384 件 ・ 関連度順
概要と使いどころ
Use when: assumptions audit, audit assumptions, check for hidden assumptions, plan/ticket has ambiguous scope edges, pre-flight before finalizing a ticket, unstated assumptions, or 'what am I assuming'. Surfaces unstated assumptions, ambiguous scope edges, and untested preconditions in a finished plan/ticket/ADR before it is handed to Builder. Optional pass — Architect judges when to apply it; not a mandatory gate on every ticket.
日本語の概要は準備中です。原文の説明を表示しています。
Use immediately after RBR confirms a root cause and a fix is scoped, before considering the finding complete. Checks whether the confirmed defect is one instance of a structurally identical pattern elsewhere in the same file family, workflow, or business-domain area, and folds in or explicitly defers every other instance found. Mandatory for Architect and CAO — not an optional lens the agent judges when to apply.
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
日本語の概要は準備中です。原文の説明を表示しています。
Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.
日本語の概要は準備中です。原文の説明を表示しています。
Structure any communication artifact — documents, reports, plans, issue comments, PR descriptions, emails, presentations, slides, charts, and dashboards — using Jean-luc Doumont's "Trees, Maps, and Theorems" method. Use whenever the goal is to get a message across to a busy audience, when asked to improve clarity or structure of writing or slides, or when a deliverable will be judged by whether readers act on it, not just read it.
日本語の概要は準備中です。原文の説明を表示しています。
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits `$ai_generation` and `$ai_evaluation` events with `$session_id` linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).
日本語の概要は準備中です。原文の説明を表示しています。
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).
日本語の概要は準備中です。原文の説明を表示しています。
Diagnostic test / biomarker accuracy — sensitivity, specificity, PPV, NPV, likelihood ratios, accuracy from a 2x2 table; ROC curve, AUC, and the optimal cutoff (Youden) for a continuous biomarker; and post-test probability via Bayes. Use when you have test results vs a gold standard (binary 2x2, or a continuous score + true labels) and need to judge how good the test is, pick a threshold, or compute the probability of disease given a result. Emphasizes the prevalence-dependence of PPV/NPV.
日本語の概要は準備中です。原文の説明を表示しています。
Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data (enzyme/cell assays, drug screening, agonist/antagonist pharmacology). Fits the 4-parameter logistic (Hill sigmoidal) model. Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality. NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling).
日本語の概要は準備中です。原文の説明を表示しています。
Designs and validates quantitative targeted metabolomics assays (MRM/SRM on triple-quadrupole, PRM on high-resolution instruments) to report absolute concentrations. Covers the internal-standard strategy (external cal -> global IS -> standard addition -> stable-isotope-labeled IS), weighted calibration judged by back-calculated %RE not R-squared, ion-ratio quantifier/qualifier confirmation, matrix-effect/recovery characterization, and ICH M10 method validation. Use when quantifying a closed panel of known metabolites with units, building or validating an LC-MS/MS assay, choosing an IS or calibration weighting, or judging whether a reported concentration is trustworthy. For untargeted feature detection see metabolomics/xcms-preprocessing; for group statistics see metabolomics/statistical-analysis; for flux/MID/tracing see metabolomics/isotope-tracing.
日本語の概要は準備中です。原文の説明を表示しています。
Benchmark stellar-build skills to measure quality and the lift from optimization. Use when the user says "bench my skills", "bench-skills", "benchmark skills", "did optimization help", "measure my skills", "stellar-loop bench", or wants to quantify whether /optimize-skills actually improved things. Held-out eval prompts scored by an LLM judge, reproducible with fixed seeds. Fully local.
日本語の概要は準備中です。原文の説明を表示しています。
Help job seekers use Otameshi Tenshoku to prepare profiles and applications, clarify trial conditions, plan learning visits or paid trial work, and reflect on the experience. Use when a candidate wants to apply for, prepare for, negotiate the scope of, or review an otameshi work experience; do not use to predict whether they will be hired or to judge their aptitude, to state fees, contract terms, or service conditions from memory, or to submit an application, update a profile, or send a message on their behalf. Employer-side requests belong to the employer skills (trial-work-design, trial-listing-draft, applicant-reply and others).
日本語の概要は準備中です。原文の説明を表示しています。
Debrief a finished Otameshi Tenshoku trial from the employer's side: set the observed facts against the completion criteria agreed before the start, keep expectations added afterwards, second-hand or off-the-job observations and the company's own late or missing support apart, settle the hours actually worked separately from any evaluation, and draft feedback to the candidate that states facts, support gaps and what happens next without promising a hire or continuation the company has not decided. Use when a hiring manager, recruiter or small-business owner wants to review a trial, decide what to tell the candidate, or work out the settlement after a shortfall; do not use to judge the candidate's aptitude or predict a hire, to cut pay or demand unpaid rework because of dissatisfaction, to compare candidates, or to send the feedback, pay, or update records on the user's behalf.
日本語の概要は準備中です。原文の説明を表示しています。
Check, from the employer's side, what has been put in writing before a paid Otameshi Tenshoku assignment starts under gyomu-itaku: item by item whether the deliverable, delivery date, fee and how it is calculated, payment due date, who pays, out-of-scope work, revision limits, company support, rights, confidentiality and termination are stated in a contract, purchase order or email rather than in chat or by word of mouth, count the days from delivery to payment, and find pay tied to satisfaction or hiring, unpaid or unlimited revisions and one-sided termination. Use when a hiring manager, recruiter or small-business owner is about to offer terms to a candidate, has been asked by a candidate what is still unwritten, or needs the conditions written for a platform contract screen; do not use to judge whether the terms are lawful or the fee fair, to compute withholding or consumption tax, for employment contracts, or to sign, send or conclude the contract on the user's behalf.
日本語の概要は準備中です。原文の説明を表示しています。
Reply to an applicant for an employer's Otameshi Tenshoku listing: match the application against the listed requirements item by item on what the applicant actually stated, list the questions still open, and draft an invitation, a request for clarification, a hold notice or a decline that sticks to the listed conditions, keeps other applicants and internal notes out, and presents any new work or dates as a proposal rather than an agreed term. Use when a hiring manager, recruiter or small-business owner has applications to answer, wants to know what to ask before inviting, or has to decline; do not use to judge an applicant's aptitude or predict hiring outcomes, to screen on personal attributes unrelated to the work, to design the work (trial-work-design) or the listing (trial-listing-draft), or to send the message or update applicant records on the user's behalf.
日本語の概要は準備中です。原文の説明を表示しています。
Review and revise Japanese job-application documents (entry sheets, rirekisho, shokumu-keirekisho) by checking each answer against the question asked, the stated character limit, and the evidence the applicant can actually support, then propose concrete rewrites the applicant decides on. Use when a user wants an ES or resume answer critiqued, tightened, or drafted from their own experience; to assemble a whole shokumu-keirekisho from an experience inventory, use resume-draft instead; do not use to invent experience, to judge pass or fail probability, or to submit an application.
日本語の概要は準備中です。原文の説明を表示しています。
Turn vague preferences about employers into criteria that can actually be used to choose between them: for each one, what would have to be seen to confirm it, whether it comes from firsthand experience or from an untested assumption, whether it is a must, a nice-to-have, or something to avoid, and which pairs of criteria pull against each other while both being treated as required, then test the set against real candidates. Use when a new graduate is working out what to select employers on, when someone who has decided to move needs criteria for where to apply, or when a stated axis like "a place I can grow" needs to be made checkable; do not use to recommend an industry, job, or employer, to score or rank candidates, or to judge someone's stated preferences.
日本語の概要は準備中です。原文の説明を表示しています。
Inventory a person's work history as facts before any document is written, listing each period of employment and what they actually did, splitting every experience into situation, their own actions, outcome, and stated role, and recording what each claim rests on (public record, their own records, someone who was there, or memory alone). Use when a user is starting a job search, needs material for a rirekisho, shokumu-keirekisho, or entry sheet, or wants to find which periods of their history they have never written down; do not use to judge their strengths, aptitude, or market value, to name a job they are suited for, or to write finished application copy.
日本語の概要は準備中です。原文の説明を表示しています。
Check the terms of a specific side-work assignment offered as gyomu-itaku or freelance work in Japan, item by item: what the client has actually put in writing about the deliverable, the fee, the payment due date, what counts as out of scope, how many revisions are included, who bears expenses, who owns the result, confidentiality, and how either side can end it. Convert the fee into an effective hourly figure over the hours the work will really take including meetings, revisions and unpaid preparation, and count the days from delivery to the payment due date. Use when someone is offered or is discussing a paid side job, a freelance assignment, spot consulting, or paid trial work and wants to know what is still unwritten before starting; do not use to judge whether the fee is fair or the terms lawful, to decide whether to accept, to draft or sign the contract for the user, or to check whether their employer's rules permit side work, which is sidework-rules-check.
日本語の概要は準備中です。原文の説明を表示しています。
Plan the first months at a new Japanese employer after an offer is accepted, listing every expectation and promise made in interviews, the offer, or negotiation with its source, separating what is in writing from what was only said and what has no agreed measure, working out when the probation period ends and whether its criteria and conditions are known, and scheduling who to confirm what with before and after the start date. Use when a user has accepted an offer and wants to prepare for joining, make sure verbal promises such as remote days or a future role are confirmed, or understand what the probation period means for them; do not use to predict whether they will fit in or pass probation, to judge their manager or colleagues, to rule on the legality of probation terms, or to contact the new employer.
日本語の概要は準備中です。原文の説明を表示しています。
Plan a resignation and the move to a new employer: check the intended notice date, last working day, and start date against the notice period the employer's own rules require, count the weekdays left against remaining paid leave, and work through the checklist of handover, documents to receive, items to return, and the insurance, pension, and residual tax steps that a gap between jobs creates. Use when a user has accepted an offer and needs to work out when and how to resign, or wants to know what to confirm before giving notice; do not use to rule on whether they can legally leave, to judge a non-compete clause, to promise the departure will go smoothly, or to notify anyone.
日本語の概要は準備中です。原文の説明を表示しています。
Go through an interview that has just finished and sort out what happened: the questions asked and how fully they were answered, which of them were prepared for and which came from the submitted documents, the reverse questions still unanswered, what the employer said about conditions and whether any of it was in writing, and when a result was promised. Use when a user has just come out of an interview and wants to record it while it is fresh or to work out what to fix before the next round; do not use to judge how it went, to estimate whether they will pass, or to read anything into the interviewer's manner.
日本語の概要は準備中です。原文の説明を表示しています。
Read a Japanese job posting closely and report what it actually states: base pay separated from fixed overtime allowance, the range converted to an hourly basis, required versus preferred requirements, and the terms left ambiguous. Use when a user wants a 求人票 or job description examined before applying, wants two postings compared on the same basis, or wants questions prepared about pay and working conditions; do not use to judge whether the user will be hired, to infer duties the posting does not state, or to evaluate the employer's reputation.
日本語の概要は準備中です。原文の説明を表示しています。
Sort incoming scout messages and agent-forwarded openings by what they actually disclose: whether the employer is named at all, which of pay, location, employment type, and duties are stated, whether the message refers to the applicant's own history or reads as a mass send, whether a stated salary is an offer or a "up to" figure, and whether the same employer has arrived through more than one route. Use when a user has a backlog of scout messages and wants to know which ones can be researched, what to ask before replying, and what to settle before handing over a resume; do not use to rate how promising an opening is, to judge an employer or an agent, or to reply on the user's behalf.
日本語の概要は準備中です。原文の説明を表示しています。