needs.
- Creating three personas from survey responses
- Grouping interview findings by user goals and behavior
- Comparing user needs to guide product decisions
phuryn/pm-skills☆ 27.2KUpdated Oct 16, 2026
Analyze user feedback and usage data to identify at least three customer groups based on behavior, goals, and unmet needs. Build profiles covering pain points, product fit, and priorities for serving each group.
- Finding customer groups within diverse user feedback
- Comparing needs across user groups
- Prioritizing product improvements by customer group
phuryn/pm-skills☆ 27.2KUpdated Oct 16, 2026
Interpret n8n validation results and work through fixes for missing settings, broken references, and expression errors. Distinguishes blocking errors from advisory warnings, explains validation profiles, and guides review of automatic fixes and execution failures.
- Understanding validation errors
- Deciding which warnings need attention
- Choosing a validation profile
czlonkowski/n8n-mcp☆ 23.1KUpdated Oct 19, 2026
Analyze a single discovery interview to understand actual behavior, needs, workarounds, and open questions. Receive a concise account tied to sources, separating participant actions from hypothetical intentions, interviewer suggestions, and interpretation.
- Summarize actual behavior from an interview
- Identify needs and current workarounds
- Prepare follow-up research questions
screenpipe/screenpipe☆ 22KUpdated Oct 20, 2026
Design file-based storage for agent context, including large tool results, plans, logs, and handoff notes. Keep information available outside the conversation and retrieve relevant sections when needed, instead of loading everything at once.
- Saving large tool results for selective reading
- Keeping plans available during long tasks
- Sharing findings between agents through files
muratcankoylan/Agent-Skills-for-Context-Engineering☆ 18.2KUpdated Oct 12, 2026
Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.
- Test CUDA code without a local GPU
- Run model training or LoRA fine-tuning on cloud GPUs
- Deploy a model inference API or vLLM service
wanshuiyin/Auto-claude-code-research-in-sleep☆ 17.8KUpdated Oct 19, 2026
Request an owner’s permission to use a listed keychain credential needed by a command. An approval card appears in the conversation, and owner approval automatically reruns the blocked command with access shared across that conversation.
- Request permission for a credential needed by a command
- Resume a blocked command after its owner approves access
- Share approved access across sessions in one conversation
yc-software/qm☆ 15.5KUpdated Oct 20, 2026
Choose a feature design using the relevant code, requirements, and existing conventions. Record the chosen approach, alternatives, risks, and coverage of key user journeys, and identify decisions that need human input before implementation.
- Choose an implementation approach before coding
- Document alternatives and reasons for rejecting them
- Check coverage of key user journeys
omnigent-ai/omnigent☆ 10.9KUpdated Oct 20, 2026
Compare a regulatory change with an indexed company policy library. Identify affected policies, missing or conflicting provisions, responsible owners, and specific changes needed, with source labels and flags for uncertainty about whether the rule is in force.
- Identifying policies affected by a regulatory change
- Comparing new requirements with existing policy wording
- Finding requirements that need a new policy
anthropics/claude-for-legal☆ 9.8KUpdated Oct 14, 2026
Prepare an internal Privacy Impact Assessment, a review of how a feature uses personal data. Check whether assessment is needed, examine legal grounds and policy commitments, and document specific risks, required actions, and owners in the team’s format.
- Reviewing personal data use in a new feature
- Checking whether a privacy assessment is needed
- Comparing processing plans with privacy policy commitments
anthropics/claude-for-legal☆ 9.8KUpdated Oct 14, 2026
Draft an AI usage policy for a law firm or legal team using published policies and guidance. Adapt selected sections to the organization, cite sources, and flag decisions and open questions for attorney review.
- Creating a first AI usage policy draft
- Updating an existing policy for regulatory changes
- Drafting rules for confidential data and AI tool approval
anthropics/claude-for-legal☆ 9.8KUpdated Oct 14, 2026
Structure customer research around what people want to accomplish, the difficulties they face, and the benefits they seek. Explore practical tasks, social perceptions, and emotions to clarify unmet needs and guide product positioning or priorities.
- Uncovering needs behind feature requests
- Organizing findings from customer interviews
- Revisiting product positioning around customer goals
deanpeters/Product-Manager-Skills☆ 7.5KUpdated Oct 16, 2026
Choose charts and diagrams that fit the data and the question readers need to answer. Plan layouts and interactions for large screens and mobile devices, or critique existing visuals for misleading comparisons, unclear labels, and hidden information.
- Choose a chart for a specific analytical question
- Review an existing chart for misleading presentation
- Plan dashboard layouts for desktop and mobile
openai/plugins☆ 7.5KUpdated Oct 8, 2026
Decide whether geographic data needs a map, then choose suitable background maps, visual forms, and implementation tools. Plan overlapping markers, zoom behavior, and mobile interactions so the map supports the intended analysis or product task.
- Deciding whether regional comparisons need a map
- Designing regional maps with meaningful color scales
- Planning overlapping markers and zoom behavior
openai/plugins☆ 7.5KUpdated Oct 8, 2026
Analyze an Amazon competitor by ASIN, its product identifier, using listing text, keywords, images, and reviews. Identify competitor strengths and unmet buyer needs, then turn those findings into positioning and product opportunities for your brand.
- Analyze a competitor's titles and selling points
- Review keyword placement across a listing
- Find unmet buyer needs in reviews
browser-act/skills☆ 6.2KUpdated Aug 24, 2026
Prepare a first reply to a customer inquiry by classifying the issue, confirming understanding, and requesting missing details. Use existing documentation for answers, acknowledge feature requests, or route cases that need human follow-up.
- Preparing the first reply to a customer inquiry
- Requesting details needed to investigate a bug
- Acknowledging a feature request
agentscope-ai/agentscope-java☆ 6.1KUpdated Oct 20, 2026
Manage projects involving multiple Workers with a shared plan that records task status, assignments, and dependencies. It covers project setup, task completion updates, plan changes, blocked work, and final notifications to the administrator.
- Start a project involving multiple Workers
- Assign tasks and handle completion reports
- Revise plans when tasks become blocked
agentscope-ai/AgentTeams☆ 5.8KUpdated Oct 17, 2026
Manage Python and R packages for notebook work. Resolve missing-package errors, check installed versions, install into the selected runtime, and restart the kernel when needed, with guidance on using separate environments for different dependency requirements.
- Resolve missing-package errors in a notebook
- Check installed package versions
- Separate project dependencies into a named environment
aipoch/open-science☆ 5.3KUpdated Oct 20, 2026
Draft first replies to customers and identify tickets that require human review before sending. The skill defines sensitive cases to escalate and guides replies that explain the next action, name who handles it, and match the customer's tone.
- Drafting a first reply to a customer
- Identifying tickets that need human review
- Explaining next steps and who handles them
Kiln-AI/Kiln☆ 5.2KUpdated Oct 20, 2026
Maintain Kiln’s list of large language models by discovering new releases, testing provider access, and marking unavailable entries as deprecated. Prepare pull requests, report unresolved issues, and check whether the updated list needs publication.
- Run the scheduled model sweep manually
- Add new models and test provider access
- Mark unavailable model entries as deprecated
Kiln-AI/Kiln☆ 5.2KUpdated Oct 20, 2026
Find the TRES Finance report that fits a task such as month-end close, audit preparation, or balance checks. Recommendations explain relevant Excel tabs and columns, useful filters, and the report identifier needed for API exports.
- Choose reports for month-end close or an audit
- Find a report showing balances on a past date
- Select transaction and realized gains reports for tax preparation
anthropics/claude-plugins-community☆ 4.7KUpdated Oct 20, 2026
Convert LaTeX article manuscripts into Quarto documents for publishing as HTML, PDF, or Word. Preserve mathematical content while adapting document settings, citations, figures, tables, and cross-references, and receive a report of items needing manual review.
- Migrate a LaTeX paper to Quarto
- Prepare a manuscript for HTML, PDF, and Word
- Convert citations and cross-references
brycewang-stanford/Auto-Empirical-Research-Skills☆ 4.7KUpdated Oct 19, 2026
Collect unresolved work that needs human judgment from configured pull requests, issues, feedback, errors, and delivery signals. Group related problems into a decision queue with source links, supporting evidence, and visible gaps in coverage.
- Reviewing work that still needs a human decision
- Grouping recurring errors and user concerns
- Checking pull requests awaiting review or approval
BuilderIO/skills☆ 4.6KUpdated Oct 15, 2026