「verified」の検索結果

Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes. Use when: (1) a scoring pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the weak label was already low (κ < ~0.6). Core check: if gold POSITIVES share the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).

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。

Strict test-driven development for behavior changes. Requires verified RED before production code, minimal GREEN, and refactor only after passing tests.

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。

Email marketing operations and automation for B2B SaaS. Use this skill for newsletter strategy, email automation sequences, lifecycle campaigns, nurture workflows, onboarding sequences, deliverability optimization, email copywriting, lead scoring, marketing automation platform setup, and cold-email sending infrastructure — secondary sending domains, SPF/DKIM/DMARC, and domain warmup — plus the contact budget: a cross-channel frequency cap across every sender (marketing, sales sequences, customer success, in-app). Also triggers on: email, newsletter, drip campaign, lifecycle, nurture, onboarding sequence, deliverability, email automation, lead scoring, marketing automation, our emails are going to spam, SPF, DKIM, DMARC, sender reputation, sending domain, cold email domains, domain warmup, mailbox setup, blacklist, bounce rate, BIMI, brand logo in inbox, VMC, Verified Mark Certificate, Common Mark Certificate, transactional email, password reset emails going to spam, frequency cap, email fatigue, customers get too many emails, too many messages, sales and marketing both emailing the same person, communication limits, send frequency safeguard, global frequency capping, quiet period, message precedence.

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 Community Health Worker — screening a client for social-determinants-of-health barriers, triaging a referral to housing/food/transportation resources, translating a clinical instruction into a teach-back-verified action plan, or deciding whether a no-show pattern signals disengagement or an unaddressed barrier.

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。

Verify code-review or security-review findings for false positives using deep codebase tracing, framework-aware analysis, and web research. Produces a .verified.md report alongside the original. Use when a review report has been generated and needs independent verification, or when user runs /verify-findings, mentions "verify review", "check false positives", or "validate findings".

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 this whenever the user asks to "open a PR", "ship this", "create the pull request", "make a PR", or once a Vue feature/fix is verified and ready to push. Full lifecycle: branch → commit (commitizen) → issue → draft PR → CI → ready → autonomous monitor loop (fix comments, resolve threads, iterate until CI green + zero unresolved threads). `--perfect` adds a CodeRabbit convergence loop on top. Never works on `main`/`master`, never uses `--no-verify`.

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。

Build a production-ready data API from scratch: scaffold REST endpoints with models and validation, generate integration tests that verify every route, then load test for scalability. Use when you need an API backend, data service, CRUD layer, or microservice with verified correctness and performance.

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。

Verify statistics and claims in blog posts by fetching cited source URLs and checking if the claimed data actually appears on the page. Extracts all load-bearing claims (statistics, product or policy claims, ranking and comparative claims, named sources), validates cited URLs before fetching, and scores match confidence (exact match 1.0, paraphrase 0.7-0.9, not found 0.0). Flags uncited claims as UNVERIFIED. Use when user says "fact check", "verify statistics", "check sources", "validate claims", "factcheck", "source verification".

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 a paid-media client, brand, account, data-source, privacy, and mutation-guardrail profile for Claude Ads. Use for onboarding, initial configuration, brand DNA, API tokens or credential profiles, environment-variable or keychain setup, connecting exports or read adapters, safe native or verified-local installation, curl-pipe-bash install requests, declaring KPIs, or preparing a new advertising project.

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。

Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints; any TTS backend and any video tool (Remotion, HyperFrames, CapCut, ...) work, and how much human oversight to apply is set by the working project's AGENTS.md/CLAUDE.md, not here. Use when the user wants a quick personal narrated video with minimal steps, whether or not they name the tool stack. Do NOT trigger for audio-only podcasts, written episodic content, or heavy multi-format production.

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。

Reconstruct editable LaTeX from PDF content using page-aware extraction and visual comparison. Preserve source evidence, flag uncertain math/tables/citations, and distinguish text extraction, OCR, reconstruction, and verified compilation.

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 Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use when the user asks what Caveman found, where LLM spend goes, why cost or quality changed, which workflows need attention, or asks for a trace or analytics review. Prefer Caveman MCP tools; fall back to CLI JSON.

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 a verified Salesforce research packet into a concise, role-aware learning brief with clear objectives, concept sequencing, worked examples, release caveats, checks for understanding, and citations mapped to claims. Trigger keywords: teach me Salesforce, explain Salesforce concept, create learning brief, Salesforce study guide, role-based lesson. NOT for open-ended source discovery or freshness verification — use architect/salesforce-learning-research first. NOT for generating production metadata or changing an org.

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。

Configuring Salesforce Email-to-Case: Standard vs On-Demand mode selection, routing address setup, email threading via Lightning tokens, auto-response rules, attachment limits, and per-address case field defaults. Trigger keywords: email-to-case, routing address, on-demand email-to-case, email threading, case from email, email agent, routing address setup, Case.settings-meta.xml, EmailToCaseRoutingAddress, emailServicesAddress, isVerified, caseOrigin, enableThreadTokenInBody, useEmailHeadersForThreading, overEmailLimitAction, unauthorizedSenderAction, enableE2CAttachmentAsFile, saveEmailHeaders, newEntityRecordType, casePriority, EmailMessage.EmailRoutingAddressId, auto-response loop. NOT for the wider case layer (queues, escalation rules, case teams, entitlements) - use admin/case-management-setup. NOT for routing case work items to agents after creation - use admin/omni-channel-routing-setup. NOT for the email templates or letterheads themselves - use admin/email-templates-and-alerts.

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。

Handle Chinese mojibake in CMD, .bat/.cmd files, Windows logs, and native command output by using PowerShell to read raw bytes as GBK/CP936, capture command output with an explicit decoder, and convert it to UTF-8/Unicode. Use when text contains 锟斤拷, mojibake, or replacement characters and the source encoding must be verified.

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 a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents — builders never review their own work. Quality decisions are grounded in project context (identity, audience, goals) and established visual/motion design principles. Measurable criteria (text size, contrast, overflow) are verified with tooling, not visual judgment. Use when the user says "make this video", "implement this brief", "build this composition", or provides a video script/brief to implement.

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。

Mechanical consistency check for game design — answers "is the design consistent with itself?" — plus changed-scope impact analysis across all three GDD axes: systems, flows, and content types. Offline and deterministic: greps the facts registry against the documents (numbers, terms, IDs, duplicate & dangling references, roster↔disk, map freshness, Depends 3-way, status/version, AC presence, placeholder leaks, flow & content schema), and from a git diff computes which dependent systems, flows, and content a change affects. Scope is inferred: a named document checks that document; an unverified diff triggers a changed-scope pass; otherwise everything. Use when the user wants a consistency or impact check, e.g. "verify the design", "what did this change affect", "find broken references in the design". Conflicts triage into four tracks; the entailed fixes hand off to /unikit-gd-apply in one pass. This is the mechanical pass — for a subjective "is this design good" quality critique use /unikit-gd-review.

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。

White-box security audit. Blue-teamer and lead red-teamer run in parallel isolation for an independent first pass — neither sees the other's output during reconnaissance. A synthesis step categorizes findings into four prescriptive buckets (anchoring-suppressed, convergent, blue-flagged-unverified, divergent), producing a unified target list. Focused red-teamers then deep-dive each target. Iterates when exploit chains are discovered. Heavy and thorough by design. Advisory only — produces findings and proposes tickets; does not implement remediation.

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。

Converts transparent or solid-background single-color PNG files and SVG files containing one embedded or local PNG into verified path-only SVG output. Removes pure-color backgrounds automatically. Uses Potrace threshold and parameter scans with alpha error metrics to preserve detailed logos, stamps, engravings, and line art. Use when the user asks to convert images to SVG, vectorize PNG, convert bitmap to true SVG, remove embedded raster data from SVG, 图片转矢量, PNG 转 SVG, 真矢量, or 位图描摹.

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 after a verified Decisions harness audit when the user asks to apply safe fixes to harness drift, dead references, stale projected skills, duplicate routing, bloated state files, or invalid local config.

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。

Adversarially verifies DATA_MODEL.md property rows against cited Source files. Use after data-model-documenter when DATA_MODEL.md changed — inventories each property in added/changed catalog sections and classifies VERIFIED / REFUTED / UNVERIFIABLE. Triggers on "verify DATA_MODEL", "check catalog against source", "data model verification".

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 adversarially reviewing a document that makes formal or technical claims — math derivations, physics papers, statistical analyses, benchmark reports, whitepapers. Inventories every equation and quantitative claim, verifies each AS NAMED in the text (never a paraphrase or a neighboring statement), and classifies VERIFIED / REFUTED / UNVERIFIABLE / VACUOUS. Triggers on "check this paper", "verify these claims", "is this derivation right", "review this proof", "audit this benchmark", "does the math hold up". For source-code review see code-review-and-quality; for skill/agent library audits see skill-library-review; for content quality scoring see content-ops.

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。

Capture a solved, verified problem as a durable learning in `docs/solutions/` so the next agent or engineer does not repeat the mistake or redo the investigation, and keep the `CONCEPTS.md` glossary in step. Use after a fix, debugging session, or design decision whose reasoning is not readable from the final code, tests, or existing docs — "document this", "write up what we learned", "capture this learning", "add it to solutions", "that worked, save it for next time". Writes nothing for routine fixes the code already explains. For auditing or cleaning up existing learnings, use `learn-with-docs-refresh`.

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。