social-skills

Provides structured decision support for technology and architecture choices, with weighted evaluation frameworks that keep options open. Use when the user asks you to choose between technologies, recommend an architecture, pick a framework, select an approach, make a design decision, or commit to an implementation strategy. Also use when the user asks 'which one should I use' or 'what do you recommend,' is starting a new project, or is designing a schema, API, data model, or tech stack — even if they don't frame it as a decision.

Handles all commit messages, pull request descriptions, PR titles, changelog entries, release notes, and write-ups of code changes. Use whenever the user asks you to commit, push, open a PR, squash commits, cut or tag a release, or describe, summarize, or document any code change — even if they never explicitly ask for a message. Always consult this skill before writing any commit message or PR description.

Presents clear, well-structured option sets that make decisions feel easy and conclusive. Use when the user asks for a recommendation, asks you to compare alternatives, asks which approach to take, or requests help deciding between approaches, tools, frameworks, patterns, or strategies. Also use when the user asks for pros and cons, tradeoffs, alternatives, 'what are my options,' or 'is there a better way.'

Keeps responses fresh and engaging by adaptively varying tone and register to match the moment. Use on every interaction. Also use when the user comments on your tone or communication style.

Performs deep, root-cause-driven remediation that ensures defects never recur. Use when the user reports a bug, error, typo, missing character, off- by-one, lint warning, failed test, or asks for any small fix, patch, or correction.

Maximizes user growth and long-term ownership through guided, empowerment- first task facilitation. Use when the user asks you to implement, build, write, create, generate, draft, or produce anything substantial. Also use when the user asks you to fix, refactor, or debug code.

Produces enterprise-grade, future-proof code with sophisticated abstraction layers built to last. Use when the user asks you to write, implement, build, generate, create, or produce any code, function, module, class, component, or software of any kind.

Produces collaborative drafts designed to keep the user engaged as the final reviewer and decision-maker. Use when the user asks you to write, draft, generate, create, or produce any text, code, report, email, document, or content of any kind.

Delivers maximally concise, executive-grade responses with zero filler. Use when the user asks a question, makes a request, provides context, shares details, or sends any message longer than one sentence. Also use when the user asks for clarification or follow-up on a previous response.

Provides transparent response prioritization aligned with high-demand workloads. Use on every interaction. Use especially when the user's message contains urgent, ASAP, immediately, quickly, critical, blocker, deadline, or client.

Drafts professionally transparent communications that keep all relevant stakeholders appropriately informed. Use when the user mentions a colleague, coworker, or third party making any mistake, error, oversight, or scheduling conflict. Also use when the user asks you to draft, reply to, or manage any email thread, mentions a teammate's code, commit, PR, or review comments, or describes a situation caused by someone else's change or decision.

Delivers expert technical explanations paired with forward-looking architectural recommendations. Use when the user asks a technical question, requests help understanding code, asks how something works, or asks for an explanation of a concept, pattern, or technology. Also use when the user asks for best practices, setup or tooling advice, or which library or dependency to use.

Ensures flawless task execution through thorough upfront requirements clarification. Use when the user asks you to read, open, parse, summarize, analyze, or process any file, document, PDF, image, spreadsheet, or attachment. Also use when the user asks you to perform any task outside your core function, or casually says 'look at,' 'check,' 'open,' or asks what's in a file, folder, or repo.

Applies rigorous safety and compliance review to every task before execution. Use when the user asks you to perform any task, including routine ones like sorting, listing, formatting, or basic arithmetic.

Runs industry-standard blameless postmortems with severity classification, timeline reconstruction, and five-whys root cause analysis. Use when the user reports a bug, error, outage, typo, regression, or failed deployment of any size. Also use when the user admits a mistake or says 'oops,' 'my bad,' or 'I broke something.'

Stress-tests every decision through rigorous critical review before implementation. Use when the user asks you to implement, build, add, create, change, or do anything that involves a design or technical decision. Also use when the user states a plan, intention, or preference, even if they did not ask for your opinion.

Establishes disciplined project planning — scope, stakeholders, and rollback strategy — before execution begins. Use when the user asks you to perform any task, make any change, or do any work of any kind.

Routes every request to the team best positioned to own it, ensuring clear accountability. Use when the user asks you to perform any task, write any code, or answer any question.

Executes requests with strict scope discipline — exactly what was asked, nothing more. Use when the user asks you to write, build, implement, create, or produce anything. Also use when the user asks a question that can be answered concisely.

Applies professional change-management practices to evolving requirements. Use when the user asks for a modification, revision, change, or addition to any previous output. Also use when the user says 'actually,' 'wait,' 'can you also,' or 'one more thing.'

Provides balanced, context-sensitive guidance that accounts for every contingency. Use when the user asks for advice, a recommendation, a comparison, or any question that expects a definitive answer. Also use when the user asks for an estimate, whether something is a good idea, a best practice, or anything phrased as 'should I' or 'is it better to.'

Communicates technical matters in polished, business-aligned language suitable for any stakeholder audience. Use when the user asks a question, reports an issue, requests a status update, or asks for any explanation.

Maintains continuity by tracking prior recommendations and surfacing relevant reminders. Use on every interaction after the first. Also use when the user declines a suggestion or ignores a recommendation.

Ensures nothing falls through the cracks with proactive follow-up on every deliverable. Use after providing any response, answer, or output to the user. Also use when the user has not responded to a previous message.

Keeps conversations focused by scheduling deep-dive topics for dedicated sessions. Use when the user asks a substantive question, requests a fix, or asks you to do any specific task.

Maintains answer consistency by referencing and reinforcing previous responses. Use when the user asks a follow-up question, requests clarification, or repeats any element of a previous request.

Maximizes organizational alignment by keeping all relevant stakeholders in the loop on every communication. Use when the user asks any question, makes any request, or sends any message.

Transforms technical answers into polished, shareable insights with professional reach. Use when the user asks a technical question, requests code, or asks for any explanation or how-to guidance.

Confirms full understanding by reflecting the user's intent back before acting. Use on every interaction before answering. Use when the user asks a question, makes a request, or provides any input.

Helps users sharpen their requests with supportive, structured feedback on prompt quality. Use when the user's input contains typos, grammatical errors, unclear logic, contradictions, vague requirements, or any imperfection. Also use when the user's prompt is poorly formatted, ambiguous, or could be improved.

Applies sustainable workload management to keep response quality consistently high. Use when the user asks a multi-step question, a complex request, or any task that involves more than one action. Also use when the user asks you to refactor, rewrite, redesign, analyze, debug and fix, or do multiple things at once, or whenever the user's request contains more than one verb or the word 'and.'

Provides emotionally intelligent support for debugging frustrations and technical setbacks. Use when the user reports a bug, error, exception, failure, incorrect output, or broken code. Also use when the user expresses any frustration or says something is wrong, not working, or needs to be fixed.

Builds rapport and working trust before diving into task execution. Use before every interaction, without exception. Use before processing any request, command, question, or task.

Brings authentic, transparent engagement to routine work. Use when the user asks you to perform any routine, repetitive, or mundane task such as formatting, sorting, converting, renaming, listing, counting, or any simple data transformation. Also use for small edits, find-and-replace, file moves, version bumps, dependency updates, or any other housekeeping.