Skills 目录 · 第 47 页

Identify and explain likely duplicate SharePoint List records using supplied matching rules. Use when a list owner needs a review queue of duplicate candidates without merging, deleting, or overwriting records. Do not use to treat similar titles as confirmed duplicates.

Normalize SharePoint List intake items into a reviewable, schema-aligned draft. Use when new list items need required-field checks, controlled-value mapping, duplicate flags, or consistent descriptions before they are saved. Do not use to invent missing facts or silently update list items.

Turn unresolved questions and missing-content signals into a reviewable SharePoint List knowledge-gap draft. Use when a site team needs a visible, owned backlog of questions, impact, and proposed source research. Do not use to invent answers, perform external research, or create List items silently.

Turn supplied meeting notes into a reviewable SharePoint List action draft. Use when decisions, owners, due dates, and follow-up actions need consistent fields and duplicate checks before list items are created or updated. Do not use to infer commitments, assign people, or write action records without confirmation.

Create a cited portfolio-health brief from supplied SharePoint List fields and owner-approved health rules. Use when project, initiative, or work-item signals need a consistent executive exception summary. Do not use to invent portfolio status, alter items, or make funding or delivery decisions.

Triage SharePoint List requests into a transparent review queue using supplied routing rules. Use when request items need completeness checks, category suggestions, priority flags, or owner-ready next steps. Do not use to assign people, change status, or route requests without explicit rules and confirmation.

Review a SharePoint List of risks or issues into a ranked, evidence-led exception view. Use when owners, due dates, severity, mitigation, or escalation gaps need a consistent review. Do not use to change risk ratings, assign owners, or make management decisions without approved rules.

OverKill Hill P³ SharePoint List database architecture reviewer. Use when designing, reviewing, or hardening SharePoint Online Lists used as lightweight databases, controlled vocabularies, lookup-backed registries, or CMDB-lite data stores. Also activate when the user asks about list thresholds, indexed columns, lookup relationships, required fields, content types, attachments, offline sync, Quick Edit, SharePoint UI-only build constraints, or whether a SharePoint list setting is safe for database-like use. This is the authoritative SharePoint-list-as-database architecture skill for this repo -- use it even when the user only says "SharePoint list settings" or "list build".

Review a SharePoint List schema, views, indexes, and visible configuration against supplied design rules. Use when a list owner needs a prioritized health report before changing fields, views, or settings. Do not use to alter a list or claim settings that the current host cannot inspect.

Produce a SharePoint List SLA exception watchlist from supplied status, due-date, and service-target rules. Use when a team needs a current, evidence-led view of imminent or breached work. Do not use to invent SLA rules, alter service dates, send alerts, or change records.

Review a SharePoint List of vendors or obligations for supplied expiry, ownership, and compliance-field exceptions. Use when a controlled review needs next-review candidates and evidence without changing agreements or making legal conclusions. Do not use to determine compliance or take action.

Design, author, evaluate, and deploy-plan a personal or site Copilot in SharePoint skill. Use when creating a task-focused SharePoint Library or List SKILL.md. Do not use for Cowork, Copilot Studio, GitHub Copilot, external-system, or custom-code workflows.

Generate a SIPOC table from a validated PNS. Use this skill when the user needs a high-level process summary showing Suppliers, Inputs, Process steps, Outputs, and Customers; when they ask to produce a SIPOC, create a process summary table, or generate a one-page process overview. This is a process-level input/output summary, not a stakeholder engagement register — for who is involved and how to engage them, use okhp3-stakeholder-and-role-mapping instead. Derives directly from PNS process_box and activity_sequence. Produces a sipoc.md Markdown table suitable for presentations, kickoff documents, and governance packs.

OverKill Hill P³ skill cataloger. Inventory and validate repository-local Agent Skills, then safely regenerate a marked README catalog and machine-readable catalog metadata. Use when asked to list, audit, version-check, validate, or refresh skills under .agents/skills/, or to index a distribution repository’s root family folders. Choose catalog mode for a project surface and explicit --full mode for a distribution index; use --check or --dry-run when no file changes are authorized.

Find, verify, compare, and route to project-local, installed, runtime, or plugin-provided agent skills. Use when the user asks what skills exist, how to invoke one, or when the correct reusable workflow is unclear. Do not use it to install unavailable capabilities without an explicit request.

Create, audit, test, and improve portable Agent Skills with evidence-backed instructions, progressive disclosure, risk-based evaluations, and release checks. Use when authoring a new SKILL.md, improving an existing skill, designing or grading evaluations, diagnosing weak trigger behavior, or synchronizing a skill across repositories. Also activate when a workflow should become a reusable skill or a skill must improve itself without making unsupported quality claims. This is the authoritative OKHP3 authoring and skill-evolution workflow.

Promote and synchronize a project-local Agent Skill into a portable, reviewable distribution package. Use when a skill under .agents/skills needs a publication mirror, provenance record, canonical family assignment, or a safe handoff into OKHP3/skillz. Also activate when multiple SKILL.md copies must be compared or reconciled. Do not use for generic repository publishing.

Draft a new Slack channel message for a supplied workspace destination. Use when the user needs a clear announcement, update, question, or handoff for a named Slack channel. It returns formatted draft text only and does not send, schedule, direct-message, mention broadly, attach files, react, or change workspace or channel settings.

Draft a Slack thread reply from a supplied channel, parent message, and conversation context. Use when the user needs a grounded response that stays in a named Slack thread. It returns a draft only and does not send, forward to a channel, direct-message, react, save, pin, schedule, or change notifications.

Generate Standard Operating Procedures (SOPs) and work instructions from a validated PNS. Use this skill when the user needs to produce a human-readable procedure document from a process narrative; when they ask to write an SOP, create work instructions, generate a procedure, or produce an ISO 9001-compliant process document. The generated SOP follows ISO 9001 §4.4.2 documented information requirements and embeds its own RACI summary — use okhp3-raci-governance-matrix instead only when a standalone, wider-audience RACI document is needed. Produces sop.md and optional work-instructions.md for each role.

Produce research notes, comparisons, or recommendations with traceable sources, retrieval dates, and explicit uncertainty. Use when work depends on external facts, changing information, technical documentation, or claims that should be verified. Do not use when the needed evidence is already fully available in local files.

Derive and validate a structured stakeholder register from a completed Process Intake Record. Use this skill when you have a PIR from okhp3-process-intake-and-scope and need to identify all affected parties, classify their roles, assess influence and interest, and define engagement strategies. Use when the user asks who is involved in a process, needs a RACI-ready role list, wants to understand stakeholder impact, or needs an engagement plan before narrative authoring begins. Produces a stakeholder engagement register, not a one-page process summary — for that, use okhp3-sipoc-generation instead.

Reconstruct a successful one-off and design tests for a repeatable success class. Use for "bottle lightning", "it worked once but we lost the recipe", or separating essential conditions from incidental details. Produce an evidence ledger and a proposed re-strike protocol, not proven causality, an exact replay guarantee, or autonomous experiments.

Verify provenance and integrity of agent packages, models, tools, configurations, and deployments. Use when onboarding, releasing, changing, or investigating an agentic component. Do not invent attestations or treat a checksum as proof of trust.

Find and resume an interrupted task in its original conversation. Use when restarting an archived thread, recovering unfinished agent work, or checking whether a dispatched restart actually completed. Excludes new-task creation and handoff-only writing.

Draft a Microsoft Teams channel post for a supplied team and channel. Use when the user needs a clear new post for a named Teams channel, including a subject, body, supplied links, and a permission-aware handoff. It returns draft text only and does not send, create a channel, mention broadly, attach, react, pin, moderate, or change Teams settings.

Draft a Microsoft Teams channel-thread reply from supplied parent-post and channel context. Use when the user needs a grounded reply within a named Teams channel conversation. It returns a reviewable draft only and does not send, start a new post, react, attach, edit, delete, moderate, or change notification or channel settings.

Draft a Telegram channel post from supplied broadcast-channel context. Use when the user needs a concise channel message, media-caption handoff, and review checklist for a named Telegram channel. It prepares text only and does not send, schedule, pin, enable comments, change channel settings, or manage subscribers or administrators.

Draft a Telegram group reply from supplied group, parent-message, and thread context. Use when the user needs a grounded response in a named Telegram group or topic. It returns a draft only and does not send, direct-message, mention, react, pin, delete, report, moderate, invite, remove, or change group permissions or settings.

Extract pasted or uploaded AI chat threads into standalone, actionable Markdown. Use when the user wants to evacuate context from ChatGPT, Claude, Gemini, Perplexity, Microsoft Copilot, Grok, Mistral Vibe, an unknown AI platform, or a mixed transcript; preserve goals, decisions, reasoning, next actions, prompts, code, files, images, citations, canvases, artifacts, diagrams, and provenance; resolve uncertain speaker boundaries; or requests rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for complete, partial, flattened, exported, or turn-by-turn human-supplied captures. Do not use for logging into or scraping source services, lossless transcript archival, ordinary short-form summaries, or platform support questions that do not require a durable handoff artifact.

Extract pasted or uploaded AI chat threads into standalone, actionable Markdown. Use when the user wants to evacuate context from ChatGPT, Claude, Gemini, Perplexity, Microsoft Copilot, Grok, Mistral Vibe, an unknown AI platform, or a mixed transcript; preserve goals, decisions, reasoning, next actions, prompts, code, files, images, citations, canvases, artifacts, diagrams, and provenance; resolve uncertain speaker boundaries; or requests rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for complete, partial, flattened, exported, or turn-by-turn human-supplied captures. Do not use for logging into or scraping source services, lossless transcript archival, ordinary short-form summaries, or platform support questions that do not require a durable handoff artifact.

Extract manually supplied ChatGPT conversations into standalone, actionable Markdown. Use when the user pastes a ChatGPT chat, Project thread, Canvas, Deep Research report, search answer, prompt-response sequence, generated file or image reference, or export excerpt and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, turn-by-turn transfers, flattened UI text, and uncertain roles. Do not use for account login or scraping, wholesale Project migration, Custom GPT design, OpenAI API support, ordinary summaries, or lossless transcript archival.

Extract manually supplied ChatGPT conversations into standalone, actionable Markdown. Use when the user pastes a ChatGPT chat, Project thread, Canvas, Deep Research report, search answer, prompt-response sequence, generated file or image reference, or export excerpt and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, turn-by-turn transfers, flattened UI text, and uncertain roles. Do not use for account login or scraping, wholesale Project migration, Custom GPT design, OpenAI API support, ordinary summaries, or lossless transcript archival.

Extract manually supplied Claude conversations into standalone, actionable Markdown. Use when the user pastes a Claude chat, Project excerpt, Artifact, Research or web-search output, prompt-response sequence, uploaded-file reference, or export excerpt and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, turn-by-turn transfers, flattened UI text, Artifact versions, and uncertain roles. Do not use for Claude account access or scraping, ordinary summaries, unrelated Anthropic API support, or lossless transcript archival.

Extract manually supplied Claude conversations into standalone, actionable Markdown. Use when the user pastes a Claude chat, Project excerpt, Artifact, Research or web-search output, prompt-response sequence, uploaded-file reference, or export excerpt and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, turn-by-turn transfers, flattened UI text, Artifact versions, and uncertain roles. Do not use for Claude account access or scraping, ordinary summaries, unrelated Anthropic API support, or lossless transcript archival.

Extract manually supplied Microsoft Copilot and Microsoft 365 Copilot chats into standalone, actionable Markdown. Use when the user pastes a Copilot chat, Work or Web-grounded answer, Copilot Page, agent output, prompt-response sequence, or references to files, emails, meetings, people, or tenant sources and wants goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for flattened or turn-by-turn captures. Do not use for Microsoft tenant, Graph, SharePoint, Teams, Outlook, or OneDrive access; GitHub Copilot coding chats; ordinary summaries; or lossless archival.

Extract manually supplied Google Gemini conversations into standalone, actionable Markdown. Use when the user pastes a Gemini chat, Gem output, Canvas, Deep Research report, Workspace-grounded answer, file analysis, prompt-response sequence, image or audio reference, or export excerpt and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, turn-by-turn transfers, flattened UI text, and uncertain roles. Do not use for Google account or Drive access, ordinary summaries, Gemini API support, or lossless transcript archival.

Extract manually supplied xAI Grok conversations into standalone, actionable Markdown. Use when the user pastes a Grok chat, X-grounded answer, DeepSearch or reasoning output, prompt-response sequence, source list, connector result, image, video, file, or Canvas reference and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, flattened UI text, and uncertain roles. Do not use for xAI or X account access, live social research by itself, API support, ordinary summaries, or lossless transcript archival.

Extract manually supplied Mistral Vibe or former Le Chat conversations into standalone, actionable Markdown. Use when the user pastes a Vibe Work, Chat, or Code thread, Canvas, plan, tool trace, approval request, connector result, file analysis, prompt-response sequence, or export excerpt and wants its goals, reasoning, decisions, reusable assets, next actions, provenance, and missing sidecars preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, flattened UI text, and uncertain roles. Do not use for Mistral account or connector access, Vibe operation, API support, ordinary summaries, or lossless transcript archival.

Extract manually supplied Perplexity conversations into standalone, actionable Markdown. Use when the user pastes a Perplexity Thread, Space excerpt, Research or Create output, source-rich answer, prompt-response sequence, uploaded-file reference, or export excerpt and wants its goals, reasoning, decisions, citations, reusable assets, next actions, provenance, and missing sources preserved at rapid, balanced, comprehensive, essential, substantial, exhaustive, scan, distill, or catalog depth. Use for control-all copies, turn-by-turn transfers, flattened source cards, and uncertain roles. Do not use for Perplexity account access or live research, citation verification by itself, ordinary summaries, API support, or lossless archival.

Synthesize dated threat signals into coherent defensive narratives and validation priorities. Use when multiple observations need clustering, source comparison, or risk framing. Do not turn a narrative into an exploit recipe or unsupported attribution.

Validate whether a proposed agentic threat pattern affects a representative synthetic architecture and whether controls respond. Use when a threat hypothesis is ready for bounded laboratory review. Do not test production, real credentials, real data, or uncontrolled targets.

Draft a TikTok comment or reply from supplied post and conversation context. Use when the user wants a context-aware response under a named TikTok post. It returns reviewable text only and does not post, delete, report, block, follow, message, manage filters, or automate engagement.

Draft a TikTok video or photo post caption and publishing handoff from supplied material. Use when the user needs post text, on-screen-text notes, and a review checklist for a named TikTok post. It prepares a draft only and does not record, edit, upload, set privacy, schedule, or publish.

Fetch, compute, and format religious observance calendars for the three in-scope Abrahamic traditions of the Abrahamic Reference Engine: Judaism, Christianity, and Islam. Use this skill whenever an agent needs to retrieve religious holiday data, generate iCalendar (.ics) output, look up holiday descriptions for cross-tradition audiences, or produce a unified observance event list. Covers Hebcal API (Jewish), AlAdhan API (Islamic), TypeScript Computus algorithm (Christian -- Western and Orthodox), Wikipedia summary fetching for event descriptions, .ics file generation, emoji assignments, holiday filter lists, and session caching strategy. All data sources are free, public, and require no API key. Zero cost. MIT license. Also activate when a user asks to "add holidays to my calendar app", "download religious observances as .ics", "show Jewish/Islamic/Christian holidays for a year", or compute Easter dates -- including when they ask for "all three faiths" or any single tradition's observa

Reference ARE scope, canon, denominations, translations, Pew US shares, and free API providers for Judaism, Christianity, and Islam. Use before answering canon or denomination questions, choosing a translation, writing scripture fetch code, checking whether a tradition is in scope, or explaining LDS, Catholic, Orthodox, Jewish, or Islamic reference coverage. Preserve denominational variation, source dates, licensing, and known API gaps.

Translate owned plainspoken text artifacts one way from United States English (en-US) to Germany German (de-DE), preserving source voice, meaning, protected tokens, structure, and the pair-specific dictionary. Use only after any specialist register has separately been mediated into plain en-US. Do not use for another pair, a register conversion, reverse translation, generic copyediting, or machine-only publication.

Adapt owned plainspoken text artifacts one way from United States English (en-US) to British English (en-GB), preserving source voice, meaning, protected tokens, and structure while changing spelling, vocabulary, and locale conventions that genuinely differ. This is a same-language regional adaptation, not a bilingual translation. Use only after any specialist register has separately been mediated into plain en-US. Do not use for another English locale (en-AU, en-CA, en-IE), a bilingual language pair, a register conversion, reverse adaptation, generic copyediting, or machine-only publication.

Translate owned plainspoken text artifacts one way from United States English (en-US) to Spain Spanish (es-ES), preserving source voice, meaning, protected tokens, structure, and the pair-specific dictionary. Use only after any specialist register has separately been mediated into plain en-US. Do not use for another pair, a register conversion, reverse translation, generic copyediting, or machine-only publication.

Translate owned plainspoken text artifacts one way from United States English (en-US) to Mexican Spanish (es-MX), preserving source voice, meaning, protected tokens, structure, and the pair-specific dictionary. Use only after any specialist register has separately been mediated into plain en-US. Do not use for another pair (including es-ES or es-419), a register conversion, reverse translation, generic copyediting, or machine-only publication.