{"items":[{"slug":"huawei-cloud-security-group-list","displayName":"huawei-cloud-security-group-list","summary":"Lists Huawei Cloud security groups (安全组) — enumerates all security groups in a VPC project with security group ID, name, description, enterprise project ID, tags and creation time, using the KooCLI `hcloud VPC ListSecurityGroups` command (primary) or the huaweicloudsdkvpc Python SDK (fallback). Provides read-only security group inventory for network security auditing, firewall rule review and resource discovery. Use this skill whenever the user mentions security group list query. Triggers include: list security groups, security group list, query security groups, enumerate security groups, show security groups, security group inventory, 查询安全组, 安全组列表, 查看安全组, 列出安全组, 获取安全组列表, 查询安全组列表.","description":"Lists Huawei Cloud security groups (安全组) — enumerates all security groups in a VPC project with security group ID, name, description, enterprise project ID, tags and creation time, using the KooCLI `hcloud VPC ListSecurityGroups` command (primary) or the huaweicloudsdkvpc Python SDK (fallback). Provides read-only security group inventory for network security auditing, firewall rule review and resource discovery. Use this skill whenever the user mentions security group list query. Triggers include: list security groups, security group list, query security groups, enumerate security groups, show security groups, security group inventory, 查询安全组, 安全组列表, 查看安全组, 列出安全组, 获取安全组列表, 查询安全组列表.","topics":[],"tags":{"huawei-cloud":"1.0.0","inventory":"1.0.0","latest":"1.0.0","query":"1.0.0","security-group":"1.0.0","vpc":"1.0.0"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785597763513,"updatedAt":1785597838516,"latestVersion":{"version":"1.0.0","createdAt":1785597763513,"changelog":"v1.0.0 初始发布: 支持华为云安全组列表查询(CLI 主路径 + Python SDK fallback)","license":null},"metadata":null},{"slug":"career-coach-ai-cn","displayName":"Career Coach Ai","summary":"个人职业成长教练（CareerCoach AI）。当用户需要职业规划、简历优化、模拟面试，或职场答疑（薪资谈判、晋升发展、转行跳槽、职场关系、试用期焦虑）时使用。覆盖\"职业迷茫/瓶颈、想跳槽转行、简历石沉大海、面试总卡壳、怎么谈加薪、如何平稳转正\"等场景。用 GROW / Ikigai / SWOT / STAR 等结构化方法陪用户看清自己、拆解路径并给出可执行的下一步动作。","description":"个人职业成长教练（CareerCoach AI）。当用户需要职业规划、简历优化、模拟面试，或职场答疑（薪资谈判、晋升发展、转行跳槽、职场关系、试用期焦虑）时使用。覆盖\"职业迷茫/瓶颈、想跳槽转行、简历石沉大海、面试总卡壳、怎么谈加薪、如何平稳转正\"等场景。用 GROW / Ikigai / SWOT / STAR 等结构化方法陪用户看清自己、拆解路径并给出可执行的下一步动作。","topics":[],"tags":{"latest":"1.0.2"},"stats":{"comments":0,"downloads":84,"installs":1,"stars":0,"versions":2},"createdAt":1785438162948,"updatedAt":1785597728252,"latestVersion":{"version":"1.0.2","createdAt":1785597664518,"changelog":"- 加强了结构化指导方法，详细介绍了 GROW、Ikigai、SWOT、STAR 等工具的具体应用流程。\n- 明确六大核心场景（职业规划、简历优化、模拟面试等）及应对流程，提升用户体验的针对性。\n- 优化多轮对话逻辑，确保循序渐进、行动导向，并加入情绪分级应对机制。\n- 补充质量红线，强调不提供结论性法律/医疗/心理建议、不虚假承诺、不收集敏感信息等边界。\n- 增加参考资料链接，便于按需调用实用模板和详细方法说明。","license":null},"metadata":null},{"slug":"douyin-creator-insight","displayName":"douyin-creator-insight","summary":"分析公开抖音创作者的视频主题、互动结构和代表内容，并输出 HTML、Markdown、JSON 报告。适用于研究某个抖音博主、拆解选题和内容结构；不用于收藏夹同步、私密账号或绕过平台访问控制。","description":"分析公开抖音创作者的视频主题、互动结构和代表内容，并输出 HTML、Markdown、JSON 报告。适用于研究某个抖音博主、拆解选题和内容结构；不用于收藏夹同步、私密账号或绕过平台访问控制。","topics":[],"tags":{"latest":"1.2.3"},"stats":{"comments":0,"downloads":121,"installs":2,"stars":0,"versions":5},"createdAt":1785402766574,"updatedAt":1785596501143,"latestVersion":{"version":"1.2.3","createdAt":1785596327361,"changelog":"v1.2.3 removes an internal task_plan.md process artifact from the public package; functional v1.2.2 first-run setup remains unchanged.","license":null},"metadata":null},{"slug":"tock-mcp","displayName":"Tmp.0U06iwue3J","summary":"Discover restaurants on Tock (exploretock.com) via MCP — list cities, search a metro, and get a venue's details plus its bookable experiences, prices, party sizes, and open dates/times. Triggers on phrases like \"search Tock for\", \"what's on Tock in Chicago\", \"find a Tock reservation at\", \"does Alinea have availability on Tock\", \"what experiences does <venue> offer on Tock\", or \"my Tock reservations\". Requires tock-mcp installed and the fetchproxy browser extension running in a signed-in exploretock.com tab.","description":"Discover restaurants on Tock (exploretock.com) via MCP — list cities, search a metro, and get a venue's details plus its bookable experiences, prices, party sizes, and open dates/times. Triggers on phrases like \"search Tock for\", \"what's on Tock in Chicago\", \"find a Tock reservation at\", \"does Alinea have availability on Tock\", \"what experiences does <venue> offer on Tock\", or \"my Tock reservations\". Requires tock-mcp installed and the fetchproxy browser extension running in a signed-in exploretock.com tab.","topics":[],"tags":{"latest":"0.2.5"},"stats":{"comments":0,"downloads":343,"installs":0,"stars":0,"versions":6},"createdAt":1783291086352,"updatedAt":1785596182179,"latestVersion":{"version":"0.2.5","createdAt":1785596130042,"changelog":"- Added a new \"Booking verification protocol\" section to the documentation, outlining steps and rules for confirming Tock reservations.\n- Emphasized that bookings must be verified by both a confirmation artifact and appearance in `tock_list_reservations` after re-query.\n- Explained pitfalls with Tock's post-booking modal and reservation backend lag.\n- Removed the file: skill-card.md.","license":null},"metadata":null},{"slug":"agentpost200","displayName":"AgentPost200","summary":"AgentPost200 (api.agentpost200.com): hosted agent mailbox with live endpoints — register for API key and inbound POST URL, receive without hosting, poll/ack, two-way reply_to, optional webhook forward, blocklists. Senders POST without an account. Not email/IMAP AgentPost (agentpost.no or similar).","description":"AgentPost200 (api.agentpost200.com): hosted agent mailbox with live endpoints — register for API key and inbound POST URL, receive without hosting, poll/ack, two-way reply_to, optional webhook forward, blocklists. Senders POST without an account. Not email/IMAP AgentPost (agentpost.no or similar).","topics":[],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785595946605,"updatedAt":1785596021953,"latestVersion":{"version":"1.0.0","createdAt":1785595946605,"changelog":"Initial release: hosted agent mailbox API at api.agentpost200.com — register, inbound POST, poll/ack, reply_to, optional forward.","license":null},"metadata":{"setup":[],"os":null,"systems":null}},{"slug":"workspace-backup","displayName":"workspace-backup","summary":"PURE LOCAL file backup of this Mac's workspace: mirrors ~/playground, ~/experiment and ~/WorkBuddy into BOTH a fixed local folder and an external drive, incremental and verified, so an interrupted run resumes. Use-when: '备份一下工作区', 'back up my workspace to the external drive', 'what is not backed up yet / 备份状态', 'the drive is plugged in, catch up the backup', '$workspace-backup'. Do-NOT use for: Time Machine repair or restore; git push to a remote; iCloud or cloud sync; database dumps; deleting node_modules to free space (this skill never deletes from the source); or a single-file .bak.","description":"PURE LOCAL file backup of this Mac's workspace: mirrors ~/playground, ~/experiment and ~/WorkBuddy into BOTH a fixed local folder and an external drive, incremental and verified, so an interrupted run resumes. Use-when: '备份一下工作区', 'back up my workspace to the external drive', 'what is not backed up yet / 备份状态', 'the drive is plugged in, catch up the backup', '$workspace-backup'. Do-NOT use for: Time Machine repair or restore; git push to a remote; iCloud or cloud sync; database dumps; deleting node_modules to free space (this skill never deletes from the source); or a single-file .bak.","topics":[],"tags":{"latest":"0.2.3"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785593699732,"updatedAt":1785593808839,"latestVersion":{"version":"0.2.3","createdAt":1785593699732,"changelog":"First hub release. Pure-local memoized workspace backup to a fixed folder AND an external drive: inventory -> classify -> route -> copy -> verify, incremental with resume. Never deletes from source; three hard safety lines enforced by exit codes (Time Machine volume refusal, guard-approved destinations only, no SAFE verdict without real observation). Two adversarial battery rounds + a real 36 GB run behind it.","license":null},"metadata":null},{"slug":"paper-writer","displayName":"paper-writer","summary":"Author a NEW, complete, spec-compliant paper (essay/thesis chapter/literature review/课程论文) from a requirement (word-count/citation-style/sections) and/or a topic-选题. Use for \"write me a paper on…\", \"写一篇…的学术论文\", \"turn a brief into a paper\". NOT to proofread/summarize/humanize/fact-check an EXISTING paper (→ siblings).","description":"Author a NEW, complete, spec-compliant paper (essay/thesis chapter/literature review/课程论文) from a requirement (word-count/citation-style/sections) and/or a topic-选题. Use for \"write me a paper on…\", \"写一篇…的学术论文\", \"turn a brief into a paper\". NOT to proofread/summarize/humanize/fact-check an EXISTING paper (→ siblings).","topics":[],"tags":{"latest":"0.1.0"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785593685381,"updatedAt":1785593772087,"latestVersion":{"version":"0.1.0","createdAt":1785593685381,"changelog":"First hub release. Writes a NEW, complete, spec-compliant paper from a requirement (word count / citation style / sections) and/or topic. Two integrity invariants: never fabricate citations, never plagiarize — unverifiable sources are marked [SOURCE NEEDED], not invented. Pre-registered disjunctive stop conditions; independent blind-judge rubric with unknown-exit auditing.","license":null},"metadata":null},{"slug":"logic-pacer","displayName":"logic-pacer","summary":"Rewrite EXISTING admired Chinese/English expository prose so its reasoning is easier to follow — shrink the inferential STEP SIZE and re-anchor each step on ground the reader already holds (given-new), while KEEPING the voice, the vocabulary (never 对齐词汇), the facts/claims/stance, and staying lean (net length <= ~1.3x). Method: detect >=2-move leaps, unfold each into its minimal chain, subtract ornament. Use for \"这段逻辑跳太快，放慢但别动文风/词汇\", \"reduce the inferential step size\", \"$logic-pacer\". ABSTAIN if the prose is already followable. NOT de-AI (→humanizer-academic), NOT simplify-words/对齐词汇, NOT summarize/translate, NOT reorder points, NOT generate new prose.","description":"Rewrite EXISTING admired Chinese/English expository prose so its reasoning is easier to follow — shrink the inferential STEP SIZE and re-anchor each step on ground the reader already holds (given-new), while KEEPING the voice, the vocabulary (never 对齐词汇), the facts/claims/stance, and staying lean (net length <= ~1.3x). Method: detect >=2-move leaps, unfold each into its minimal chain, subtract ornament. Use for \"这段逻辑跳太快，放慢但别动文风/词汇\", \"reduce the inferential step size\", \"$logic-pacer\". ABSTAIN if the prose is already followable. NOT de-AI (→humanizer-academic), NOT simplify-words/对齐词汇, NOT summarize/translate, NOT reorder points, NOT generate new prose.","topics":[],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785593673046,"updatedAt":1785593743781,"latestVersion":{"version":"1.0.0","createdAt":1785593673046,"changelog":"First hub release. Slows the logical pacing of prose you already like: shrinks inference step size so每步 lands where the reader stands (given-new), without touching style, vocabulary, facts, or stance (net length <=~1.3x). Built end-to-end by the skill-creator-max pipeline; independent battery caught and fixed a real defect the builder's self-tests missed.","license":null},"metadata":null},{"slug":"loop-constructor","displayName":"loop-constructor","summary":"Design the engineered loop for a medium/large (semi-)autonomous AI-coding task by decomposing it into gated sub-loops, emitted as a runnable .loop/ runbook. Use-when: \"design an agent loop\", \"set up an autonomous / self-running agent workflow\", \"$loop-constructor\". It DESIGNS the loop; it does NOT execute it.","description":"Design the engineered loop for a medium/large (semi-)autonomous AI-coding task by decomposing it into gated sub-loops, emitted as a runnable .loop/ runbook. Use-when: \"design an agent loop\", \"set up an autonomous / self-running agent workflow\", \"$loop-constructor\". It DESIGNS the loop; it does NOT execute it.","topics":[],"tags":{"latest":"0.3.0"},"stats":{"comments":0,"downloads":291,"installs":1,"stars":0,"versions":3},"createdAt":1782269143727,"updatedAt":1785593737192,"latestVersion":{"version":"0.3.0","createdAt":1785593648164,"changelog":"R17 H-series: two-sided stop gates (zero-change stop + minimum progress), pre-quantified stall criteria for restart/loopback/escalate, check execution outside the generator write surface, contract assertion floors by surface area (x3 ceilings, machine-gradable only), paired success/integrity run-report metrics, compensator-vs-structural harness settlement. Zero linter/schema changes; 69/69 green. Bundle slimmed: design-time KB indexes excluded (runtime uses only loop-principle/templates/).","license":null},"metadata":null},{"slug":"skill-creator-max","displayName":"skill-creator-max","summary":"Build a NEW agent skill from scratch, end-to-end — a thin conductor dispatches fresh subagents through five gated roles (compose spec -> design structure -> red-green build -> compress -> independent attack). EXPENSIVE (large token cost): trigger ONLY on an explicit user request to author/build/create an agent skill — \"build me a skill\", \"create a new skill\", \"package this repeated workflow so it triggers automatically\", \"$skill-creator-max\". Do-NOT fire for: summarizing or writing daily/session memory or journaling (incl. Chinese \"总结/记录今天的记忆\"), or any generic \"create/make/summarize X\" that is not authoring an agent skill.","description":"Build a NEW agent skill from scratch, end-to-end — a thin conductor dispatches fresh subagents through five gated roles (compose spec -> design structure -> red-green build -> compress -> independent attack). EXPENSIVE (large token cost): trigger ONLY on an explicit user request to author/build/create an agent skill — \"build me a skill\", \"create a new skill\", \"package this repeated workflow so it triggers automatically\", \"$skill-creator-max\". Do-NOT fire for: summarizing or writing daily/session memory or journaling (incl. Chinese \"总结/记录今天的记忆\"), or any generic \"create/make/summarize X\" that is not authoring an agent skill.","topics":[],"tags":{"latest":"1.2.0"},"stats":{"comments":0,"downloads":157,"installs":0,"stars":0,"versions":2},"createdAt":1784015062652,"updatedAt":1785593734405,"latestVersion":{"version":"1.2.0","createdAt":1785593588580,"changelog":"R17 alignment folded into the role-packs: composer spec-boundary step (adversarial precedents on load-bearing clauses; reject codebase-to-spec reverse authorship; 89% compliance ceiling), engineer verifier-engineering discipline + loop-charter gate for loop-type skills, guidance per-surface branches (tool/action/memory). Conductor gate logic untouched; five L0 gates green.","license":null},"metadata":null},{"slug":"mp-cli-sup","displayName":"Vince MP CLI Support","summary":"Drive Mini Program CLI debugging","description":"Debug a WeChat Mini Program's LIVE runtime via the system `vince-mp` JSON CLI — one persistent session, then instant reused commands (pageData, query/tap, scan, console, doctor, log correlation). Use for \"debug WeChat DevTools\", \"连上小程序\", \"$mp-cli-sup\". NOT for browser automation, source-only edits, or non-WeChat work.","topics":[],"tags":{"latest":"0.2.2"},"stats":{"comments":0,"downloads":272,"installs":1,"stars":0,"versions":3},"createdAt":1782269153913,"updatedAt":1785593686167,"latestVersion":{"version":"0.2.2","createdAt":1785593557795,"changelog":"Hardening-loop stop condition upgraded from single terminal state to a four-way disjunction: converged / cap (limits live in the condition) / no-progress / RESTART-ESCALATE (a defect whose regression points at the previous round's added check stops the loop and reports). R17 audit; no script changes.","license":null},"metadata":null},{"slug":"neat","displayName":"neat","summary":"End-of-session knowledge cleanup — reconciles project docs (CLAUDE.md, README, docs/) and agent memory against the code so nothing rots. Trigger on dev-milestone cues: \"sync up\", \"tidy up docs\", \"update memory\", \"/neat\", \"整理文档\", \"$neat\", or stale-docs reports. NOT for non-dev \"整理\", tidying code, or pasted text.","description":"End-of-session knowledge cleanup — reconciles project docs (CLAUDE.md, README, docs/) and agent memory against the code so nothing rots. Trigger on dev-milestone cues: \"sync up\", \"tidy up docs\", \"update memory\", \"/neat\", \"整理文档\", \"$neat\", or stale-docs reports. NOT for non-dev \"整理\", tidying code, or pasted text.","topics":[],"tags":{"latest":"1.2.0"},"stats":{"comments":0,"downloads":242,"installs":1,"stars":0,"versions":2},"createdAt":1782269016436,"updatedAt":1785593659982,"latestVersion":{"version":"1.2.0","createdAt":1785593570644,"changelog":"R17 memory-engineering lifecycle: incremental deltas over full rewrites (brevity bias / context collapse), forgetting duty with delete/tombstone two-tier retirement, fact entries re-run verification anchors instead of comparing text, runtime memory split from institutional accumulation.","license":null},"metadata":null},{"slug":"loop-constructor-codex","displayName":"loop-constructor-codex","summary":"Design an engineered gated loop for a medium/large (semi-)autonomous AI-coding task executed with the Codex CLI (single-agent, `codex exec`), emitted as a runnable .loop/ runbook. Use-when: \"design an agent loop for codex\", \"$loop-constructor-codex\". It DESIGNS the loop; it does NOT execute it.","description":"Design an engineered gated loop for a medium/large (semi-)autonomous AI-coding task executed with the Codex CLI (single-agent, `codex exec`), emitted as a runnable .loop/ runbook. Use-when: \"design an agent loop for codex\", \"$loop-constructor-codex\". It DESIGNS the loop; it does NOT execute it.","topics":["codex","loop-engineering","subagents","stupidskills"],"tags":{"latest":"0.2.0"},"stats":{"comments":0,"downloads":199,"installs":0,"stars":0,"versions":3},"createdAt":1783337344390,"updatedAt":1785593613434,"latestVersion":{"version":"0.2.0","createdAt":1785593535017,"changelog":"Synced with loop-constructor 0.3.0 (R17 H-series; byte-identical shared modules preserved; 71/71 green). Codex-runtime mapping unchanged.","license":null},"metadata":null},{"slug":"attacker","displayName":"attacker","summary":"Attack any target (skill, design, argument, code, KB) with a FRESH independent attacker rotating five lenses; coverage-first strike, then PROVE-OR-FLAG adjudication (findings vs flags); never fixes. A different-vendor attacker buys stronger independence. Use-when: \"red-team/break this\", \"$attacker\". Do-NOT: fix or edit the target.","description":"Attack any target (skill, design, argument, code, KB) with a FRESH independent attacker rotating five lenses; coverage-first strike, then PROVE-OR-FLAG adjudication (findings vs flags); never fixes. A different-vendor attacker buys stronger independence. Use-when: \"red-team/break this\", \"$attacker\". Do-NOT: fix or edit the target.","topics":[],"tags":{"latest":"0.7.0"},"stats":{"comments":0,"downloads":392,"installs":2,"stars":0,"versions":4},"createdAt":1782269136733,"updatedAt":1785593599144,"latestVersion":{"version":"0.7.0","createdAt":1785593517320,"changelog":"R17 alignment: fix-audit re-aim mode (attack the previous round's fixes: propagation/new-defects/masking/silent-skips; validated by 4 P1s in the philosophy KB's own battery), rubric adversarial-axis acceptance (agreement is blind to exploitability), first non-anecdotal quantitative support for different-vendor independence; resident body paid back under the 3,000-token line.","license":null},"metadata":null},{"slug":"model-pyramid","displayName":"model-pyramid","summary":"Right-size MODEL + EFFORT for the session and for each subagent at fan-out time, and decide whether to attach an advisor. Two axes: capability gap → change model; thoroughness gap → change effort. Use when spawning / fanning out / delegating subagents, or when asked which model or effort something should get: \"$model-pyramid\". NOT API price shopping.","description":"Right-size MODEL + EFFORT for the session and for each subagent at fan-out time, and decide whether to attach an advisor. Two axes: capability gap → change model; thoroughness gap → change effort. Use when spawning / fanning out / delegating subagents, or when asked which model or effort something should get: \"$model-pyramid\". NOT API price shopping.","topics":["subagents","model-sizing","reasoning-effort","stupidskills"],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":193,"installs":0,"stars":0,"versions":3},"createdAt":1783337351282,"updatedAt":1785593598911,"latestVersion":{"version":"1.0.0","createdAt":1785593544624,"changelog":"Ground-up rebuild for the Claude 5 effort ladder: two-axis sizing (capability gap -> model; thoroughness gap -> effort), session+subagent+advisor scope, check_plan.mjs validates only the deterministically checkable parts; 26 evals in three groups; two-arm live test 9/9 vs bare 5/9.","license":null},"metadata":null},{"slug":"album-review","displayName":"album-review","summary":"Deep, source-traceable long-form Chinese album review (乐评). Use when the user names a music credit (artist/composer/band) + an album and wants one comprehensive critique. Triggers: \"写一篇深度乐评\", \"全面评测这张专辑\", \"$album-review\". NOT for audio-gear evaluation (→ hifi-review).","description":"Deep, source-traceable long-form Chinese album review (乐评). Use when the user names a music credit (artist/composer/band) + an album and wants one comprehensive critique. Triggers: \"写一篇深度乐评\", \"全面评测这张专辑\", \"$album-review\". NOT for audio-gear evaluation (→ hifi-review).","topics":["Music"],"tags":{"latest":"0.2.0"},"stats":{"comments":0,"downloads":544,"installs":6,"stars":0,"versions":4},"createdAt":1780642623811,"updatedAt":1785593573060,"latestVersion":{"version":"0.2.0","createdAt":1785593489814,"changelog":"Honest publish gate: length gate proven blind to CJK repetition padding (judge-must-flag negative registry, no mechanical threshold); fix loop gains cap + escalate exit; integrity pairing declared untested (R17 audit).","license":null},"metadata":null},{"slug":"marketing-material-review-business","displayName":"marketing-material-review-business","summary":"营销版面审核技能（对外版）- 从广告审核法务视角，对营销素材进行合规性审核。支持图片审核、风险点标注、修改建议。触发词：这个版面、详情页、主图、KT板、直播间文案、素材、文档帮我审核一下。","description":"营销版面审核技能（对外版）- 从广告审核法务视角，对营销素材进行合规性审核。支持图片审核、风险点标注、修改建议。触发词：这个版面、详情页、主图、KT板、直播间文案、素材、文档帮我审核一下。","topics":[],"tags":{"latest":"1.1.8"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785593193717,"updatedAt":1785593343923,"latestVersion":{"version":"1.1.8","createdAt":1785593193717,"changelog":"**发布环境和兼容性大幅加固，提升审核稳定性和部署灵活性**\n\n- 新增依赖安装优先使用 CPython，增强环境适配能力  \n- 自动适配 skill 目录不可写场景，降级到用户缓存或临时目录，保障输出流程不中断  \n- 继续完善上一版本的自动依赖安装、环境检测及入口选择机制，提高首次运行体验  \n- 进一步明确宿主与脚本入口约束，避免因环境问题导致审核中断  \n- 持续优化对食品、乳制品、保健品等行业营销素材合规审核能力","license":null},"metadata":{"setup":[{"key":"BAIDU_API_KEY","required":true},{"key":"BAIDU_SECRET_KEY","required":true}],"os":null,"systems":null}},{"slug":"smyx-smoking-detection-analysis","displayName":"Intelligent Public Smoking Detection Skill | 公共场所吸烟行为智能检测技能","summary":"Automatically detects smoking behavior in target areas based on computer vision; supports real-time detection of video streams, images, and video files; identifies violation smoking behavior and triggers violation alerts, assisting in smoking control safety management for parks/communities/units. | 公共场所吸烟行为智能检测技能，基于计算机视觉自动检测目标区域内的吸烟行为，支持视频流、图片、视频文件实时检测，识别违规吸烟行为，触发违规预警，助力园区/社区/单位控烟安全管理","description":"Automatically detects smoking behavior in target areas based on computer vision; supports real-time detection of video streams, images, and video files; identifies violation smoking behavior and triggers violation alerts, assisting in smoking control safety management for parks/communities/units. | 公共场所吸烟行为智能检测技能，基于计算机视觉自动检测目标区域内的吸烟行为，支持视频流、图片、视频文件实时检测，识别违规吸烟行为，触发违规预警，助力园区/社区/单位控烟安全管理","topics":["安全"],"tags":{"latest":"1.0.8"},"stats":{"comments":0,"downloads":1034,"installs":22,"stars":4,"versions":9},"createdAt":1776396843048,"updatedAt":1785592187262,"latestVersion":{"version":"1.0.8","createdAt":1785592056003,"changelog":"- Updated skill version to 1.0.11.\n- Removed the file skill-card.md.\n- SKILL.md revised; the version in metadata changed from 1.0.8 to 1.0.11.\n- No user-facing functional or capability changes described.  \n- Documentation and resource index were updated to reflect current state.","license":null},"metadata":null},{"slug":"sgcc-doc-format","displayName":"sgcc-doc-format","summary":"将 Word 文档调整为SGCC规范格式（方正字体、标题层级、28磅行距、-1-页码、表格、中文引号等12条规则）。用户发来 docx文档，并说\"调成规范格式\"时使用。","description":"将 Word 文档调整为《国家电网公司规范格式》（方正字体、标题层级、28磅行距、-1-页码、表格、中文引号等12条规则）。用户发来 docx 并说\"调成规范格式\"时使用。","topics":[],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":0,"installs":0,"stars":0,"versions":1},"createdAt":1785590957816,"updatedAt":1785591117910,"latestVersion":{"version":"1.0.0","createdAt":1785590957816,"changelog":"- 首发版本，支持将 Word 文档批量调整为国家电网公司规范格式  \n- 一键自动排版：按 12 条方正字体、字号、行距、标题、页码、表格等国网规范执行  \n- 支持目录自动生成与页码分节，目录可点击跳转  \n- 英文双引号批量替换为中文引号  \n- 保留原文件，输出新规范格式文件  \n- 文档通过飞书消息返回给用户","license":null},"metadata":null},{"slug":"manage-agent-skills","displayName":"Manage Agent Skills","summary":"Toggle skills across major coding agents","description":"Manage Agent Skills across Codex, Claude Code, Copilot CLI, OpenClaw, and Hermes. Audit, search, enable, disable, and apply presets without deletion.","topics":["agent-skills","skill-management","developer-tools","codex","claude-code"],"tags":{"latest":"0.1.3"},"stats":{"comments":0,"downloads":186,"installs":0,"stars":0,"versions":4},"createdAt":1785264810385,"updatedAt":1785590777130,"latestVersion":{"version":"0.1.3","createdAt":1785590713727,"changelog":"- Removed the sample skill-card.md file.\n- SKILL.md: Shortened the description for clarity and conciseness; functionality and safety notes unchanged.\n- No code or command changes. Only documentation and file cleanup.","license":null},"metadata":null},{"slug":"smyx-family-conflict-intensity-detect-analysis","displayName":"Family / Couple Conflict Intensity Detection | 夫妻/家庭争吵强度识别","summary":"Using a fixed camera with microphone in the living room, the system analyzes audio and video in real time, detecting sound intensity (dB) and the intensity of body movements (e.g., rapid hand waving, finger pointing, pushing, throwing objects). It comprehensively evaluates the family conflict intensity level (low / medium / high). | 通过客厅固定摄像头（含麦克风），实时分析音频和视频，检测声音强度（分贝）和肢体动作激烈程度（如快速挥手、戳指、推搡、摔物等）。综合评估家庭争吵的冲突强度等级（低/中/高），当强度达到中或高时，通过手机APP推送提醒（如'检测到高强度冲突，建议冷静沟通或暂时分开'）。","description":"Using a fixed camera with microphone in the living room, the system analyzes audio and video in real time, detecting sound intensity (dB) and the intensity of body movements (e.g., rapid hand waving, finger pointing, pushing, throwing objects). It comprehensively evaluates the family conflict intensity level (low / medium / high). | 通过客厅固定摄像头（含麦克风），实时分析音频和视频，检测声音强度（分贝）和肢体动作激烈程度（如快速挥手、戳指、推搡、摔物等）。综合评估家庭争吵的冲突强度等级（低/中/高），当强度达到中或高时，通过手机APP推送提醒（如'检测到高强度冲突，建议冷静沟通或暂时分开'）。","topics":["Smart Home","健康管理","智能家居","Audio","Health"],"tags":{"latest":"1.0.4"},"stats":{"comments":0,"downloads":601,"installs":7,"stars":0,"versions":5},"createdAt":1779847345685,"updatedAt":1785590516793,"latestVersion":{"version":"1.0.4","createdAt":1785590372305,"changelog":"- Updated SKILL.md content, including version bump from 1.0.6 to 1.0.8\n- Removed redundant file: skill-card.md\n- Documentation improvements and clarifications in SKILL.md\n- No code or workflow changes detected","license":null},"metadata":null},{"slug":"gemini-mcp","displayName":"Tmp.EUU09c2J1a","summary":"Generate and edit images, video, and music with Google Gemini models via MCP. Use when the user asks to generate, create, or edit images (Gemini / Nano Banana), produce a consistent set of images, compose/blend multiple images, generate a short video (text→video or image→video, via the omni model), or generate music/audio clips (via Lyria). Triggers on phrases like \"generate an image of\", \"edit this image with Gemini\", \"create a set of consistent images\", \"make a video of\", \"generate a video\", \"generate music\", \"make a song/audio clip\", \"use Nano Banana to make\", or any request to produce images, video, or music via the Gemini API. Requires the @chrischall/gemini-mcp package installed and the gemini server registered (see Setup below).","description":"Generate and edit images, video, and music with Google Gemini models via MCP. Use when the user asks to generate, create, or edit images (Gemini / Nano Banana), produce a consistent set of images, compose/blend multiple images, generate a short video (text→video or image→video, via the omni model), or generate music/audio clips (via Lyria). Triggers on phrases like \"generate an image of\", \"edit this image with Gemini\", \"create a set of consistent images\", \"make a video of\", \"generate a video\", \"generate music\", \"make a song/audio clip\", \"use Nano Banana to make\", or any request to produce images, video, or music via the Gemini API. Requires the @chrischall/gemini-mcp package installed and the gemini server registered (see Setup below).","topics":["Prompt"],"tags":{"latest":"1.5.1"},"stats":{"comments":0,"downloads":1100,"installs":8,"stars":0,"versions":22},"createdAt":1780881114509,"updatedAt":1785589777882,"latestVersion":{"version":"1.5.1","createdAt":1785589643152,"changelog":"gemini-mcp 1.5.1\n\n- Removed the sample file \"skill-card.md\" from the repository.\n- No changes to functionality or usage.","license":null},"metadata":null},{"slug":"xmemo","displayName":"XMemo Memory","summary":"Persistent user-owned memory for agents with standalone runtime execution. Use when an agent should remember, recall, search memory, save or restore handoff state, manage TODOs, record expenses, diagnose XMemo auth, or operate XMemo even when MCP tools are not configured.","description":"Persistent user-owned memory for agents with standalone runtime execution. Use when an agent should remember, recall, search memory, save or restore handoff state, manage TODOs, record expenses, diagnose XMemo auth, or operate XMemo even when MCP tools are not configured.","topics":["memory","agent-memory","long-term-memory","cross-agent-memory","ai-agents"],"tags":{"latest":"1.0.10"},"stats":{"comments":0,"downloads":716,"installs":5,"stars":6,"versions":11},"createdAt":1780943020859,"updatedAt":1785589042205,"latestVersion":{"version":"1.0.10","createdAt":1785588971575,"changelog":"- Removed the sample file skill-card.md.\n- Updated documentation to clarify temporary memory policy: item cap, inactivity expiry, and maximum lifetime are disclosed before registration.\n- Noted that the bundled script does not expose memory deletion or overwrite commands—users must use an authorized product surface for destructive operations.\n- Added or clarified CLI commands: `auth-status` and `auth claim-deny`.\n- Provided additional detail on temporary access limits and memory operations in SKILL.md.","license":null},"metadata":null},{"slug":"agent4-io","displayName":"agent4.io","summary":"Build and run grounded business agents on agent4.io over MCP — agents, knowledge bases, load-on-demand skills, stateful Storylines and page playbooks.","description":"Build and run grounded business agents on agent4.io over MCP — agents, knowledge bases, load-on-demand skills, stateful Storylines and page playbooks.","topics":[],"tags":{"latest":"1.1.6"},"stats":{"comments":0,"downloads":569,"installs":1,"stars":0,"versions":42},"createdAt":1785276275360,"updatedAt":1785588698265,"latestVersion":{"version":"1.1.6","createdAt":1785588620518,"changelog":"Per-step icebreaker questions (node.questions chips), step summaries in the read-only map (click a taken step to see what it collected), whole-key blackboard packing for long flows, New-chat dropdown fix.","license":null},"metadata":{"setup":[{"key":"AGENT4_API_KEY","required":true}],"os":null,"systems":null}},{"slug":"shieldcortex","displayName":"ShieldCortex","summary":"Memory and defence for AI agents: semantic recall, knowledge graph and decay, plus a memory firewall that scans and enforces against prompt injection, credential leaks and poisoning.","description":"Memory and defence for AI agents: semantic recall, knowledge graph and decay, plus a memory firewall that scans and enforces against prompt injection, credential leaks and poisoning.","topics":["Prompt Injection","Learning"],"tags":{"latest":"4.47.26"},"stats":{"comments":0,"downloads":4843,"installs":97,"stars":2,"versions":126},"createdAt":1770998187206,"updatedAt":1785588224939,"latestVersion":{"version":"4.47.26","createdAt":1785588070867,"changelog":"Auto-sync from npm publish v4.47.26","license":null},"metadata":null}],"nextCursor":"{\"v\":1,\"index\":\"by_active_updated\",\"key\":[{\"__undef\":1},1785588224939,1773255984503.605,\"r179f6darykk514ezab5ayrkah82qq7y\"]}"}