Research & Search

iamwaqargulzar Bundle

Use when the user asks to "codify how our founder sounds", "build a founder voice dossier", or "set our content pillars"; runs an 80%-extraction interview over the user's OWN posts, emails, and decks (never competitor scraping, never an invented persona) and produces the versioned voice record — a per-platform register map (incl. 小红书/微信公众号), banned phrases, per-context disclosure lines (the ECHO C2 upstream), a few-shot bank built exclusively from own posts, and 3-5 content pillars with Estimated %-allocations — submitted via memory/events/channels.ndjson for channel-registry to store as voice-dossier.md, the record every Craft-phase skill reads first. Not for the brand-level voice canon — use brand-language-codifier; not for audience/persona research — use audience-mapper. 声音档案/品牌语气/创始人语气/内容支柱/披露声明

iamwaqargulzar Bundle

Use when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks. Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer. 域名权威/网站可信度

joogy06 Bundle

Use when the user wants to summarize, condense, digest, or extract the key points / TL;DR / executive summary / action items / minutes from any source — pasted text, a file, an email or email thread (Outlook), a Confluence page (optionally with all its subpages), a wiki page, or a web URL. Picks an output shape (TL;DR / exec summary / key points / action-items & decisions / abstract / meeting minutes / structured per-section), fetches the source by composing existing skills (large-file-analysis, confluence-rest-api, ms-office-graph-python, wiki, web-research), and produces a faithful, attributed summary that never invents facts. Trigger on - summarize this, summarise the email/page/thread, TL;DR, give me the key points, exec summary, action items from, minutes from this, condense, digest, what does this say, brief me on.

ericrisco Bundle

Use when a rough product, service, workflow or feature idea needs divergent options and assumption pressure-testing before it becomes a spec. Produces a decision brief with alternatives, evidence gaps, Not Now and a cheap experiment. NOT requirements or acceptance criteria (`specify`), NOT market sizing (`market-research`).

ericrisco Bundle

Use when a MARKET as a whole needs a defensible picture — TAM/SAM/SOM sized top-down AND bottom-up until the two converge, cut into reachable segments with one named beachhead, demand proven real, and a dated source behind every figure. NOT profiling named rivals and their moves (that is `competitor-watch`), NOT building a list of accounts to sell to (that is `lead-gen`).

ericrisco Bundle

Use when deciding which videos a channel should make next and tracking whether each bet beat baseline — generating, scoring and prioritising candidate ideas from the channel's own performance log plus outlier and search-trend research, then recording each promoted idea as a dated hypothesis with its measured outcome. NOT writing the title or thumbnail text for a chosen idea (that is `youtube-packaging`).

ericrisco Bundle

Use when implementation or review depends on current version-specific framework, SDK, protocol or platform behaviour and memory is unsafe. Detects exact local versions, verifies primary sources, tests applicability and marks unknowns. NOT a standalone cited memo (`research-ops`), NOT diagnosis of a reproduced failure (`debug`).

codyswanngt Skill

Idempotently create or update one financial advisor in Harper using FINRA BrokerCheck, saved AdvisorHub articles, and targeted public web research. Required input is the advisor's legal name; optional disambiguators include CRD, current firm, state, career-start year, or a phrase like "James Taylor at Wells Fargo in NYC". Uses the repo's Bun/TypeScript scripts and deterministic upserts.

codyswanngt Skill

Run the scheduled advisory-rankings public-web research cycle for due AdvisorResearchCheck rows. Uses deployed Harper, source-backed public sources only, records each checked advisor, and never scrapes LinkedIn pages.

planifest Bundle

UX research synthesis workflow for turning mixed evidence into prioritized design actions. Use when multiple qualitative and quantitative inputs must be consolidated into clear design implications; do not use for backend architecture or deployment planning.

allinherog-star Bundle

客户研究助手适合市场营销、运营、software、教育培训在用户提出“这个客户怎么切入”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成销售策略、沟通素材、跟进计划。

allinherog-star Bundle

用户研究助手适合市场营销、运营、software、教育培训在用户提出“用户到底想要什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成用户洞察、需求分层、内容/销售话术建议。

allinherog-star Bundle

资料整理助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这份材料重点是什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成内容诊断、优化建议、执行清单。

allinherog-star Bundle

销售增长助手适合销售、市场营销、运营、产品在用户提出“客户为什么不推进”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

allinherog-star Bundle

教育研究方法助手适合市场营销、运营、software、教育培训在用户提出“研究方法选对了吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成教学或招聘诊断、改进建议、评分/活动清单。

allinherog-star Bundle

业务诊断助手适合运营、市场营销、healthcare、教育培训在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

allinherog-star Bundle

资料整理助手适合运营、市场营销、technical、产品在用户提出“这份材料重点是什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

samarv Skill

A framework to close stalled sales deals by addressing the customer's fear of failure (FOMU) rather than their fear of missing out (FOMO). Use this when a prospect has expressed intent to buy but starts ghosting, relitigating old concerns, or demanding endless research.

iamwaqargulzar Bundle

Use when the user asks to "optimize entity presence", reconcile an entity identity, or update canonical Knowledge Graph facts; audits and maintains machine-facing identity, sameAs, schema, disambiguation, and AI-recognition evidence through the entities registry. Not for page-level AI-citation readiness - use geo-content-optimizer; not for human-facing brand canon - use narrative-registry. 实体注册/知识图谱

iamwaqargulzar Bundle

Use when the user asks to "find keywords", "挖词", or "搜什么词"; prioritizes search volume, keyword difficulty, intent, and topic clusters from provided or connected data. Not for competitor-relative coverage gaps — use content-gap-analysis. 关键词研究/内容选题

deciqai Bundle

Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do NOT activate when: the role is genuinely high-coordination with no discrete focus windows (ER medicine, real-time trading desk), or user is in a short-term emergency where availability must dominate. More: deciqai.com/s/deep-work

deciqai Bundle

Activate when: user asks 'why isn't anyone using our product?', 'how do we understand what customers really want?', 'we know the tech works but the market isn't responding', team is stuck on a single solution and needs divergent ideas, or someone discusses user research / personas / prototyping / iterative design. Do NOT activate when: the problem and solution are both already validated and the challenge is pure execution; or the team cannot access real users at any point. More: deciqai.com/s/design-thinking

deciqai Bundle

Activate when: user says 'we keep finding evidence that supports our view,' 'the team is all aligned on this,' 'I've done the research and it checks out,' or a decision moves forward with only supporting evidence cited. Do NOT activate when: context is explicit advocacy (legal brief, pitch deck) where one-sided argument is the design; or stakes are too low to justify structured disconfirmation. More: deciqai.com/s/confirmation-bias

joogy06 Bundle

Use when a caller needs to query GDELT 2.0 (Global Database of Events, Language, and Tone) for industry events, theme velocity, inflection detection, or macro trend grounding. Supports events_by_theme, inflection_scan, and location_events operations. Reusable by founder-ideation (for trend-first team data), research-*, geopolitical-market-impact, and any caller that needs global event signal grounding. One-shot fetch-analyze-return. Trigger on: "query GDELT", "industry inflections", "event velocity for theme X", "what global events relate to Y", "macro trends in Z".

joogy06 Bundle

Use when a skill gap is identified during task planning, when the user asks to create or improve a skill, or when forge detects no matching skill for a domain.

knuckles-team Bundle

Compatibility alias for the consolidated web-crawler single-page workflow. Use when an existing workflow names web-fetch; prefer web-crawler for new fetch, crawl, sitemap, rendered-page, or GraphOS-ingestion tasks.

knuckles-team Skill

Edit an existing draft for clarity, coherence, concision, grammar, terminology, and adherence to a supplied voice or style guide without changing its supported meaning. Use when a draft is factually settled and needs an editorial pass. Do not use to perform research, verify citations, add new factual claims, or publish the result.

knuckles-team Bundle

Bounded, privacy-aware website and sitemap crawler with AgentConfig-managed egress, TLS, output confinement, and optional GraphOS document ingestion. Use when fetching one page, crawling a site or sitemap, or ingesting approved web content into GraphOS.

richfrem Bundle

Summarize podcast episodes from audio metadata. Extracts ID3 tags, chapter markers, and show notes.

richfrem Bundle

Run the Phase 0 research workflow to scaffold research artifacts before task planning.

kienbui1995 Skill

Use when planning user interviews, writing discussion guides, running usability tests, or synthesizing research findings

williamcorrea23 Skill

Ingests an expert's answers to an L2 questionnaire in the abap_wiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/<id>/inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert has answered the functional questions generated by research-l2.

hmbown Skill

This spell is archaeology, not history research. It operates on specific artifacts from a specific dead system to answer specific questions. It is NOT general tech history, NOT interviewing living people, and NOT monitoring live systems.

shengdabai Bundle

Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".

shengdabai Bundle

Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain.

shengdabai Skill

Compile daily briefing with meeting context, active deals, and citation tracking