tristanmanchester

Audit or design websites, docs, apps, CLIs/TUIs, APIs, SDKs, MCP/A2A agents, Agent Skills, and repos so AI agents can discover, understand, safely operate, verify, and recover from real tasks. Use for agent-readiness audits, action/context parity reviews, AGENTS.md/llms.txt/OpenAPI/API catalog/MCP/A2A/tool design, CLI JSON/non-interactive ergonomics, shared workspaces, prompt-native features, evals, templates, and implementation roadmaps.

Coach users to plan, create, rehearse, and deliver high-impact presentations, talks, keynotes, pitches, board updates, scientific or technical talks, lectures, webinars, demos, and slide decks. Use when the user is preparing a presentation, wants a stronger story or slide flow, needs speaker notes or rehearsal and Q&A practice, is anxious about presenting, or asks how to make a talk clearer, more persuasive, memorable, engaging, accessible, or executive-ready.

Audit and harden OpenClaw deployments and interpret `openclaw security audit` findings. Use when the user wants to secure OpenClaw, review gateway exposure/auth/reverse proxies/Tailscale Serve or Funnel, check DM/group access (pairing, allowlists, mention gating, `session.dmScope`), minimise tool permissions and sandboxing, review plugins/skills/secrets/transcripts/log retention, or lock down Docker/macOS/laptop/EC2 installs. Not for generic OS, Docker, or cloud hardening unrelated to OpenClaw.

Use this skill when the user needs to design, critique, redesign, audit, generate, code, or explain quantitative graphics: charts, dashboards, tables, maps, scientific/statistical figures, visual evidence, or chart specifications. It helps choose display forms, avoid misleading encodings, compute lie factors, inspect CSV structure, generate simple SVG charts, check color contrast, and produce Tufte-informed but non-formulaic recommendations. Do not use for decorative illustration or general data cleaning unless a quantitative display is involved.

Generates genuinely novel, useful ideas for products, businesses, features, campaigns, names, research directions, and process redesign. Use when the user asks to brainstorm, ideate, improve a weak concept, escape generic answers, find differentiated options under real constraints, or turn a vague opportunity into a shortlist of strong concepts with wedges and tests. Preserves diversity with independent idea pools, analogy transfer, contradiction solving, critique-and-repair, and reality checks. Do not use for simple rewriting, proofreading, or purely factual research.

Use this skill when the user wants to integrate with, call, debug, or operate the Resend API or official SDKs/MCP tooling. Covers sending and scheduling emails, batch sends, templates, domains and DNS verification, API keys, contacts, segments, topics, broadcasts, inbound email, webhooks, receiving attachments, and Resend workflows/events. Also use it when the user mentions Resend, resend.emails.send, verified domains, email.received, broadcast campaigns, template publishing, or needs help choosing between single email, batch, broadcast, inbound, or workflow patterns.

Use this skill when an AI agent needs to manage, audit, report on, create, pause, update, or troubleshoot Meta/Facebook/Instagram ads through Meta's official Ads CLI (`meta ads ...`). It is designed for any shell-capable agent, not just OpenClaw. It focuses on safe command planning, JSON output, confirmation gates, read-before-write behaviour, paused-by-default launches, reporting workflows, datasets/pixels, catalog/product operations, and failure handling.

Use this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.

Recall what the user copied on this Mac via the local clipmem archive — text, commands, URLs, file paths, HTML, images, PDFs. Triggers on requests like "what was that command I copied?", "the URL I copied from Safari", "find that snippet before I restarted", or any paraphrase involving copy, paste, or clipboard. Offers ranked recall, chronological timeline, lexical / FTS search, raw-byte export for binary content, cursor pagination, and filters by app, kind, time window, and content shape. Use before reaching for generic web or repo search whenever the user is trying to recover something they previously had on the clipboard.

Recall what the user copied on this Mac via the local clipmem archive: exact text, commands, SQL, URLs, file paths, HTML, images, and PDFs. Trigger on requests like "what was that command I copied?", "paste back that SQL", "the URL I copied from Safari", "show me what I copied from Xcode today", "find the snippet/path/link from before I restarted", and indirect paraphrases about clipboard history or recovering copied content. Prefer this over web, repo, or filesystem search only when the target was likely copied.

Recall what the user copied on this Mac via the local clipmem archive — text, commands, URLs, file paths, HTML, images, PDFs. Triggers on requests like "what was that command I copied?", "the URL I copied from Safari", "find that snippet before I restarted", or any paraphrase involving copy, paste, or clipboard. Offers ranked recall, chronological timeline, lexical / FTS search, raw-byte export for binary content, cursor pagination, and filters by app, kind, time window, and content shape. Use before reaching for generic web or repo search whenever the user is trying to recover something they previously had on the clipboard.

Use this skill when the user wants to recover, inspect, or re-export something they previously copied on this same Mac from the local clipmem archive: exact text, commands, SQL, URLs, file paths, HTML, images, or PDFs. Trigger on requests like "what was that command I copied?", "paste back that SQL", "the URL I copied from Safari", "show me what I copied from Xcode today", "find the snippet/path/link from before I restarted", and indirect paraphrases about clipboard history, copy/paste, or recovering something from earlier even if the user never says "clipboard". Prefer this over web, repo, or filesystem search only when the target was likely copied; do not use for content the user never copied, generic file search, or current web lookups.

Use this skill when you need to find code in a local checkout or Git source by behavior, intent, symbol, file path, related implementation, or indexed chunk context. Use it before broad file reads or grep-style sweeps for exploratory codebase questions, architecture tracing, call-site discovery, and "where/how is X implemented?" tasks. Do not use it for general web search or non-code files unless the user asks to search a source tree.

Use this skill when you need to find code in a local checkout or Git source by behavior, intent, symbol, file path, related implementation, or indexed chunk context. Use it before broad file reads or grep-style sweeps for exploratory codebase questions, architecture tracing, call-site discovery, and "where/how is X implemented?" tasks. Do not use it for general web search or non-code files unless the user asks to search a source tree.

Use this skill when you need to find code in a local checkout or Git source by behavior, intent, symbol, file path, related implementation, or indexed chunk context. Use it before broad file reads or grep-style sweeps for exploratory codebase questions, architecture tracing, call-site discovery, and "where/how is X implemented?" tasks. Do not use it for general web search or non-code files unless the user asks to search a source tree.

Use this skill when you need to find code in a local checkout or Git source by behavior, intent, symbol, file path, related implementation, or indexed chunk context. Use it before broad file reads or grep-style sweeps for exploratory codebase questions, architecture tracing, call-site discovery, and "where/how is X implemented?" tasks. Do not use it for general web search or non-code files unless the user asks to search a source tree.