[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MB0PYCX2JA3D2RKFSQFW1N":3,"skill-same:01M6MB0PYCX2JA3D2RKFSQFW1N":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":67,"ownerHtmlUrl":68,"ownerBlogUrl":69,"ownerDescription":70,"updatedAt":71,"install":72,"resources":85},"01M6MB0PYCX2JA3D2RKFSQFW1N","research-skill-creator",null,"Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet the Agent Skills specification and this repository's quality and security bar. Use when turning a repeated research task into a reusable skill, contributing a new skill to Research Agent Skills, rewriting an existing skill, writing trigger-accurate descriptions, or adding evals. Works alongside Anthropic's official skill-creator.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1559,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fresearch-skill-creator\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"skill creator","research","research skill creator","creator","new","writing","when","Meet","research agent skills","skill-creator","specification","uv","databases","eval","loop","improve","research agent","analysis","Paper Writing","create","official","skill authoring","workflows","2026-11-10 10:12:30",false,"---\nname: research-skill-creator\ndescription: Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet the Agent Skills specification and this repository's quality and security bar. Use when turning a repeated research task into a reusable skill, contributing a new skill to Research Agent Skills, rewriting an existing skill, writing trigger-accurate descriptions, or adding evals. Works alongside Anthropic's official skill-creator.\nlicense: MIT\ncompatibility: Python 3.9+ for the scaffold script. Repository validators need uv. Anthropic's skill-creator (optional) provides the eval loop.\nmetadata:\n  version: \"1.0\"\n  category: research-automation\n  maintainer: Kalaris Labs\n  author: Kalaris Labs (Sayan Chowdhury)\n  tags: skill authoring, agent skills, SKILL.md, evals, contributing\n---\n\n# Research Skill Creator\n\nA good research skill packages *procedural knowledge an expert would otherwise\nhave to explain every time*: the order of steps, the checks that catch mistakes,\nthe venue- or instrument-specific rules. It is not a textbook chapter and not a\nwrapper around one API call.\n\n## 0. Install the official tooling (once)\n\nAnthropic's `skill-creator` supplies the eval loop, description optimizer and\npackager. In Claude Code:\n\n```text\n\u002Fplugin marketplace add anthropics\u002Fskills\n\u002Fplugin install example-skills@anthropic-agent-skills\n```\n\nUse it to run evals (`run_eval.py`, `run_loop.py`) and to tune the description\n(`improve_description.py`). This skill adds the research-specific conventions.\n\n## 1. Decide whether it should be a skill\n\nCreate a skill when **all** hold:\n- The task recurs across projects or people (not a one-off script).\n- Doing it well requires non-obvious steps, checks or domain rules.\n- An agent would plausibly get it wrong without guidance (test this: ask without the skill first).\n\nOtherwise write a note or a script instead. Check `catalog\u002Fskills.json` for overlap and\nextend an existing skill rather than creating a near-duplicate.\n\n## 2. Scaffold\n\n```bash\npython skills\u002Fresearch-skill-creator\u002Fscripts\u002Fnew_skill.py rebuttal-letter \\\n  --category research-writing \\\n  --description \"Draft point-by-point responses to peer reviewers. Use when ...\" \\\n  --scripts --references\n```\n\nThis writes `skills\u002F\u003Cname>\u002FSKILL.md` with spec-compliant frontmatter and `evals\u002F\u003Cname>\u002Fevals.json`.\n\n## 3. Write the description (it decides whether the skill is ever used)\n\n- Say **what it does** and **when to use it**, with the words users actually type:\n  \"journal cover letter\", \"response to reviewers\", \"PRISMA flow diagram\".\n- Name concrete artifacts, tools and venues (\"BibTeX\", \"Nature\", \"pgvector\").\n- At most 1024 characters, third person, no angle brackets, no marketing adjectives.\n- Add \"Use when ...\" clauses for the 3-6 most common triggers, plus distinguishing\n  cues vs. sibling skills (e.g. \"for systems venues use systems-paper-writing\").\n\n## 4. Write the body\n\n| Principle | Practice |\n|---|---|\n| Procedure over prose | Numbered workflows, decision tables, checklists |\n| Progressive disclosure | SKILL.md under 500 lines; long material in `references\u002F*.md`, linked with one-line \"read when\" hints |\n| Deterministic work in code | Parsing, validation and conversion go in `scripts\u002F`, which the agent runs rather than re-implements |\n| Verify-first for facts that change | Venue limits, API versions, guidelines: tell the agent to fetch the official source and cite it |\n| Honesty rules | Explicit \"never fabricate data, citations or results; say when unverifiable\" |\n| Handoffs | End with related skills and when to switch |\n\n## 5. Scripts: the repository contract\n\n- Python 3.9+ **standard library** unless a dependency is essential. Declare it in `compatibility`.\n- `argparse` CLI with `--help`, a docstring with usage, exit codes `0` ok, `1` findings, `2` bad input.\n- UTF-8 console setup (the scaffold includes it) so Windows terminals don't crash.\n- Network calls only to documented APIs. Every new domain must be added to\n  `security\u002Fallowed-domains.txt` with a reviewer's approval. Set a descriptive `User-Agent`.\n- Never read credentials beyond the env var the user configures for that service. Never\n  exfiltrate environment data. No `eval`\u002F`exec` of fetched content. Never pipe downloaded scripts into a shell.\n\n## 6. Test\n\n1. `uv run tools\u002Fvalidate.py skills\u002F\u003Cname>`: spec + repo policy.\n2. `uv run tools\u002Flint_injection.py skills\u002F\u003Cname>`: prompt-injection and payload lint.\n3. Fill `evals\u002F\u003Cname>\u002Fevals.json` with 3-10 realistic prompts, including near-misses that\n   should **not** trigger, and run them with skill-creator's eval loop. Compare with\u002Fwithout the skill.\n4. Run each script on real sample inputs, including malformed ones, on Windows and Unix if possible.\n5. `uv run tools\u002Fbuild_catalog.py` to regenerate the marketplace, catalog and README tables.\n\n## 7. Rewriting an adapted skill\n\nSkills listed in `third_party\u002Fupstream-manifest.json` with `rewrite_status: imported`\nare adaptations. A rewrite must be written from scratch (new structure, new\nwording, re-verified facts), not paraphrased line by line. When it merges, set\n`rewrite_status: original` for that skill in the manifest. The notices generator then\ndrops it from `THIRD_PARTY_NOTICES.md` and the importer stops overwriting it.\n\n## Related skills\n\n`research-agent-skills` repository docs (`CONTRIBUTING.md`), Anthropic `skill-creator`,\n`autoskill` (detects repeated workflows worth turning into skills).\n","# Research Skill Creator\n\nA good research skill packages *procedural knowledge an expert would otherwise\nhave to explain every time*: the order of steps, the checks that catch mistakes,\nthe venue- or instrument-specific rules. It is not a textbook chapter and not a\nwrapper around one API call.\n\n## 0. Install the official tooling (once)\n\nAnthropic's `skill-creator` supplies the eval loop, description optimizer and\npackager. In Claude Code:\n\n```text\n\u002Fplugin marketplace add anthropics\u002Fskills\n\u002Fplugin install example-skills@anthropic-agent-skills\n```\n\nUse it to run evals (`run_eval.py`, `run_loop.py`) and to tune the description\n(`improve_description.py`). This skill adds the research-specific conventions.\n\n## 1. Decide whether it should be a skill\n\nCreate a skill when **all** hold:\n- The task recurs across projects or people (not a one-off script).\n- Doing it well requires non-obvious steps, checks or domain rules.\n- An agent would plausibly get it wrong without guidance (test this: ask without the skill first).\n\nOtherwise write a note or a script instead. Check `catalog\u002Fskills.json` for overlap and\nextend an existing skill rather than creating a near-duplicate.\n\n## 2. Scaffold\n\n```bash\npython skills\u002Fresearch-skill-creator\u002Fscripts\u002Fnew_skill.py rebuttal-letter \\\n  --category research-writing \\\n  --description \"Draft point-by-point responses to peer reviewers. Use when ...\" \\\n  --scripts --references\n```\n\nThis writes `skills\u002F\u003Cname>\u002FSKILL.md` with spec-compliant frontmatter and `evals\u002F\u003Cname>\u002Fevals.json`.\n\n## 3. Write the description (it decides whether the skill is ever used)\n\n- Say **what it does** and **when to use it**, with the words users actually type:\n  \"journal cover letter\", \"response to reviewers\", \"PRISMA flow diagram\".\n- Name concrete artifacts, tools and venues (\"BibTeX\", \"Nature\", \"pgvector\").\n- At most 1024 characters, third person, no angle brackets, no marketing adjectives.\n- Add \"Use when ...\" clauses for the 3-6 most common triggers, plus distinguishing\n  cues vs. sibling skills (e.g. \"for systems venues use systems-paper-writing\").\n\n## 4. Write the body\n\n| Principle | Practice |\n|---|---|\n| Procedure over prose | Numbered workflows, decision tables, checklists |\n| Progressive disclosure | SKILL.md under 500 lines; long material in `references\u002F*.md`, linked with one-line \"read when\" hints |\n| Deterministic work in code | Parsing, validation and conversion go in `scripts\u002F`, which the agent runs rather than re-implements |\n| Verify-first for facts that change | Venue limits, API versions, guidelines: tell the agent to fetch the official source and cite it |\n| Honesty rules | Explicit \"never fabricate data, citations or results; say when unverifiable\" |\n| Handoffs | End with related skills and when to switch |\n\n## 5. Scripts: the repository contract\n\n- Python 3.9+ **standard library** unless a dependency is essential. Declare it in `compatibility`.\n- `argparse` CLI with `--help`, a docstring with usage, exit codes `0` ok, `1` findings, `2` bad input.\n- UTF-8 console setup (the scaffold includes it) so Windows terminals don't crash.\n- Network calls only to documented APIs. Every new domain must be added to\n  `security\u002Fallowed-domains.txt` with a reviewer's approval. Set a descriptive `User-Agent`.\n- Never read credentials beyond the env var the user configures for that service. Never\n  exfiltrate environment data. No `eval`\u002F`exec` of fetched content. Never pipe downloaded scripts into a shell.\n\n## 6. Test\n\n1. `uv run tools\u002Fvalidate.py skills\u002F\u003Cname>`: spec + repo policy.\n2. `uv run tools\u002Flint_injection.py skills\u002F\u003Cname>`: prompt-injection and payload lint.\n3. Fill `evals\u002F\u003Cname>\u002Fevals.json` with 3-10 realistic prompts, including near-misses that\n   should **not** trigger, and run them with skill-creator's eval loop. Compare with\u002Fwithout the skill.\n4. Run each script on real sample inputs, including malformed ones, on Windows and Unix if possible.\n5. `uv run tools\u002Fbuild_catalog.py` to regenerate the marketplace, catalog and README tables.\n\n## 7. Rewriting an adapted skill\n\nSkills listed in `third_party\u002Fupstream-manifest.json` with `rewrite_status: imported`\nare adaptations. A rewrite must be written from scratch (new structure, new\nwording, re-verified facts), not paraphrased line by line. When it merges, set\n`rewrite_status: original` for that skill in the manifest. The notices generator then\ndrops it from `THIRD_PARTY_NOTICES.md` and the importer stops overwriting it.\n\n## Related skills\n\n`research-agent-skills` repository docs (`CONTRIBUTING.md`), Anthropic `skill-creator`,\n`autoskill` (detects repeated workflows worth turning into skills).\n",{"name":5,"license":15,"metadata":55,"description":7,"compatibility":61},{"tags":56,"author":57,"version":58,"category":59,"maintainer":60},"skill authoring, agent skills, SKILL.md, evals, contributing","Kalaris Labs (Sayan Chowdhury)","1.0","research-automation","Kalaris Labs","Python 3.9+ for the scaffold script. Repository validators need uv. Anthropic's skill-creator (optional) provides the eval loop.","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fresearch-skill-creator",474,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-11 14:40:14",{"source":8,"skillName":5,"commands":73,"prompt":83,"zipAvailable":84},[74,77,80],{"tool":75,"command":76},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill research-skill-creator",{"tool":78,"command":79},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill research-skill-creator",{"tool":81,"command":82},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill research-skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fresearch-skill-creator\u002FSKILL.md",true,[86],{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fnew_skill.py","SCRIPT","脚本",6233,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fresearch-skill-creator\u002Fscripts\u002Fnew_skill.py",[93,102,109,116,142,167],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":101},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":101},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":101},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":50},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[123,124,125,126,127,128,129,130,131,132,133,33,134,135,136,137,138,139,140,141],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","you","done","reviewer","io","change","cli","merge","past",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":50},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[149,150,151,137,152,153,154,155,156,157,158,159,160,161,128,162,163,164,165,166],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":180,"publishedAt":50},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[173,176,177],{"categoryNo":174,"categoryName":175,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":178,"categoryName":179,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[169,181,182,183,184,185,186,163,187,129,188,189,190,191,33,192,193,194,195,196],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]