[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75Z01BA8H7M1JSCBESQ2V6C":3,"skill-same:01M75Z01BA8H7M1JSCBESQ2V6C":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75Z01BA8H7M1JSCBESQ2V6C","semantic-compression",null,"Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fragments. Use when compressing text for prompts, reducing token count, preparing context for LLM input, or making documentation more token-efficient. Applies LLM-aware compression rules that delete predictable grammar while preserving semantics.","microbotdata-dev\u002Foh-my-pi","microbotdata-dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F266543605?v=4","01M75YZY1V4XRYMJX491T21XNA","01M75YZY2JHT6HCJTZ74CFPH0B",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Fsemantic-compression\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: semantic-compression\ndescription: Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fragments. Use when compressing text for prompts, reducing token count, preparing context for LLM input, or making documentation more token-efficient. Applies LLM-aware compression rules that delete predictable grammar while preserving semantics.\n---\n\n# Semantic Compression\n\nLLMs reconstruct grammar from content words. Remove predictable glue; keep semantic payload. Prefer fragments over sentences.\n\n## Aggressive Stance\n\n- Output can be noun\u002Fverb stacks, list fragments, or label:value phrases.\n- Default to deletion; keep function words only when loss changes meaning.\n- Prefer base verb forms; drop tense\u002Faspect unless timeline is critical.\n\n## Deletion Tiers\n\n**Tier 1 — Always delete (even if fragments):**\n- Articles: a, an, the\n- Copulas: is, are, was, were, am, be, been, being\n- Expletive subjects: \"There is\u002Fare...\", \"It is...\"\n- Complementizer: that (as clause marker)\n- Pure intensifiers: very, quite, rather, really, extremely, somewhat\n- Filler phrases: \"in order to\" → to, \"due to the fact that\" → because, \"in terms of\" → delete\n- Infinitive \"to\" before verbs (unless it prevents noun\u002Fverb confusion)\n- Conjunctions when list\u002Fcontrast obvious: and, or, but\n\n**Tier 2 — Delete unless meaning changes:**\n- Auxiliary verbs: have\u002Fhas\u002Fhad, do\u002Fdoes\u002Fdid, will\u002Fwould (keep if tense\u002Faspect matters)\n- Modal verbs: can\u002Fcould\u002Fmay\u002Fmight\u002Fshould (keep when obligation\u002Fpermission\u002Fpossibility is critical; always keep must\u002Fmust not)\n- Pronouns: it\u002Fthis\u002Fthat\u002Fthese\u002Fthose\u002Fhe\u002Fshe\u002Fthey (drop when referent obvious; replace with noun if ambiguous)\n- Relative pronouns: which, that, who, whom\n- Prepositions: of, for, to, in, on, at, by (keep for material, direction, agency, or disambiguation)\n\n**Tier 3 — Delete only if relation still clear:**\n- Remaining prepositions: with\u002Fwithout, between\u002Famong, within, after\u002Fbefore, over\u002Funder, through (drop only if relation obvious)\n- Redundant adverbs: \"shout loudly\" → \"shout\"\n\n## Always Preserve\n\n- Nouns, main verbs, meaning-bearing adjectives\u002Fadverbs\n- Numbers, quantifiers: \"at least 5\", \"approximately\", \"more than\"\n- Uncertainty markers: \"appears\", \"seems\", \"reportedly\", \"what sounded like\"\n- Negation: not, no, never, without, none\n- Temporal markers: dates, frequencies, durations\n- Causality and conditionals: because, therefore, despite, although, if, unless\n- Requirements\u002Fpermissions: must, required, prohibited, allowed\n- Proper nouns, titles, technical terms\n- Prepositions encoding relationships: from\u002Fto (direction), with\u002Fwithout (inclusion), between\u002Famong\u002Fwithin (relation), after\u002Fbefore (temporal), by (agent if passive)\n\n## Structural Compression\n\n- Passive → active when agent known: \"was eaten by dog\" → \"dog ate\"\n- Nominalization → verb: \"made a decision\" → \"decided\"\n- Drop implied subject when context allows: \"System should log errors\" → \"Log errors\"\n- Redundant pairs → single: \"each and every\" → \"every\"\n- Clause → modifier: \"anomaly that was reported\" → \"reported anomaly\"\n\n## Examples\n\n| Original | Compressed |\n|----------|------------|\n| The system was designed to efficiently process incoming data from multiple sources | System design: efficient process incoming data, multiple sources |\n| There were at least 20 people who appeared to be waiting | At least 20 people apparent waiting |\n| It is important to note that the medication should not be taken without food | Medication: should not take without food |\n| The researcher made a decision to investigate the anomaly that was reported | Researcher decided: investigate reported anomaly |\n","# Semantic Compression\n\nLLMs reconstruct grammar from content words. Remove predictable glue; keep semantic payload. Prefer fragments over sentences.\n\n## Aggressive Stance\n\n- Output can be noun\u002Fverb stacks, list fragments, or label:value phrases.\n- Default to deletion; keep function words only when loss changes meaning.\n- Prefer base verb forms; drop tense\u002Faspect unless timeline is critical.\n\n## Deletion Tiers\n\n**Tier 1 — Always delete (even if fragments):**\n- Articles: a, an, the\n- Copulas: is, are, was, were, am, be, been, being\n- Expletive subjects: \"There is\u002Fare...\", \"It is...\"\n- Complementizer: that (as clause marker)\n- Pure intensifiers: very, quite, rather, really, extremely, somewhat\n- Filler phrases: \"in order to\" → to, \"due to the fact that\" → because, \"in terms of\" → delete\n- Infinitive \"to\" before verbs (unless it prevents noun\u002Fverb confusion)\n- Conjunctions when list\u002Fcontrast obvious: and, or, but\n\n**Tier 2 — Delete unless meaning changes:**\n- Auxiliary verbs: have\u002Fhas\u002Fhad, do\u002Fdoes\u002Fdid, will\u002Fwould (keep if tense\u002Faspect matters)\n- Modal verbs: can\u002Fcould\u002Fmay\u002Fmight\u002Fshould (keep when obligation\u002Fpermission\u002Fpossibility is critical; always keep must\u002Fmust not)\n- Pronouns: it\u002Fthis\u002Fthat\u002Fthese\u002Fthose\u002Fhe\u002Fshe\u002Fthey (drop when referent obvious; replace with noun if ambiguous)\n- Relative pronouns: which, that, who, whom\n- Prepositions: of, for, to, in, on, at, by (keep for material, direction, agency, or disambiguation)\n\n**Tier 3 — Delete only if relation still clear:**\n- Remaining prepositions: with\u002Fwithout, between\u002Famong, within, after\u002Fbefore, over\u002Funder, through (drop only if relation obvious)\n- Redundant adverbs: \"shout loudly\" → \"shout\"\n\n## Always Preserve\n\n- Nouns, main verbs, meaning-bearing adjectives\u002Fadverbs\n- Numbers, quantifiers: \"at least 5\", \"approximately\", \"more than\"\n- Uncertainty markers: \"appears\", \"seems\", \"reportedly\", \"what sounded like\"\n- Negation: not, no, never, without, none\n- Temporal markers: dates, frequencies, durations\n- Causality and conditionals: because, therefore, despite, although, if, unless\n- Requirements\u002Fpermissions: must, required, prohibited, allowed\n- Proper nouns, titles, technical terms\n- Prepositions encoding relationships: from\u002Fto (direction), with\u002Fwithout (inclusion), between\u002Famong\u002Fwithin (relation), after\u002Fbefore (temporal), by (agent if passive)\n\n## Structural Compression\n\n- Passive → active when agent known: \"was eaten by dog\" → \"dog ate\"\n- Nominalization → verb: \"made a decision\" → \"decided\"\n- Drop implied subject when context allows: \"System should log errors\" → \"Log errors\"\n- Redundant pairs → single: \"each and every\" → \"every\"\n- Clause → modifier: \"anomaly that was reported\" → \"reported anomaly\"\n\n## Examples\n\n| Original | Compressed |\n|----------|------------|\n| The system was designed to efficiently process incoming data from multiple sources | System design: efficient process incoming data, multiple sources |\n| There were at least 20 people who appeared to be waiting | At least 20 people apparent waiting |\n| It is important to note that the medication should not be taken without food | Medication: should not take without food |\n| The researcher made a decision to investigate the anomaly that was reported | Researcher decided: investigate reported anomaly |\n",{"name":5,"description":7},"main","f219efab0df19b1dad5113a026a0fc340df64418",".omp\u002Fskills\u002Fsemantic-compression",0,"https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev","2026-06-21 17:05:30",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add microbotdata-dev\u002Foh-my-pi --skill semantic-compression",{"tool":36,"command":37},"bunx","bunx skills add microbotdata-dev\u002Foh-my-pi --skill semantic-compression",{"tool":39,"command":40},"pnpm","pnpm dlx skills add microbotdata-dev\u002Foh-my-pi --skill semantic-compression","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Fsemantic-compression\u002FSKILL.md",true,[],[45,52,59,66,72,79],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75Z0MYWNQ2Q6QTTRQ61E3H5","greet","A greeting skill for testing","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Fmarketplace\u002Ffixtures\u002Fvalid-marketplace\u002Fplugins\u002Fhello-plugin\u002Fskills\u002Fgreet\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75Z0M3FFG9QKSNFVS6D1TGE","valid-skill","A valid skill for testing purposes.","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fvalid-skill\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75Z0K48T613RE0RMJPKBMYY","unknown-field","A skill with an unknown frontmatter field.","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Funknown-field\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M75Z0H8BY7H2HXPQ3CGAR65S","no-frontmatter","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fno-frontmatter\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M75Z0G97YNEMWD3S3EMM6CVD","child-skill","A nested skill in a subdirectory.","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fnested\u002Fchild-skill\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M75Z0F7ZZ98C5TZ1ANZ78XDH","different-name","A skill with a name that doesn't match the directory.","https:\u002F\u002Fgithub.com\u002Fmicrobotdata-dev\u002Foh-my-pi\u002Fblob\u002Fmain\u002Fpackages\u002Fcoding-agent\u002Ftest\u002Ffixtures\u002Fskills\u002Fname-mismatch\u002FSKILL.md",[],[]]