[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K7VTJ5SSKJDBY24VFDN01":3,"skill-same:01M75K7VTJ5SSKJDBY24VFDN01":46},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M75K7VTJ5SSKJDBY24VFDN01","roadmap-author",null,"Author a new ORS skill from scratch using the v0.4.0 schema. Produces a valid SKILL.md (frontmatter + metadata + sections) following spec\u002Fskill-format.md, guided by spec\u002Fauthor-guide.md, validated by scripts\u002Fvalidate-skills.py. Use when a user says 'add a new skill', 'create a skill for X', or 'I want to contribute a skill'.","pradyumnasagar\u002Fopen-research-skills","pradyumnasagar","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10559871?v=4","01M75K78MYCCVKRTYGT8KKC380","Pradyumna Jayaram","01M75K78NTNE41F2PE1XBVFHAS",8,"MIT","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Fmeta\u002Froadmap-author\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: roadmap-author\ndescription: \"Author a new ORS skill from scratch using the v0.4.0 schema. Produces a valid SKILL.md (frontmatter + metadata + sections) following spec\u002Fskill-format.md, guided by spec\u002Fauthor-guide.md, validated by scripts\u002Fvalidate-skills.py. Use when a user says 'add a new skill', 'create a skill for X', or 'I want to contribute a skill'.\"\nlicense: MIT\n---\n\u003C!-- metadata:\n  oversight: low\n  version: 1.0.0\n  author: ORS maintainers\n  tags: [meta, authoring, schema, contributing]\n  difficulty: beginner\n-->\n\n# Roadmap Author\n\nAuthor a new ORS skill that passes `scripts\u002Fvalidate-skills.py` on first run.\n\n## When to use\n\n- A user asks to add a new skill, contribute a skill, or extend ORS with a new\n  tool, format, or workflow.\n- You need a guided tour through the v0.4.0 schema (frontmatter + metadata\n  block + body sections) and the validator's expectations.\n- You are converting an external agent prompt or Claude skill into ORS\n  format and want the resulting SKILL.md to be schema-compliant.\n\n## When NOT to use\n\n- The user wants to *use* an existing skill (load that skill directly).\n- The skill already exists and the task is to *update* it (use\n  `meta\u002Frelease-management`).\n- The task is to audit a skill for quality issues before publishing (use\n  `meta\u002Fintegrity-audit`).\n\n## Hard rules\n\n1. **No fabricated citations.** Every cited work must resolve to a verifiable\n   record (DOI, PMID, arXiv ID, ISBN, URL with retrieval date, or stable\n   identifier). If a source cannot be resolved, the skill must say so\n   explicitly rather than presenting the claim as established.\n2. **No claim without provenance.** Every quantitative or factual claim\n   must point to a file, line, table, figure, dataset, or external source\n   the agent can show. \"Trust me\" is not provenance.\n3. **No silent failure.** Every script invocation, API call, or tool use\n   must declare its exit status and what to do on non-zero. A skill that\n   silently swallows errors is a violation.\n\n## Author workflow\n\nA new skill goes through 6 steps. Skipping steps produces skills that fail\nthe validator or don't fit the catalog.\n\n### Step 1: Pick the category\n\nEvery skill belongs to one category (a subdirectory of `skills\u002F`). Pick\nthe existing one that best matches the domain, or propose a new category\nif the domain is genuinely missing. Categories are: `bioinformatics-sequence`,\n`chemoinformatics`, `clinical-research`, `data-engineering`, `experimental-design`,\n`hypothesis-generation`, `imaging`, `literature-research`, `meta`,\n`pharmacology`, `scientific-communication`, `scientific-writing`,\n`statistics`, `structural-biology`, `systems-biology`,\n`visualization-and-figure-prep`, `workflow-and-pipeline-management`,\n`writing-and-drafting`.\n\n**Rule:** The category MUST be a leaf category — do not invent sub-categories\ninside a leaf. If a leaf is too coarse, propose a new leaf in a GitHub issue.\n\n### Step 2: Pick the slug\n\nThe slug is the skill's kebab-case directory name. Rules:\n- Lowercase, kebab-case (e.g. `bwa-alignment`, not `bwa_alignment` or `BWA-Alignment`).\n- No version suffix in the slug. Versioning goes in the metadata block.\n- No `ors-` prefix. The slug is the bare tool name.\n- Must be unique across `skills\u002F`.\n\n**Rule:** The slug becomes the cross-reference key (see\n`meta\u002Fcross-reference-mapper`). Changing the slug after publication breaks\nlinks.\n\n### Step 3: Write the frontmatter\n\nThe YAML frontmatter is the *Anthropic* skill spec — `name`, `description`,\noptional `license`. The `description` field is what Claude sees when deciding\nto load the skill, so it must:\n- Start with the tool\u002Fworkflow name.\n- Describe the core capability in 1-2 sentences.\n- State the trigger conditions (when to load).\n- State the negative triggers (when NOT to load).\n\nMaximum length: 1024 characters.\n\n### Step 4: Write the metadata block\n\nThe `\u003C!-- metadata: ... -->` block captures ORS-specific fields:\n\n```yaml\n\u003C!-- metadata:\n  category: \u003Cone of the leaf categories>\n  oversight: \u003Cvery-high | high | medium | low>\n  version: \u003Csemver>\n  author: \u003Cname>\n  tags: [\u003Ckebab-case tags>]\n  difficulty: \u003Cbeginner | intermediate | advanced>\n-->\n```\n\nThe `oversight` field tells Claude how much to trust the skill:\n- `very-high` — generative, may fabricate facts (e.g. literature review)\n- `high` — mixed, may contain plausible-but-wrong details\n- `medium` — framework is reliable, specifics need verification\n- `low` — deterministic, mechanical (e.g. format conversion)\n\nThe `difficulty` field tells the user how much background knowledge is\nrequired to use the skill effectively.\n\n### Step 5: Write the body\n\nRequired body sections (in order):\n\n1. `# \u003CSkill Name>` — the H1, must match the frontmatter `name` in human form.\n2. `## When to use` — 3-10 trigger bullets. Be specific. \"Use this skill for\n   any kind of analysis\" is useless.\n3. `## When NOT to use` — 2-5 anti-trigger bullets. Cross-reference sibling\n   skills that *do* fit.\n4. `## Hard rules` — the 3 base rules (cite, claim-provenance, no-silent-fail).\n   Add 0-5 domain-specific rules. Domain rules are concrete, not aspirational\n   (\"Check exit codes on every shell call\" not \"Be careful\").\n5. `## Workflow` — the main procedure. Numbered steps, with example commands.\n6. `## Code patterns` — copy-pasteable snippets, not pseudocode.\n7. `## Validation` — how the user verifies the skill worked.\n8. `## Cross-references` — sibling skill slugs, one per line, with a\n   one-line description. See `meta\u002Fcross-reference-mapper`.\n9. `## Changelog` — version history. Latest version first.\n\nOptional sections (highly recommended): `## Pitfalls`, `## References`,\n`## Decision tree`, `## Per-tool failure modes`.\n\n### Step 6: Validate\n\nRun from the repo root:\n\n```bash\npython scripts\u002Fvalidate-skills.py skills\u002F\u003Ccategory>\u002F\u003Cslug>\u002F\n```\n\nMust exit 0. If errors, fix and re-run. Do not commit a skill that fails\nvalidation.\n\n## Validation\n\nThe skill is valid when:\n- `python scripts\u002Fvalidate-skills.py \u003Cpath>\u002F` exits 0.\n- The skill can be loaded by Claude without frontmatter parsing errors.\n- A user reading only the description can decide whether to load it.\n\n## Cross-references\n\n- meta\u002Fintegrity-audit — audit a draft skill against the 7-mode AI failure checklist.\n- meta\u002Frelease-management — version bumps, changelog discipline, marketplace sync.\n- meta\u002Fcross-reference-mapper — find related skills across categories automatically.\n\n## Related docs (not skills)\n\n- `spec\u002Fskill-format.md` — the formal v0.4.0 schema definition.\n- `spec\u002Fauthor-guide.md` — narrative guidance for first-time authors.\n\n## Changelog\n\n- **1.0.0** (2026-06-17) — Initial release. Authoring workflow distilled from\n  the v0.4.0 spec and the lessons of bulk-migrating 116 existing skills.\n","\u003C!-- metadata:\n  oversight: low\n  version: 1.0.0\n  author: ORS maintainers\n  tags: [meta, authoring, schema, contributing]\n  difficulty: beginner\n-->\n\n# Roadmap Author\n\nAuthor a new ORS skill that passes `scripts\u002Fvalidate-skills.py` on first run.\n\n## When to use\n\n- A user asks to add a new skill, contribute a skill, or extend ORS with a new\n  tool, format, or workflow.\n- You need a guided tour through the v0.4.0 schema (frontmatter + metadata\n  block + body sections) and the validator's expectations.\n- You are converting an external agent prompt or Claude skill into ORS\n  format and want the resulting SKILL.md to be schema-compliant.\n\n## When NOT to use\n\n- The user wants to *use* an existing skill (load that skill directly).\n- The skill already exists and the task is to *update* it (use\n  `meta\u002Frelease-management`).\n- The task is to audit a skill for quality issues before publishing (use\n  `meta\u002Fintegrity-audit`).\n\n## Hard rules\n\n1. **No fabricated citations.** Every cited work must resolve to a verifiable\n   record (DOI, PMID, arXiv ID, ISBN, URL with retrieval date, or stable\n   identifier). If a source cannot be resolved, the skill must say so\n   explicitly rather than presenting the claim as established.\n2. **No claim without provenance.** Every quantitative or factual claim\n   must point to a file, line, table, figure, dataset, or external source\n   the agent can show. \"Trust me\" is not provenance.\n3. **No silent failure.** Every script invocation, API call, or tool use\n   must declare its exit status and what to do on non-zero. A skill that\n   silently swallows errors is a violation.\n\n## Author workflow\n\nA new skill goes through 6 steps. Skipping steps produces skills that fail\nthe validator or don't fit the catalog.\n\n### Step 1: Pick the category\n\nEvery skill belongs to one category (a subdirectory of `skills\u002F`). Pick\nthe existing one that best matches the domain, or propose a new category\nif the domain is genuinely missing. Categories are: `bioinformatics-sequence`,\n`chemoinformatics`, `clinical-research`, `data-engineering`, `experimental-design`,\n`hypothesis-generation`, `imaging`, `literature-research`, `meta`,\n`pharmacology`, `scientific-communication`, `scientific-writing`,\n`statistics`, `structural-biology`, `systems-biology`,\n`visualization-and-figure-prep`, `workflow-and-pipeline-management`,\n`writing-and-drafting`.\n\n**Rule:** The category MUST be a leaf category — do not invent sub-categories\ninside a leaf. If a leaf is too coarse, propose a new leaf in a GitHub issue.\n\n### Step 2: Pick the slug\n\nThe slug is the skill's kebab-case directory name. Rules:\n- Lowercase, kebab-case (e.g. `bwa-alignment`, not `bwa_alignment` or `BWA-Alignment`).\n- No version suffix in the slug. Versioning goes in the metadata block.\n- No `ors-` prefix. The slug is the bare tool name.\n- Must be unique across `skills\u002F`.\n\n**Rule:** The slug becomes the cross-reference key (see\n`meta\u002Fcross-reference-mapper`). Changing the slug after publication breaks\nlinks.\n\n### Step 3: Write the frontmatter\n\nThe YAML frontmatter is the *Anthropic* skill spec — `name`, `description`,\noptional `license`. The `description` field is what Claude sees when deciding\nto load the skill, so it must:\n- Start with the tool\u002Fworkflow name.\n- Describe the core capability in 1-2 sentences.\n- State the trigger conditions (when to load).\n- State the negative triggers (when NOT to load).\n\nMaximum length: 1024 characters.\n\n### Step 4: Write the metadata block\n\nThe `\u003C!-- metadata: ... -->` block captures ORS-specific fields:\n\n```yaml\n\u003C!-- metadata:\n  category: \u003Cone of the leaf categories>\n  oversight: \u003Cvery-high | high | medium | low>\n  version: \u003Csemver>\n  author: \u003Cname>\n  tags: [\u003Ckebab-case tags>]\n  difficulty: \u003Cbeginner | intermediate | advanced>\n-->\n```\n\nThe `oversight` field tells Claude how much to trust the skill:\n- `very-high` — generative, may fabricate facts (e.g. literature review)\n- `high` — mixed, may contain plausible-but-wrong details\n- `medium` — framework is reliable, specifics need verification\n- `low` — deterministic, mechanical (e.g. format conversion)\n\nThe `difficulty` field tells the user how much background knowledge is\nrequired to use the skill effectively.\n\n### Step 5: Write the body\n\nRequired body sections (in order):\n\n1. `# \u003CSkill Name>` — the H1, must match the frontmatter `name` in human form.\n2. `## When to use` — 3-10 trigger bullets. Be specific. \"Use this skill for\n   any kind of analysis\" is useless.\n3. `## When NOT to use` — 2-5 anti-trigger bullets. Cross-reference sibling\n   skills that *do* fit.\n4. `## Hard rules` — the 3 base rules (cite, claim-provenance, no-silent-fail).\n   Add 0-5 domain-specific rules. Domain rules are concrete, not aspirational\n   (\"Check exit codes on every shell call\" not \"Be careful\").\n5. `## Workflow` — the main procedure. Numbered steps, with example commands.\n6. `## Code patterns` — copy-pasteable snippets, not pseudocode.\n7. `## Validation` — how the user verifies the skill worked.\n8. `## Cross-references` — sibling skill slugs, one per line, with a\n   one-line description. See `meta\u002Fcross-reference-mapper`.\n9. `## Changelog` — version history. Latest version first.\n\nOptional sections (highly recommended): `## Pitfalls`, `## References`,\n`## Decision tree`, `## Per-tool failure modes`.\n\n### Step 6: Validate\n\nRun from the repo root:\n\n```bash\npython scripts\u002Fvalidate-skills.py skills\u002F\u003Ccategory>\u002F\u003Cslug>\u002F\n```\n\nMust exit 0. If errors, fix and re-run. Do not commit a skill that fails\nvalidation.\n\n## Validation\n\nThe skill is valid when:\n- `python scripts\u002Fvalidate-skills.py \u003Cpath>\u002F` exits 0.\n- The skill can be loaded by Claude without frontmatter parsing errors.\n- A user reading only the description can decide whether to load it.\n\n## Cross-references\n\n- meta\u002Fintegrity-audit — audit a draft skill against the 7-mode AI failure checklist.\n- meta\u002Frelease-management — version bumps, changelog discipline, marketplace sync.\n- meta\u002Fcross-reference-mapper — find related skills across categories automatically.\n\n## Related docs (not skills)\n\n- `spec\u002Fskill-format.md` — the formal v0.4.0 schema definition.\n- `spec\u002Fauthor-guide.md` — narrative guidance for first-time authors.\n\n## Changelog\n\n- **1.0.0** (2026-06-17) — Initial release. Authoring workflow distilled from\n  the v0.4.0 spec and the lessons of bulk-migrating 116 existing skills.\n",{"name":5,"license":15,"description":7},"main","9c0b41e2036cc5588c699f06e658ea6dc3b9685d","meta\u002Froadmap-author",2,"https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar","PhD Scholar,\r\nManipal School Of Life Sciences, Manipal\r\n #OpenSourceDeveloper #LifeSciences #ComputationalBiology","2026-10-30 01:30:52",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add pradyumnasagar\u002Fopen-research-skills --skill roadmap-author",{"tool":38,"command":39},"bunx","bunx skills add pradyumnasagar\u002Fopen-research-skills --skill roadmap-author",{"tool":41,"command":42},"pnpm","pnpm dlx skills add pradyumnasagar\u002Fopen-research-skills --skill roadmap-author","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Fmeta\u002Froadmap-author\u002FSKILL.md",true,[],[47,54,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M75KTS5K9QNX8FQBTJW2GQSH","good-skill","A well-formed test fixture for the validation script.","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M75KTR7FAT0MMMED2EGC9WZZ","BadSkill","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fbad-skill\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M75KTN949EDF77GJDS8H6VR8","my-new-skill","One sentence (max 200 chars) — what the skill does and when to use it.","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Ftemplate\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M75KTHTFS121SSF1Q5X2FXDA","thesis-structure","Use when planning or checking the architecture of a PhD \u002F MPhil thesis in the life sciences or bioinformatics — monograph vs article-based, chapter sequence, IMRaD-based chapters, abstract-to-conclusion flow, and the examiner expectations that the structure must meet.","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Fskills\u002Fthesis-writing\u002Fthesis-structure\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M75KTE3WKW46FXFHQ579H8YP","thesis-methods-reproducibility","Use when writing or checking the Methods, figures, data, and code of a bioinformatics \u002F microbiology \u002F life-science PhD thesis — the FAIR data, versioned code, report-generation, figure-and-table discipline, and the reproducibility expectations that examiners probe at viva.","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Fskills\u002Fthesis-writing\u002Fthesis-methods-reproducibility\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M75KTA033ZQCJY3DC8P5VQET","thesis-defense-viva","Use when preparing for the viva voce \u002F oral thesis defense — building the examiner's question set, rehearsing the presentation, and the pre-defense polish (slides, summary, the 'what if I'm stuck' responses) for a life-science or bioinformatics PhD.","https:\u002F\u002Fgithub.com\u002Fpradyumnasagar\u002Fopen-research-skills\u002Fblob\u002Fmain\u002Fskills\u002Fthesis-writing\u002Fthesis-defense-viva\u002FSKILL.md",[],[]]