Skills 目录 · 第 43 页

Prepare a Build in Public proof brief from supplied build, test, and release receipts before drafting a public progress update. Reconcile mixed revisions, baseline comparisons, and disclosure limits into a private claim ledger and a separate candidate fact packet. Does not select angles, write posts, approve exports, or publish.

Preserve one raw idea, file, link, transcript, or request in a project inbox with provenance and minimal handling. Use when material first arrives and must be captured before interpretation, grouping, scoping, or promotion. Do not use for batch triage or lifecycle decisions.

OverKill Hill P³ offline celestial data engine. Use when implementing or reviewing moon-phase, zodiac-season, Mercury-retrograde, or upcoming lunar-event features in JavaScript or TypeScript. Also activate when a UI needs display-grade night-sky data without a network request. Preserve the repo's exact functions and return shapes, use the bundled deterministic implementation, and validate date data with the supplied scripts.

OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventorying, normalizing, reconciling, or incorporating ChatGPT project threads, conversation exports, or complete chat histories into a repository. Also activate when a user needs a lossless thread archive, project-to-export crosswalk, provenance ledger, or public-safe distillation workflow. This is the authoritative capture and reconciliation process for ChatGPT project material in this repo -- use it even when the user asks only to "save", "review", or "summarize" a large set of threads.

OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventorying, normalizing, reconciling, or incorporating ChatGPT project threads, conversation exports, or complete chat histories into a repository. Also activate when a user needs a lossless thread archive, project-to-export crosswalk, provenance ledger, or public-safe distillation workflow. This is the authoritative capture and reconciliation process for ChatGPT project material in this repo -- use it even when the user asks only to "save", "review", or "summarize" a large set of threads.

Create a Cloudflare Worker that proxies API calls from a static frontend to a keyed API, keeping the API key server-side. Use when a client-only app (GitHub Pages, Netlify, Cloudflare Pages) needs to call an API that requires an API key — and exposing that key in the JavaScript bundle is unacceptable. Covers Worker code, CORS headers, secret storage, and the client-side fetch pattern. Verify current Cloudflare pricing, quotas, and product behavior from official documentation before presenting them as guarantees.

Set up or refresh a private career-coaching engagement brief from provider correspondence, intake status and meeting notes. Use for outplacement service terms, sharing questions, portal checkpoints or coaching closeout. Individual applications and generic meeting minutes have separate owners.

Receive or prepare a staged conversation-context transfer and verify the destination read-back. Use for numbered transfer blocks, "continue this in another project", or a read-only CHAT-to-WORK pilot. Preserve user intent, proposal status, historical authority, gaps, and privacy. This is conceptual continuation, not a lossless archive or permission to resume old requests.

Design, author, evaluate, and package a reusable Microsoft Copilot Studio agent skill. Use when a task-specific capability must be created or shared across Copilot Studio agents powered by the GitHub Copilot harness. Do not use for Cowork packages, SharePoint site skills, GitHub repository skills, agent identity, knowledge-source design, or tool/connector implementation alone.

Find and reconcile the user's commitments across an agreed set of email and meeting sources. Use when preparing an accountable follow-up list, checking promises, or identifying open commitments. Do not assign commitments, send reminders, create tasks, or alter records without explicit approval.

Build a realistic personal execution brief from an agreed day's priorities, calendar, and commitments. Use when planning today, resolving calendar conflicts, or choosing the next action. Do not schedule, send, delegate, or alter tasks or calendar items without explicit approval.

Draft a durable decision record from an agreed discussion or source set. Use when capturing a decision, rationale, alternatives, trade-offs, owners, and follow-ups. Do not declare a decision made, update a register, or communicate it without explicit approval.

Critique a draft against an explicit audience, purpose, quality bar, and risk checklist. Use when reviewing a document, presentation, memo, or proposal for clarity, structure, evidence, and safe communication. Do not rewrite, send, share, or approve the document without explicit direction.

Propose a safe folder, naming, and retention cleanup plan for selected files. Use when reviewing document sprawl, duplicate candidates, folder structure, or records-retention questions before any file moves. Do not move, rename, delete, share, or change retention labels without explicit approval.

Triage a Microsoft 365 inbox into a prioritized, reviewable work queue. Use when organizing email, identifying follow-ups, preparing reply drafts, or separating urgent messages from newsletters and FYI. Do not use to send, delete, archive, unsubscribe, or create rules without explicit approval.

Turn an agreed meeting record into a reviewable decision and action closeout. Use when capturing decisions, owners, due dates, open questions, and follow-up drafts after a meeting. Do not send, post, create tasks, or modify calendars without explicit approval.

Prepare a concise meeting brief from an agreed calendar event and relevant Microsoft 365 context. Use when gathering agenda, attendees, open decisions, and pre-read material for a meeting. Do not schedule, update, invite, message, or send material without explicit approval.

Create a current, source-linked project context pack from selected Microsoft 365 material. Use when preparing a project brief, handoff, onboarding packet, or status orientation. Do not search an unbounded tenant, share material, or alter files without explicit approval.

Build a source-linked research evidence log with confirmed, inferred, and unknown claims. Use when preparing a research brief, comparison, or decision memo from agreed sources. Do not treat search snippets as proof, publish a conclusion, or access sources outside the agreed boundary without approval.

Design, author, evaluate, and package a task-focused Microsoft Copilot Cowork skill. Use when converting a recurring personal Microsoft 365 workflow into a Cowork SKILL.md or M365 app-package skill. Do not use for SharePoint site skills, Copilot Studio agent skills, GitHub Copilot repository skills, or connector development alone.

Draft a source-grounded stakeholder update for review from an agreed project, time window, and audience. Use when summarizing status, decisions, risks, milestones, or asks for stakeholders. Do not send, post, share, or represent unverified information as fact without explicit approval.

Create a personal weekly review from an agreed Microsoft 365 work window. Use when summarizing commitments, completed work, open loops, calendar load, and priorities for next week. Do not schedule, send, delegate, delete, or modify tasks or files without explicit approval.

Compare shared themes across Judaism, Christianity, and Islam using 20 seeded passage sets, neutral bridging notes, and the ARE proportional-representation rule. Use for side-by-side scripture comparisons, interfaith education, neutral common-ground explanations, comparison UI work, or requests about what these traditions share. Do not use it to rank traditions, prove theological priority, or invent a parallel where none is established.

Assess an incomplete or newly proposed Custom GPT concept for build readiness. Use when a user has a GPT idea, partial notes, pasted conversation, draft instructions, knowledge files, or an unfinished GPT and needs an evidence inventory, explicit gaps, targeted elicitation, a readiness score, or a structured handoff to okhp3-custom-gpt-builder.

OverKill Hill P³ daily oracle workflow. Use when building or reviewing a stable reading that combines a tarot card, optional zodiac horoscope, and an AI message. Also activate for daily insight, affirmation, card-draw, or consistent word-of-the-day features in a client-only app. Preserve the repo's ISO cache key, deterministic fallback, graceful degradation, and direct-browser security warning; do not add a backend or proxy to this repository.

OverKill Hill P³ database cartographer. Reverse-engineers and documents the live structure of Postgres, MySQL/MariaDB, MS SQL Server, SQLite, Oracle, and Microsoft Access databases via SQLAlchemy reflection or the right engine driver, producing a normalized schema inventory, a severity-classified (P1/P2/P3) diff against a locked design spec, and a Mermaid ER diagram handed to okhp3-mermaid-*/mermaid-diagrams for rendering. Use when asked to reverse-engineer, interrogate, document, or audit an existing database; verify a live build against a schema spec or data dictionary; generate an ER diagram from a real database connection; or check for schema drift. Also activate on "what does this database actually look like," "document this database," "audit against the spec," or "reflect this database's structure." Read-only by design -- not a data-quality profiler, not a migration generator, never writes to the target database.

Record decision-relevant evidence for detection, approval, response, and review decisions. Use when an agentic security workflow needs auditability or forensic reconstruction. Do not capture secrets or private model reasoning.

Author and validate decision models from PNS decision points using DMN-aligned rule tables. Use this skill when the PNS contains three or more gateway decision points that warrant a structured decision table; when the user asks to document business rules as decision logic, build a DMN table, or make decision criteria explicit. This is a recommended extension skill triggered automatically when okhp3-visual-process-modeling identifies three or more gateways. Do not use it for fewer than three decision points — document those inline in the PNS decision_points section instead. Produces a decision-model YAML and a human-readable DMN rule table.

Author and validate decision models from PNS decision points using DMN-aligned rule tables. Use this skill when the PNS contains three or more gateway decision points that warrant a structured decision table; when the user asks to document business rules as decision logic, build a DMN table, or make decision criteria explicit. This is a recommended extension skill triggered automatically when visual-process-modeling identifies three or more gateways. Produces a decision-model YAML and a human-readable DMN rule table.

Draft a Discord reply to a supplied message, thread, or forum conversation. Use when the user wants to answer, clarify, or contribute to an existing Discord discussion. It preserves channel and thread context, avoids unauthorized pings, and returns a draft only. Do not use for a new message, a new thread, direct messages, or sending content.

Draft a new Discord message, forum post, or thread opener for a named server destination. Use when the user asks to post an announcement, update, question, or discussion opener in Discord. It checks server, channel, and ping context, uses Discord-friendly Markdown when useful, and returns a draft only. Do not use for replies, direct messages, or sending content.

Plan and facilitate structured elicitation sessions using BABOK v3 interview and workshop techniques. Use this skill when you need to gather process knowledge from subject matter experts; when the user wants a question plan before an interview or workshop; when elicitation is incomplete and gaps need targeted follow-up; when they say \"help me interview the process owner\", \"prepare questions for the workshop\", or \"what should I ask to fill in the missing steps\". Use only when a PIR already exists and has gaps — for first-pass process discovery from scratch, use okhp3-process-intake-and-scope instead. Produces a question plan and elicitation notes template.

Plan and facilitate structured elicitation sessions using BABOK v3 interview and workshop techniques. Use this skill when you need to gather process knowledge from subject matter experts; when the user wants a question plan before an interview or workshop; when elicitation is incomplete and gaps need targeted follow-up; when they say "help me interview the process owner", "prepare questions for the workshop", or "what should I ask to fill in the missing steps". Produces a question plan and elicitation notes template.

Validate emerging agentic threat hypotheses and defensive controls in a disposable synthetic laboratory. Use when testing whether a pattern affects a representative architecture and whether a mitigation works. Do not operate against production or develop deployable attack tooling.

Review a document, report, spreadsheet, hypothesis, decision memo, or Agent Skill with independent evidence review, conditional disruption, and bounded adjudication. Use for claim ledgers, falsification passes, and release gates. Do not replace required statistical, legal, medical, financial, or security authority.

Classify consequential claims as confirmed, inferred, proposal, or unknown and keep those tiers visible. Use for cross-machine or cross-agent comparisons, conflicting sources, handoffs, decision records, and recommendations from incomplete evidence. Do not substitute it for mechanical validation or source research.

Draft a Facebook comment or reply to a supplied post and conversation. Use when the user wants to comment on Facebook, reply in a group discussion, or respond beneath a Page or profile post. It respects the original context and visibility boundary, then returns a draft only. Do not use for a new post or publication.

Draft a Facebook post for a named profile, Page, group, or event surface. Use when the user asks to write a Facebook update, Page post, or group post. It confirms destination and audience before drafting, preserves the supplied context, and returns a draft only. Do not use for comments, scheduling, or publication.

Design a target-state process and a structured change strategy from a gap analysis. Use this skill when the user wants to redesign a process after gaps have been identified; when they ask \"what should the process look like\", \"how do we fix this\", \"design the to-be process\", or \"build a change plan\". This is a recommended extension skill — use after okhp3-process-gap-exception-analysis has produced a gap analysis. Do not use it to document only the current state — that is okhp3-as-is-process-capture; this skill designs what should change, not what exists today. Scope firewall applies: never include employer-proprietary constraints without explicit user authorisation. Produces a future-state process artifact and a change strategy document.

Design a target-state process and a structured change strategy from a gap analysis. Use this skill when the user wants to redesign a process after gaps have been identified; when they ask "what should the process look like", "how do we fix this", "design the to-be process", or "build a change plan". Produces a future-state process artifact and a change strategy document. This is a recommended extension skill — use after process-gap-and-exception-analysis has produced a gap analysis. Scope firewall applies: never include employer-proprietary constraints without explicit user authorisation.

Audit and safely maintain local GitHub clones, compare files and branches with origin/main, review GitHub notifications, verify pull requests and CI, and prune completed branches. Use for recurring GitHub mirror hygiene, notification triage, repository reconciliation, scheduled daily or weekly maintenance, or an explicitly authorized merge or cleanup. Do not use it to infer permission to commit, push, merge, close, delete, or mark notifications done.

Triage and maintain GitHub notifications by finding the underlying issue, pull request, review, check, deployment, or branch problem; group duplicate failures; delegate bounded repairs to Dependabot, GitHub Copilot, or Actions when appropriate; verify the result; and mark only verified threads done. Use for GitHub notification cleanup, recurring CI loose ends, PR follow-up, repository maintenance, scheduled notification cleanup that appears stopped, or safe branch-pruning review. Do not use for blind bulk deletion, unreviewed merges, or autonomous publication.

Design, author, evaluate, and install-plan a task-focused GitHub Copilot Agent Skill. Use when creating a repository or personal GitHub Copilot SKILL.md for coding, review, maintenance, or repository workflows. Do not use for Cowork, SharePoint, Copilot Studio, or general agent instructions.

OverKill Hill P³ Glee-fully SPA styling. Use when a user wants a Glee-fully application, documentation artifact, presentation, or image brief aligned to the approved Glee-fully profile. Also activate when a target needs retro-bright, warm, emotionally intelligent tooling. This specialization applies the approved local profile and does not substitute OverKill Hill or AskJamie styling.

OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventorying, normalizing, reconciling, or incorporating ChatGPT project threads, conversation exports, or complete chat histories into a repository. Also activate when a user needs a lossless thread archive, project-to-export crosswalk, provenance ledger, or public-safe distillation workflow. This is the authoritative capture and reconciliation process for ChatGPT project material in this repo -- use it even when the user asks only to "save", "review", or "summarize" a large set of threads.

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.

Design, author, audit, and canon-seal portable Glee-fully Agent Skills across the Trunk, Branch, Twig, Function, and Function-ette hierarchy. Use when converting a Glee-fully Tool or Tool-ette into SKILL.md, selecting Persona Density, defining a Twig's Best for boundary, or reviewing a skill for scope, sibling, logic, and release readiness.

Assess an incomplete or newly proposed Glee-fully Tool or Tool-ette for build readiness. Use when a user has a Glee-fully GPT idea, partial notes, pasted conversation, draft instructions, knowledge files, or unfinished assistant and needs an evidence inventory, explicit gaps, targeted elicitation, a readiness score, or a handoff to okhp3-glee-fully-gpt-builder.

Create governed FoundRy child repositories from Custom GPTs, Gemini Gems, Copilot agents, prompt bundles, Notion concepts, research notes, or prototype ideas. Use whenever the user wants to migrate an AI capability into GitHub, standardize a repo, create a child repo scaffold, or convert platform-specific AI work into a reusable capability package.