Research & Search

conmuyan Bundle

Turn rough CCF research directions into concrete problem, gap, insight, method, novelty, and evidence plans. Use for idea optimization, fuzzy idea concretization, develop a fuzzy idea with no score, research direction shaping, early direction exploration, salvage routes, 优化idea, 具象化idea, 研究思路优化, 找方向, 方向探索. Do not rank or score multiple ideas as the main output.

conmuyan Bundle

Paper planning: update `docs/idea_report.md` part 4 (paper outline), choose figure plan (`notebooks/figures.ipynb`), select target venue (TPAMI/TKDE/AAAI/KDD/ICML/WWW/ICLR/CVPR), lock section ordering. Outputs the manuscript scaffold. Use for 论文规划, paper plan, outline. Defer to kim-ccf-research-write-* for section drafting.

conmuyan Bundle

Own assessment-only manuscript deliverables without rewriting: full scientific review, scoring, reviewer reports, issue diagnosis, AC/meta-review, readiness judgment, writing/format review, and cross-version comparison. Use for full review, scientific review, do not rewrite, assessment-only, paper review, score drift, moving-target review, 完整审稿, 不要改写, 模拟审稿, 论文评分, 版本对比, 复审一致性, 写作评审, LaTeX检查. Requests for revised or polished prose, including rewrite based on reviews with no new review, belong to ccf-paper-writer; rebuttals belong to ccf-rebuttal-writer; visual/table styling belongs to ccf-visual-composer.

conmuyan Bundle

Shared infrastructure for the kim-ccf-research series. This is NOT a skill — it is a namespace providing cross-skill references (routing, task modes, handoff protocols, privacy controls, venue maps, artifact contracts). Every kim-ccf-research-* leaf loads files from ../kim-ccf-research-shared/references/. Never invoke this directly.

conmuyan Bundle

Research direction exploration: from a fuzzy interest, converge to a research direction + RQ through multi-turn interaction. Outputs `docs/idea_report.md` Part 1. Use for 方向探索, 找方向, 调研, research direction. Do not write code, polish prose, or design experiments.

conmuyan Bundle

Code iteration loop: diagnose a bug or regression, backtrack to the responsible commit, update docs, modify code, re-test. Appends entries to `docs/dev_log.md`. Use for 代码迭代, debug, backtrack, diagnose. Do not restart from scratch; iterate the current version.

conmuyan Bundle

Humanize and de-defend publication-facing CCF/AI prose and artifacts as a sidecar preflight, never as the primary task owner. Use before manuscript drafting/revision and before final manuscript experiment text, tables, captions, or method descriptions when Codex must remove defensive writing, boilerplate disclaimers, repetitive improbable edge cases, unnecessary safeguards, generic SHA-256/checksum requirements, duplicated smoke tests, simplified/toy methods, or AI-like risk narration. Do not auto-load as the sole owner for raw experiment planning, retrieval, review, auditing, routing, visual rendering, or assessment-only tasks without publication prose. Keep necessary concerns in a separate user-review warning instead of silently injecting them into files. Do not conceal material evidence, fabricate results, or override venue-mandated disclosures.

conmuyan Bundle

Write and organize CCF conference rebuttals, author responses, response letters, revision summaries, reviewer-comment ledgers, and conservative resubmission adaptation plans. Use for rebuttal, author response, AC/meta-review response, revision ledger, resubmission to a new venue, 审稿意见回复, 重投迁移. Do not trigger for ordinary manuscript writing.

conmuyan Bundle

Implementation design: produce a function-level implementation guide from the experiment plan and architecture sketch. Outputs `docs/implementation.md`. Use for 实现设计, function-level coding guide, module breakdown. Do not write the actual code; defer to kim-ccf-research-code.

conmuyan Bundle

Chinese → English LaTeX translation of manuscript sections. Outputs `docs/manuscripts/<section>.en.md`. Use for 中英翻译, Chinese to English translation, 翻译. Run after every section is committed; do not interleave with kim-ccf-research-write-*.

conmuyan Bundle

Own experiment evidence semantics: decide datasets, baselines, metrics, ablations, robustness tests, chart evidence, and exactly what rows or columns a result table should contain. Use for experiment design, benchmark planning, supplied-result evidence structure, result-table schema, chart-spec semantics, 设计实验, 对比实验, 消融, 结果表证据结构. Do not search literature as the main deliverable, visually beautify or render an already specified table/figure, improve layout/colors/readability, or invent results.

conmuyan Bundle

Strictly score, rank, compare, and triage early CCF research ideas with prior-art awareness and venue-fit risk. Use only for explicit idea scoring, score and rank multiple ideas, idea ranking, idea review, acceptance-potential triage, idea评分, 选题评分, 选题排名, 严格评审. Do not polish manuscripts, brainstorm directions, develop a fuzzy idea with no score, or optimize a single idea unless scoring is explicit.

conmuyan Bundle

Write the Method section. Inputs: idea_report, implementation.md, exp_plan. Outputs `docs/manuscripts/02_method.md`. Use for 撰写手稿 Method, method section. Defer to kim-ccf-research-write-experiments in parallel; defer to kim-ccf-research-humanize after draft committed.

conmuyan Bundle

Write the Related Works section. Inputs: `docs/related_work_corpus.md` from kim-ccf-research-literature. Outputs `docs/manuscripts/04_related.md`. Use for 撰写手稿 Related Works, 相关工作. Must NOT run before kim-ccf-research-literature.

conmuyan Bundle

Write the Abstract. Inputs: every other manuscript section once drafted. Outputs `docs/manuscripts/01_abstract.md`. Use for 撰写手稿 Abstract, 摘要. Should run LAST among write-* skills (after method, experiments, intro, related, conclusion are drafted).

conmuyan Bundle

Write the Conclusion. Inputs: every other manuscript section. Outputs `docs/manuscripts/05_conclusion.md`. Use for 撰写手稿 Conclusion, 结论. Should summarize contributions, limitations, and future work.

conmuyan Bundle

Write the Experiments section. Inputs: idea_report, exp_plan, result tables/figures. Outputs `docs/manuscripts/03_experiments.md`. Use for 撰写手稿 Experiments, experiments section. Defers to kim-ccf-research-visual for figure rendering.

conmuyan Bundle

Write the Introduction. Inputs: idea_report, problem framing, contributions list. Outputs `docs/manuscripts/00_introduction.md`. Use for 撰写手稿 Introduction, 引言. Standard CCF-A intro arc: motivate → gap → contribution → outline.

belos-street Skill

个股核心投资逻辑深度研究，生成接近券商研究员风格的高质量个股分析报告，涵盖投资逻辑、风险提示和操作建议。Invoke when user asks for stock analysis, investment logic, or wants in-depth research on a specific company.

composio-community Skill

Triage Intercom conversations — classify by intent (bug, question, expansion, churn risk), assign, draft responses, escalate hot issues. Use on "triage my Intercom queue", "summarize open tickets", or "flag expansion opportunities in support".

composio-community Skill

Pull Zoom recordings/transcripts, extract deal-relevant notes (pains, budget, timeline, next steps), and log them to the CRM. Use on "summarize my demo from yesterday", "extract MEDDIC from this call", or "log Zoom notes to HubSpot".

composio-community Skill

Research a LinkedIn prospect or company before reaching out. Use when the user wants a one-page brief on a person or company — role history, recent posts, hiring signals, hooks for outreach. Invoke on "research this prospect", "LinkedIn brief", or "give me talking points on X".

dandacompany Skill

B2C 브랜드 시장조사 산출물에서 표기·용어 일관성을 보장하는 회사 공통 용어 사전. 무신사·29CM·W컨셉·LF몰 등 한국 e-커머스/패션 브랜드 표기, Bright Data 제품 명칭(Web Unlocker · SERP API · Datasets · Scraping Browser), Marp/Reveal.js 슬라이드 형식 명칭을 통일한다. Brand Intelligence Lab 모든 에이전트가 상속한다.

howarewoo Bundle

Bootstrap a genuinely greenfield web, mobile, desktop, API, or daemon project from scratch—gather requirements, research current technologies, approve the design, collision-check the target, and scaffold app-local code with shared packages only when needed. Linear, Plane, or GitHub artifacts are optional.

iamakbarsha1 Skill

Use when you're about to act on a "there is no X / none exists / not found / nothing handles this" claim — especially one from a delegated subagent, research handoff, or a teammate's summary. Positive file:line claims are citable and checkable; absence claims are only as good as the search pattern that produced them. Re-grep every "X does not exist" before building on it. Triggers on "no existing", "none found", "there's no", "doesn't exist", "nothing does X", research/subagent handoffs, and any negative finding you didn't verify yourself.

iamzifei Skill

Discover profitable business ideas from scratch. Analyzes market gaps, trending niches, user skills, and competitive landscapes with a competitive intelligence protocol including 4-filter benchmark stress test and Blue Ocean differentiation grid. Use when the user has no idea what to build, wants to explore opportunities, needs market research, competitive benchmarking, or says 'find me a business idea', 'what should I build', 'market research', 'find opportunities', or 'competitive analysis'.

imamirezaei Skill

Use this skill to prepare for or follow up on a team meeting. Triggers: 'prepare the agenda for our sprint planning', 'summarize what we decided', 'extract action items from this meeting', 'log the decisions from today', 'what are the open questions from the meeting', or any situation before or after a team meeting where the PM needs structure.

jposluns Skill

Citation Quote Verification

jposluns Skill

Verifies completion claims with evidence before declaring done. Use before stating "done", "complete", "fixed", "shipped", "ready", or any synonym. Use when wrapping up a unit of work and about to summarize to the user. Use when about to acknowledge a user-reported issue with "good catch". Use also before asserting a factual property of an artefact you have not read (a state assertion in research, assessment, planning, or review), not only at completion. Also use before ending a turn on a stated intention ("continuing with X", "next I will do X"), which is a claim about your own next action.

jwiegley Skill

The standard tooling and working discipline for planning and executing a coding task -- GitHub CLI, codebase search, the language -pro agents, web research, sequential thinking, and lint/type-check gating. The /medium and /heavy effort-tier commands build on it; load it when told to apply the standard toolkit.

jwiegley Bundle

Offload safe, independent subtasks to concurrent subagents while continuing your own work as the coordinator, then integrate what they return. Use when mid-task and some work could run in parallel without conflicting -- research, generating a standalone new file, tests for a stable interface, docs, or isolated analysis -- to accelerate without races. The coordinator alone runs git and mutates shared state; subagents read freely but write only to isolated namespaces and hand back artifacts. Triggers include "parallelize this", "spin up subagents to help", "do these in parallel", "fan this out".

kalyvask Skill

Coach a founder to get their first ~10 paying customers — the tactics of early founder-led sales, not research interviews. Starts from where the buyer actually spends their day, works the warm-network → unscalable → tools ladder, and writes outreach with one clear ask. Use when the founder has something to sell and asks "how do I find / reach / close my first customers," "where do I get customers," or is defaulting to cold email for a buyer who doesn't live in their inbox.

lensetek Bundle

Use to analyze ideas, RPS documents, research papers, thesis notes, or mixed academic sources before turning them into a book. Extracts concepts, findings, CPMK, evidence, gaps, citation risks, and privacy risks.

lensetek Bundle

Use to find academic references and paper candidates without requiring API keys. Searches and structures references from no-key sources such as Crossref, arXiv, PubMed/NCBI E-utilities, Europe PMC, and unauthenticated Semantic Scholar when available. Produces candidate references, DOI checks, relevance notes, and citation gaps without fabricating metadata.

lensetek Bundle

Use to review academic drafts for unsupported claims, missing citations, fabricated bibliography risks, source-use problems, and citation consistency.

lensetek Bundle

Use to synthesize multiple papers, literature-review notes, or research corpora into a thematic buku referensi outline, concept map, synthesis matrix, and chapter plan.