[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CP82EWA0FRR07Q6CXSGNF9":3,"skill-same:01M6CP82EWA0FRR07Q6CXSGNF9":76},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6CP82EWA0FRR07Q6CXSGNF9","dsh-trim-cot-leakage",null,"Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as \"used to\", \"no longer\", \"this cut\"; stack or review vantage (\"a later PR in this stack\", \"rejected in review\"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.","gccszs\u002FWorldSoul","gccszs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85680574?v=4","01M6CP73CSF9QGSTGE0NMMX8WV","cris_tofu","01M6CP73H2C65X28TS1NATXRZT",2,"MIT","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-trim-cot-leakage\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"dsh trim cot leakage","Citations","prose","narration","later","use","session","reviewer","decision","stack","design","flow","audit","transcript","reasoning","planning","pr","notes","change","docs","2026-11-10 10:12:30",false,"---\nname: dsh-trim-cot-leakage\ndescription: Use when auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as \"used to\", \"no longer\", \"this cut\"; stack or review vantage (\"a later PR in this stack\", \"rejected in review\"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.\n---\n\n# Trimming Chain-of-Thought Leakage\n\nChain-of-thought leakage is prose whose vantage is the authoring session rather than the repository: it cites artifacts only that session could see, narrates the change instead of the state, or argues with a reviewer who has left. The fix is never deletion alone when a passage carries factual clauses — restate each so it stands at HEAD, then delete the transcript around it; a passage carrying none (an audit code, control-flow narration) is deleted outright. **REQUIRED BACKGROUND:** [dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md) owns the complete-proposition rule this skill applies; the [committed-artifact-citations note](..\u002F..\u002Fnotes\u002Fimplemented\u002Fprocess\u002F2026-08-09-committed-artifact-citations.md) owns the citation rule's rationale. It is guidance, not a script.\n\n## The one test\n\nFor every suspect passage ask: **could a reader at HEAD, with no access to any session transcript, PR thread, or uncommitted draft, resolve every reference and verify every claim?** If no, restate the surviving facts from the repository's vantage and delete the rest. If yes, it is not leakage, however historical it sounds — but resolvability only clears this skill's bar: on current-state surfaces (READMEs, docs, JSDoc) a resolvable change story is still change narration, and class 3 routes it to its sanctioned home.\n\n## Taxonomy\n\n1. **Dead design-session citations** — `(decision 7)`, `(audit C2)`, `design §4.7`, `plan §1.4`, phase labels (`T4`, `W3`, `P-I`), \"the design ledger\", \"(B ruling)\". If the decision has a committed owner, cite it by name and path; otherwise delete the citation and restate its factual clause to stand alone.\n2. **Stack and PR vantage** — \"a later PR in this stack\", \"this PR adds\", \"the previous commit\". State the shipped mechanism or the extension point; deferred work moves to a `TODO` marker or an issue reference.\n3. **Change narration and version stamps** — \"used to\", \"no longer\", \"the old X\", and indexical stamps (\"v1\", \"this cut\", \"today\", \"now\" contrasting with a past state). State the present behavior; a fixed regression becomes a present-tense counterfactual (\"without X, Y happens\"), never repo history (\"used to Y\").\n4. **Review choreography** — \"Rejected in review:\", \"the reviewer confirmed\", draft ordinals (\"v5 of this note\"), round attributions. Keep the surviving decision and rationale as plain fact; delete who said it when.\n5. **Reviewer-addressed justification** — \"the cast is safe — it simply…\", \"this is correct because…\". A comment arguing its own correctness addresses a reviewer, not a maintainer. State the invariant that makes the code safe, or delete the comment if the code shows it.\n6. **Restatement and derivation transcripts** — control-flow narration (\"first we X, then we Y\"), test walkthroughs, proofs of obvious branches. Delete; keep only a non-obvious contract or invariant.\n7. **Hedges and planning residue** — \"probably fine for now\", \"should be enough\", deferrals with no marker. Promote to `TODO`\u002F`FIXME` or restate as the actual bound; delete the hedge.\n8. **Authoring-language slips** — untranslated working-language fragments (端, 设计稿, `---- 私有 ----` separators) in prose whose language is otherwise English, or the reverse in a zh counterpart. Translate or delete.\n\n## What is not leakage\n\nUnaided citation passes fail in both directions by deleting durable references and keeping dead ones. Apply these keep rules as written; [examples](references\u002Fexamples.md) calibrates each:\n\n- **Issue references** — `#1470`, `TODO(name):`, \"issue #N owns the follow-up\" resolve at HEAD; keep them on any surface, including READMEs. Do not relocate them to Agent Notes.\n- **Merged-PR and issue citations inside Agent Notes and postmortems** — sanctioned evidence per the [documentation standard](..\u002F..\u002F..\u002Fdocs\u002FAGENTS.md)'s change-story routing.\n- **Suppression justifications** — `oxlint-disable … -- reason`, coverage-ignore reasons, empty-catch explanations are required prose; fix a false reason, never delete it.\n- **Counterfactual-present regression pins** — \"without X, Y happens\", \"a naive X would…\".\n- **Measured bounds** — \"(measured: 512 nests ≈ 0.15s)\" calibrating a constant; the provenance word \"measured\" is load-bearing.\n- **Runtime old\u002Fnew states** — \"the old connection drains before the new one accepts\" is runtime lifecycle, not change history.\n- **Historical stage names inside a note's change-story sections** — \"the first cut shipped X\" is current-state-safe there; indexical stamps (\"this cut\") stay banned everywhere.\n- **External references that resolve outside the repo by design** — standards sections (RFC 9110 §10.1.5), Figma frame names; the §-ban covers uncommitted internal drafts, not external standards or committed docs that own their §-numbering.\n- **Project voice and genre forms** — \"we\" as project voice; a note's Alternatives-considered section.\n\n## Workflow\n\n1. Scope and exclusions per [dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md): require an explicit scope; never touch `vendor\u002F` or `.agents\u002Fnotes\u002Farchived\u002F`. Recorded fixtures and snapshots are derivatives, not prose targets: change the owning source or scenario and regenerate them only when an authorized behavior change requires new evidence.\n2. Audit read-only first: run the [recall batteries](references\u002Frecall-batteries.md) (with `--hidden` so `.agents\u002F` is searched), calibrating each probe against a known positive and a near-miss negative before trusting its output, then judge every hit semantically. The batteries are probes, not the definition — each review round of the original purge found cases the batteries missed, so also read the densest prose in scope (module JSDoc, READMEs, Agent Notes) without a pattern in hand.\n3. Fix owner-first per surface: generated catalogs → trace every consumer, fix the source JSDoc or generator template, then regenerate all derivatives; type-equivalence fences → fix the source JSDoc, then re-paste both bilingual pages (`verify-type-equiv` pins them); bilingual prose → update the counterpart minimally and re-record it through the [lightweight routine](..\u002F..\u002F..\u002Fdocs\u002FAGENTS.md#writing-rules); bilingual fences → copy the corrected verbatim block byte-for-byte into both sides per [dsh-doc](..\u002Fdsh-doc\u002FSKILL.md), then re-record the pair; model- or user-visible strings → route through [dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md) and change only with owning behavior evidence, otherwise leave unchanged and report the deferral.\n4. Before deleting anything, enumerate the passage's propositions (prose-standard) and check the [overcorrection traps](references\u002Fexamples.md#overcorrection-traps): trims that flip an obligation into an endorsement, promote a hypothetical to a shipped feature, delete a true fact, or drop provenance.\n5. Verify: re-run the batteries expecting only sanctioned keeps, this skill's own directory, and the owning note's quoted evidence; confirm every remaining citation resolves at HEAD; run the gates for touched surfaces (`doc-sync` for docs, `verify-type-equiv`, `verify-translation-pairing`).\n","# Trimming Chain-of-Thought Leakage\n\nChain-of-thought leakage is prose whose vantage is the authoring session rather than the repository: it cites artifacts only that session could see, narrates the change instead of the state, or argues with a reviewer who has left. The fix is never deletion alone when a passage carries factual clauses — restate each so it stands at HEAD, then delete the transcript around it; a passage carrying none (an audit code, control-flow narration) is deleted outright. **REQUIRED BACKGROUND:** [dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md) owns the complete-proposition rule this skill applies; the [committed-artifact-citations note](..\u002F..\u002Fnotes\u002Fimplemented\u002Fprocess\u002F2026-08-09-committed-artifact-citations.md) owns the citation rule's rationale. It is guidance, not a script.\n\n## The one test\n\nFor every suspect passage ask: **could a reader at HEAD, with no access to any session transcript, PR thread, or uncommitted draft, resolve every reference and verify every claim?** If no, restate the surviving facts from the repository's vantage and delete the rest. If yes, it is not leakage, however historical it sounds — but resolvability only clears this skill's bar: on current-state surfaces (READMEs, docs, JSDoc) a resolvable change story is still change narration, and class 3 routes it to its sanctioned home.\n\n## Taxonomy\n\n1. **Dead design-session citations** — `(decision 7)`, `(audit C2)`, `design §4.7`, `plan §1.4`, phase labels (`T4`, `W3`, `P-I`), \"the design ledger\", \"(B ruling)\". If the decision has a committed owner, cite it by name and path; otherwise delete the citation and restate its factual clause to stand alone.\n2. **Stack and PR vantage** — \"a later PR in this stack\", \"this PR adds\", \"the previous commit\". State the shipped mechanism or the extension point; deferred work moves to a `TODO` marker or an issue reference.\n3. **Change narration and version stamps** — \"used to\", \"no longer\", \"the old X\", and indexical stamps (\"v1\", \"this cut\", \"today\", \"now\" contrasting with a past state). State the present behavior; a fixed regression becomes a present-tense counterfactual (\"without X, Y happens\"), never repo history (\"used to Y\").\n4. **Review choreography** — \"Rejected in review:\", \"the reviewer confirmed\", draft ordinals (\"v5 of this note\"), round attributions. Keep the surviving decision and rationale as plain fact; delete who said it when.\n5. **Reviewer-addressed justification** — \"the cast is safe — it simply…\", \"this is correct because…\". A comment arguing its own correctness addresses a reviewer, not a maintainer. State the invariant that makes the code safe, or delete the comment if the code shows it.\n6. **Restatement and derivation transcripts** — control-flow narration (\"first we X, then we Y\"), test walkthroughs, proofs of obvious branches. Delete; keep only a non-obvious contract or invariant.\n7. **Hedges and planning residue** — \"probably fine for now\", \"should be enough\", deferrals with no marker. Promote to `TODO`\u002F`FIXME` or restate as the actual bound; delete the hedge.\n8. **Authoring-language slips** — untranslated working-language fragments (端, 设计稿, `---- 私有 ----` separators) in prose whose language is otherwise English, or the reverse in a zh counterpart. Translate or delete.\n\n## What is not leakage\n\nUnaided citation passes fail in both directions by deleting durable references and keeping dead ones. Apply these keep rules as written; [examples](references\u002Fexamples.md) calibrates each:\n\n- **Issue references** — `#1470`, `TODO(name):`, \"issue #N owns the follow-up\" resolve at HEAD; keep them on any surface, including READMEs. Do not relocate them to Agent Notes.\n- **Merged-PR and issue citations inside Agent Notes and postmortems** — sanctioned evidence per the [documentation standard](..\u002F..\u002F..\u002Fdocs\u002FAGENTS.md)'s change-story routing.\n- **Suppression justifications** — `oxlint-disable … -- reason`, coverage-ignore reasons, empty-catch explanations are required prose; fix a false reason, never delete it.\n- **Counterfactual-present regression pins** — \"without X, Y happens\", \"a naive X would…\".\n- **Measured bounds** — \"(measured: 512 nests ≈ 0.15s)\" calibrating a constant; the provenance word \"measured\" is load-bearing.\n- **Runtime old\u002Fnew states** — \"the old connection drains before the new one accepts\" is runtime lifecycle, not change history.\n- **Historical stage names inside a note's change-story sections** — \"the first cut shipped X\" is current-state-safe there; indexical stamps (\"this cut\") stay banned everywhere.\n- **External references that resolve outside the repo by design** — standards sections (RFC 9110 §10.1.5), Figma frame names; the §-ban covers uncommitted internal drafts, not external standards or committed docs that own their §-numbering.\n- **Project voice and genre forms** — \"we\" as project voice; a note's Alternatives-considered section.\n\n## Workflow\n\n1. Scope and exclusions per [dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md): require an explicit scope; never touch `vendor\u002F` or `.agents\u002Fnotes\u002Farchived\u002F`. Recorded fixtures and snapshots are derivatives, not prose targets: change the owning source or scenario and regenerate them only when an authorized behavior change requires new evidence.\n2. Audit read-only first: run the [recall batteries](references\u002Frecall-batteries.md) (with `--hidden` so `.agents\u002F` is searched), calibrating each probe against a known positive and a near-miss negative before trusting its output, then judge every hit semantically. The batteries are probes, not the definition — each review round of the original purge found cases the batteries missed, so also read the densest prose in scope (module JSDoc, READMEs, Agent Notes) without a pattern in hand.\n3. Fix owner-first per surface: generated catalogs → trace every consumer, fix the source JSDoc or generator template, then regenerate all derivatives; type-equivalence fences → fix the source JSDoc, then re-paste both bilingual pages (`verify-type-equiv` pins them); bilingual prose → update the counterpart minimally and re-record it through the [lightweight routine](..\u002F..\u002F..\u002Fdocs\u002FAGENTS.md#writing-rules); bilingual fences → copy the corrected verbatim block byte-for-byte into both sides per [dsh-doc](..\u002Fdsh-doc\u002FSKILL.md), then re-record the pair; model- or user-visible strings → route through [dsh-prose-standard](..\u002Fdsh-prose-standard\u002FSKILL.md) and change only with owning behavior evidence, otherwise leave unchanged and report the deferral.\n4. Before deleting anything, enumerate the passage's propositions (prose-standard) and check the [overcorrection traps](references\u002Fexamples.md#overcorrection-traps): trims that flip an obligation into an endorsement, promote a hypothetical to a shipped feature, delete a true fact, or drop provenance.\n5. Verify: re-run the batteries expecting only sanctioned keeps, this skill's own directory, and the owning note's quoted evidence; confirm every remaining citation resolves at HEAD; run the gates for touched surfaces (`doc-sync` for docs, `verify-type-equiv`, `verify-translation-pairing`).\n",{"name":5,"description":7},"main","d682beee161da2963de0a1bc91d17efc54ea8689","worldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-trim-cot-leakage",0,"https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul","https:\u002F\u002Fgithub.com\u002Fgccszs","Code is cheap! Show me your prompt.","2026-09-27 15:07:46",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add gccszs\u002FWorldSoul --skill dsh-trim-cot-leakage",{"tool":58,"command":59},"bunx","bunx skills add gccszs\u002FWorldSoul --skill dsh-trim-cot-leakage",{"tool":61,"command":62},"pnpm","pnpm dlx skills add gccszs\u002FWorldSoul --skill dsh-trim-cot-leakage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-trim-cot-leakage\u002FSKILL.md",true,[66,72],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fexamples.md","REFERENCE","参考文档",12577,"https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-trim-cot-leakage\u002Freferences\u002Fexamples.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Frecall-batteries.md",5041,"https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002F.agents\u002Fskills\u002Fdsh-trim-cot-leakage\u002Freferences\u002Frecall-batteries.md",[77,90,108,116,131,155],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":39},"01M6CP8JPZRGT3SEHGSV9AHG4H","user-only-skill","Prove model-disabled skills stay outside the model catalog.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fuser-only-skill\u002FSKILL.md",[],[84,85,86,87,88,89],"user","only","user only skill","model catalog","model","catalog",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":101,"publishedAt":39},"01M6CP8H9P868EE1HX81BRXY0Y","snapshot-skill","Exercise project skill discovery and loading in snapshot tests.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fsnapshot-skill\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[102,103,104,105,106,107],"snapshot skill","snapshot","discovery","exercise","project skill","skill discovery",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":39},"01M6CP8FWAC3866R4B6R8GZ04V","model-only-skill","Prove user-disabled skills remain available to the model.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.dsh\u002Fskills\u002Fmodel-only-skill\u002FSKILL.md",[],[88,85,115,84],"model only skill",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":39},"01M6CP8DE65MXX0KW3TMP2655R","editing-cordis-compositions","Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fpackages\u002Fpreset\u002Fagent-presets\u002Fpresets\u002Fcordis\u002Fskills\u002Fediting-cordis-compositions\u002FSKILL.md",[],[123,124,125,126,25,24,127,128,129,130],"editing cordis compositions","editing","harness","Composition","but","writing","plugin","preset",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":39},"01M6CP8A0ACVBGHRR5M9X77KBG","cordis-plugin-development","Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider, then define, run, repair, or roll back the Plugin.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fpackages\u002Fpreset\u002Fagent-presets\u002Fpresets\u002Fcordis\u002Fskills\u002Fcordis-plugin-development\u002FSKILL.md",[],[138,139,129,140,141,142,143,144,145,146,147,148,149,84,150,24,151,152,153,154],"cordis plugin development","development","Tools","debug","diagnostics","create","run","package","plugins","ui","services","correct","approval","version","provider","back","route",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":39},"01M6CP88NJH71DR1W6MRQ6ZMN6","preview-tour","Inspect the bundled Preview workspace and its deterministic Session examples.","https:\u002F\u002Fgithub.com\u002Fgccszs\u002FWorldSoul\u002Fblob\u002Fmain\u002Fworldsoul-harness\u002Fpackages\u002Fexperimental\u002Fwebworker-runtime\u002Ftests\u002Ffixtures\u002Fvfs-example\u002Fworkspace\u002F.agents\u002Fskills\u002Fpreview-tour\u002FSKILL.md",[],[162,163,25,164,165],"preview tour","workspace","deterministic","examples"]