「evidence」の検索結果

Turn a moment of friction — a conflicting PR, a wedged runner, a mysterious red check, a repeated manual chore — into a durable, actionable report. Sizes up the scenario, captures the evidence, separates one-off from SYSTEMIC, proposes a fix, and routes it (fix now, or hand off). Reports are LIVING documents that the fixing agent updates with the outcome. Invoke whenever something feels like it shouldn't have been this hard, or when the same annoyance shows up twice.

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。

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.

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。

Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt columns cluster at one exact length (e.g. all 1,500 chars — a hard truncation cap). Covers: full rating-basis recovery, Excel 32,767-char cell cap, multi-line CSV mangling, ruling dropdowns, companion text files.

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。

Fresh verification gate before claiming done, fixed, passing, ready, or before commit/PR. Evidence before claims, always.

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。

Systematic 4-phase debugging framework for Unity projects with GameDebug wrapper generation. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Triggers on requests like "this doesn't work", "there's a bug", "it crashes when", "fix this error", "why is this happening", "null reference exception", "test is failing", "unexpected behavior", "something broke", or any debugging task. Four-phase framework (gather evidence, isolate, hypothesize, fix) that ensures understanding before attempting solutions.

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。

Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

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 when selecting or composing behavior-preserving refactoring techniques after structural evidence is known, especially when multiple candidate transformations, preconditions, or ordering choices must be compared.

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 when diagnosing structural maintainability problems in existing frontend code before deciding how to refactor it, especially when evidence, false-positive checks, and candidate transformations are needed without editing business code.

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。

Study unfamiliar codebases and produce evidence-backed knowledge artifacts. Use for repository orientation, architecture mapping, subsystem tracing, onboarding, or codebase documentation.

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。

Product-led growth and customer-base growth for B2B SaaS. Use this skill for self-serve funnel work (activation, time-to-value, free trial vs freemium, PQL definition, in-product upgrade moments, sales-assist triggers), for the self-guided interactive product demo that runs in front of the login wall (demo portfolio and flow design, gated vs ungated policy, demo seed data and privacy, keeping a published demo in sync with the shipping product, step-level demo analytics), and for growing revenue from existing customers (adoption, expansion, churn-save, the self-serve cancel flow and failed-payment recovery, renewal marketing, net revenue retention, and champion tracking: watching the people who bought and used you at each customer, confirming a job change from evidence, and running both plays a move fires, the seat they left and the account they joined). Also triggers on: PLG, product-led growth, activation, aha moment, time to value, free trial, freemium, PQL, product qualified lead, onboarding, self-serve, customer marketing, expansion revenue, upsell, cross-sell, churn, retention, NRR, renewal, cancel flow, cancellation flow, save offer, exit survey, pause subscription, dunning, failed payment recovery, involuntary churn, people keep canceling, champion tracking, job change signals, job change alerts, our champion left, our champion changed jobs, customer alumni, former customers who moved to a new company, interactive demo, self-guided demo, product tour, click-through demo, demo automation, demo library, should our demo be gated, ungated demo, demo without a sales call, our demo is out of date, demo shows the old UI, put a demo on our homepage, demo completion rate, demo drop-off, try before you talk to sales.

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。

Provide constructive, evidence-based research mentoring feedback on student manuscripts, proposals, analyses, code, figures, and presentations. Use for advisor-style review that teaches the next improvement without impersonating an advisor or making unsupported scientific judgments.

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。

Develop research proposals with solicitation alignment, reviewer-focused logic, evidence-bounded preliminary results, milestones, risks, and compelling figures. Use for federal, foundation, equipment, partnership, or internal research proposals.

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 when a task needs the judgment of a tenure-track/tenured Education Professor in a teacher-preparation program — designing a licensure course unit against InTASC/CAEP standards, deciding whether a candidate's borderline edTPA score needs a targeted or full retake, triaging a failing student-teaching placement, or assembling CAEP self-study evidence for reaccreditation.

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 when a task needs the judgment of a Digital Forensics Analyst — capturing volatile evidence before it's lost, creating and hash-verifying a forensic disk image, documenting chain of custody from point of seizure, correcting for clock skew and timezone mismatches when building a cross-source timeline, or identifying anti-forensic activity (log wiping, timestomping) in an investigation.

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 when a task needs the judgment of a correctional officer or jailer — scoring an inmate-classification instrument, deciding a use-of-force response level, running a cell/contraband search, preparing evidence for a disciplinary hearing, or screening an inmate for suicide/mental-health crisis risk.

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。

Drive a failing GitHub Actions run to green in as few CI runs as possible, with a bounded fix-critique-commit-push-recheck loop that batches every evidenced fix into each push. Use when the user supplies a GitHub Actions run URL or run ID and wants the failure fixed, or asks to "make CI green", "fix the failing workflow/build/tests", "fix the red build", or to keep iterating on a branch or pull request until its checks pass. Pulls run results and failed-job logs through the gh CLI, and sends every fix plan to the rubber-duck reviewer before any code is touched.

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 for BayeSED3 SED work — galaxy or AGN fitting, prior setup, Results and posterior plots, Bayesian evidence or model-configuration comparison, MultiNest or advanced run modes (AB mag, phot/spec-only). Trigger immediately on vague asks like "how do I fit this galaxy?"

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 when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

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。

Shared in-workflow quality gates for code/PR skills — the gate model, trust tiers, and the three primitives (evidence-before-done, independent judge, anti-gaming). DO NOT TRIGGER directly — referenced by consumer skills via relative path.

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。

Conduct digital forensics investigations — evidence acquisition, timeline analysis, and court-ready documentation.

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。

Systematic drug repurposing — computational screening, evidence triangulation, and validation strategy.

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。

Evidence-first academic research workflow for topic ideation, scholarly search, paper reading, literature and systematic reviews, study and experiment design, statistics and data analysis, scientific figures, manuscript drafting and polishing, citation checks, peer review, rebuttals, submission packages, theses, and paper-to-presentation work. Use when an agent must plan, execute, audit, write, revise, or package research while keeping claims traceable to verified sources, data, analysis, or official requirements.

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。

Compiles binary analysis findings into structured reports — correlates facts from triage, static, and dynamic phases, validates hypotheses against evidence, and produces traceable documentation. Use when ready to summarize findings, generate a report, document what a binary does, or prepare results for handoff or archival.

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。

Analyze an incident response program for playbook coverage, MTTR optimization opportunities, evidence collection readiness, root cause analysis quality, and post-incident review effectiveness. Triggers: building a SOC, assessing IR maturity, optimizing detection-to-recovery timelines.

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。