[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C0H4JS57V4QDB722DDRWYW":3,"skill-same:01M7C0H4JS57V4QDB722DDRWYW":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},"01M7C0H4JS57V4QDB722DDRWYW","source-completeness",null,"Validates that all user-facing surfaces discovered in source code are captured in the behavioral specs. Catches coverage gaps where the analysis pipeline missed features, tools, env vars, CLI flags, or other behavioral interfaces. Run AFTER Layer 3 specs are written, BEFORE sanitization.","zak-keown\u002Fmoe","zak-keown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F320717241?v=4","01M7BZFXME0NW6TQX0H7AZM2KS","01M7BZFXN32VR0JN5AATRD53H4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-backstory\u002F.opencode\u002Fskills\u002Fsource-completeness\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: source-completeness\ndescription: Validates that all user-facing surfaces discovered in source code are captured in the behavioral specs. Catches coverage gaps where the analysis pipeline missed features, tools, env vars, CLI flags, or other behavioral interfaces. Run AFTER Layer 3 specs are written, BEFORE sanitization.\n---\n\n# Source-to-Spec Completeness Validation\n\n## Why This Exists\n\nThe analysis pipeline (Layers 1-3) reads source code and produces behavioral specs. But it can miss things:\n- Registered commands or tools defined in source but not in the tool catalog\n- Environment variables read by the code but not documented\n- CLI flags defined in the argument parser but not cataloged\n- Subcommands registered dynamically or conditionally\n- Config keys accessed in settings but not listed in the config spec\n- Events dispatched but not inventoried\n- Error categories defined but not documented\n\nThe fidelity validation (Layer 7) only checks raw→clean. This skill checks **source→raw** — it goes back to the actual source code and verifies that every discoverable user-facing surface was captured in the specs.\n\n## When to Run\n\nRun AFTER Layer 3 deep documentation is complete, ideally as part of Gate 1 or as a pre-Gate-1 completeness check. If gaps are found, dispatch deep-dive agents to cover the missing areas before proceeding.\n\nAlso run AFTER Layer 7 fidelity validation to catch anything the fidelity check couldn't find (because it was never in the raw specs).\n\n## The Checks\n\nSearch patterns depend on target shape. For a single-file bundle, grep the bundle directly. For a source tree, grep recursively across the source root. Patterns also depend on the target language's idioms for registering each surface — the examples below give common patterns for several languages; adjust to the actual target.\n\n### Check 1: Tool \u002F Command Registration Completeness\n\nApplies to targets that expose a registered command, tool, or handler surface (CLIs with subcommands, plugin hosts, RPC servers with method registration).\n\n**Source extraction:** grep for the registration pattern used by the target. Examples:\n\n```bash\n# Named-object pattern (common in JS\u002FTS\u002FGo handler registration)\ngrep -roE 'name:\\s*\"[A-Z][a-zA-Z]+\"' \u003Csource-root> | sort -u\n\n# Decorator-based registration (Python)\ngrep -roE '@(command|tool|handler|register)\\(' \u003Csource-root>\n\n# Macro-based registration (Rust)\ngrep -roE '#\\[(command|tool|handler)' \u003Csource-root>\n\n# Assigned-constant pattern (JS\u002FTS)\ngrep -roE 'var [a-zA-Z0-9_]+=\"[A-Z][a-zA-Z]+\"' \u003Csource-root> | grep -v 'Exception\\|Error\\|Element'\n```\n\n**Spec extraction:** every registered name in the tool\u002Fcommand catalog section of the spec.\n\n**Diff:** every registered name in source must appear in the spec. Missing names are P0-CRITICAL gaps.\n\n### Check 2: Environment Variable Completeness\n\n**Source extraction:** patterns by language:\n\n```bash\n# Node\u002FTypeScript\ngrep -roE 'process\\.env\\.[A-Z_][A-Z0-9_]*' \u003Csource-root> | sed 's\u002F.*process\\.env\\.\u002F\u002F' | sort -u\n# Python\ngrep -roE 'os\\.environ(\\.get)?\\(?\"[A-Z_][A-Z0-9_]*\"' \u003Csource-root> | grep -oE '[A-Z_][A-Z0-9_]+' | sort -u\n# Go\ngrep -roE 'os\\.Getenv\\(\"[A-Z_][A-Z0-9_]*\"\\)' \u003Csource-root> | grep -oE '[A-Z_][A-Z0-9_]+' | sort -u\n# Rust\ngrep -roE 'env::var\\(\"[A-Z_][A-Z0-9_]*\"\\)' \u003Csource-root> | grep -oE '[A-Z_][A-Z0-9_]+' | sort -u\n```\n\n**Spec extraction:** all env var names from the environment contract spec.\n\n**Diff:** categorize missing env vars:\n- User-facing (`DATABASE_*`, `AWS_*`, `GCP_*`, `LOG_*`, and similar) → P0: must document\n- Internal-only (test vars, build vars) → P2: note but don't require\n- Standard (`HOME`, `PATH`, `SHELL`, `TERM`) → ignore\n\n### Check 3: CLI Flag Completeness\n\n**Source extraction:**\n\n```bash\n# Quoted flag strings — works across most CLI frameworks\ngrep -roE '\"--[a-z][a-z0-9-]+\"' \u003Csource-root> | sort -u\n\n# Framework-specific definitions:\n#   Rust\u002Fclap:    .arg(\"--flag-name\")\n#   Python\u002Fargparse: add_argument(\"--flag-name\")\n#   Go\u002Fflag:      flag.StringVar(&v, \"--flag-name\", ...)\ngrep -roE '\\.arg\\(\"--[a-z-]+\"|add_argument\\(\"--[a-z-]+\"|flag\\.\\w+Var\\([^,]+,\\s*\"--[a-z-]+\"' \u003Csource-root>\n```\n\n**Spec extraction:** every `--flag` name in the CLI contract spec.\n\n**Diff:** every flag must appear. Hidden flags should be documented as hidden.\n\n### Check 4: Subcommand Completeness\n\nApplies to CLIs or REPLs with a subcommand surface.\n\n**Source extraction:** target-dependent. For subcommand CLIs, grep for the subcommand registration or dispatch table (clap subcommands, Cobra, argparse subparsers). For REPL-style interfaces, grep for the command-prefix pattern (e.g., `\u002Fhelp`, `:quit`).\n\n**Spec extraction:** every subcommand from the CLI interface spec.\n\n**Diff:** every registered subcommand must appear.\n\n### Check 5: Event Dispatch Completeness\n\nApplies to targets that dispatch named events — common shapes include observer patterns, signals, message buses, and webhook emission.\n\n**Source extraction:** grep for event dispatch calls and event-type string constants. Common shapes: `emit(\"event-name\", ...)`, `dispatch(EventType.X)`, `pubsub.publish(\"...\", ...)`, signal\u002Fslot registrations, `raise EventName(...)`.\n\n**Spec extraction:** every event type documented in the extensibility or eventing spec.\n\n**Diff:** every dispatched event type must be documented.\n\n### Check 6: Config Key Completeness\n\n**Source extraction:** Search for settings property accesses and config key strings.\n\n**Spec extraction:** Extract all config keys from the configuration spec.\n\n**Diff:** User-configurable keys must appear. Internal state keys are P2.\n\n### Check 7: Error Category Completeness\n\n**Source extraction:** Search for error class definitions, error type enums, and error message constants.\n\n**Spec extraction:** Extract all documented error categories.\n\n**Diff:** User-visible errors must be documented.\n\n## Report Format\n\n```markdown\n# Source-to-Spec Completeness Report\n\n## Summary\n| Check | Source Count | Spec Count | Missing | Extra |\n|-------|-------------|------------|---------|-------|\n| Registered commands\u002Ftools | N | N | N | N |\n| Env Vars | N | N | N | N |\n| CLI Flags | N | N | N | N |\n| Subcommands | N | N | N | N |\n| Events dispatched | N | N | N | N |\n| Config Keys | N | N | N | N |\n| Error Categories | N | N | N | N |\n\n## P0-CRITICAL Gaps (must fix)\n[List all missing user-facing surfaces]\n\n## P1 Gaps (should fix)\n[List missing non-critical surfaces]\n\n## P2 Gaps (advisory)\n[List internal-only surfaces]\n\n## Verdict: PASS | FAIL\nPASS requires zero P0 gaps.\n```\n\n## Agent Dispatch Pattern\n\nDispatch as `moe-backstory:analyzer` since it needs to read both source code and specs. Can be parallelized:\n- One agent per check (7 agents), or\n- Batch checks 1-3 (commands\u002Ftools, env vars, CLI flags) and checks 4-7 (subcommands, events, config keys, errors) into 2 agents\n\n## Relationship to Other Validations\n\n```\nSource Code → [Layer 1-3 analysis] → Raw Specs → [Layer 5 sanitization] → Output Specs\n                                          ↑                                        ↑\n                                    source-completeness                     fidelity-validation\n                                    (source → raw)                      (raw → clean)\n                                          ↑                                        ↑\n                                    \"Did we capture it?\"                   \"Did we preserve it?\"\n```\n\nTogether these two validations form a complete chain: source-completeness ensures nothing was missed during analysis, and fidelity-validation ensures nothing was lost during sanitization.\n\n## Integration with Public Documentation\n\nWhen public documentation is available (docs mode was active), cross-reference the source findings against official docs:\n- Features documented in official docs but missing from specs → P0 gap\n- Features in source but not in official docs → likely internal, lower priority\n- Features in official docs but not in source → version mismatch or deprecated\n\nThis cross-reference is especially valuable because official documentation represents the **intended** user-facing surface, while source extraction finds the **actual** surface. Discrepancies in either direction are informative.\n","# Source-to-Spec Completeness Validation\n\n## Why This Exists\n\nThe analysis pipeline (Layers 1-3) reads source code and produces behavioral specs. But it can miss things:\n- Registered commands or tools defined in source but not in the tool catalog\n- Environment variables read by the code but not documented\n- CLI flags defined in the argument parser but not cataloged\n- Subcommands registered dynamically or conditionally\n- Config keys accessed in settings but not listed in the config spec\n- Events dispatched but not inventoried\n- Error categories defined but not documented\n\nThe fidelity validation (Layer 7) only checks raw→clean. This skill checks **source→raw** — it goes back to the actual source code and verifies that every discoverable user-facing surface was captured in the specs.\n\n## When to Run\n\nRun AFTER Layer 3 deep documentation is complete, ideally as part of Gate 1 or as a pre-Gate-1 completeness check. If gaps are found, dispatch deep-dive agents to cover the missing areas before proceeding.\n\nAlso run AFTER Layer 7 fidelity validation to catch anything the fidelity check couldn't find (because it was never in the raw specs).\n\n## The Checks\n\nSearch patterns depend on target shape. For a single-file bundle, grep the bundle directly. For a source tree, grep recursively across the source root. Patterns also depend on the target language's idioms for registering each surface — the examples below give common patterns for several languages; adjust to the actual target.\n\n### Check 1: Tool \u002F Command Registration Completeness\n\nApplies to targets that expose a registered command, tool, or handler surface (CLIs with subcommands, plugin hosts, RPC servers with method registration).\n\n**Source extraction:** grep for the registration pattern used by the target. Examples:\n\n```bash\n# Named-object pattern (common in JS\u002FTS\u002FGo handler registration)\ngrep -roE 'name:\\s*\"[A-Z][a-zA-Z]+\"' \u003Csource-root> | sort -u\n\n# Decorator-based registration (Python)\ngrep -roE '@(command|tool|handler|register)\\(' \u003Csource-root>\n\n# Macro-based registration (Rust)\ngrep -roE '#\\[(command|tool|handler)' \u003Csource-root>\n\n# Assigned-constant pattern (JS\u002FTS)\ngrep -roE 'var [a-zA-Z0-9_]+=\"[A-Z][a-zA-Z]+\"' \u003Csource-root> | grep -v 'Exception\\|Error\\|Element'\n```\n\n**Spec extraction:** every registered name in the tool\u002Fcommand catalog section of the spec.\n\n**Diff:** every registered name in source must appear in the spec. Missing names are P0-CRITICAL gaps.\n\n### Check 2: Environment Variable Completeness\n\n**Source extraction:** patterns by language:\n\n```bash\n# Node\u002FTypeScript\ngrep -roE 'process\\.env\\.[A-Z_][A-Z0-9_]*' \u003Csource-root> | sed 's\u002F.*process\\.env\\.\u002F\u002F' | sort -u\n# Python\ngrep -roE 'os\\.environ(\\.get)?\\(?\"[A-Z_][A-Z0-9_]*\"' \u003Csource-root> | grep -oE '[A-Z_][A-Z0-9_]+' | sort -u\n# Go\ngrep -roE 'os\\.Getenv\\(\"[A-Z_][A-Z0-9_]*\"\\)' \u003Csource-root> | grep -oE '[A-Z_][A-Z0-9_]+' | sort -u\n# Rust\ngrep -roE 'env::var\\(\"[A-Z_][A-Z0-9_]*\"\\)' \u003Csource-root> | grep -oE '[A-Z_][A-Z0-9_]+' | sort -u\n```\n\n**Spec extraction:** all env var names from the environment contract spec.\n\n**Diff:** categorize missing env vars:\n- User-facing (`DATABASE_*`, `AWS_*`, `GCP_*`, `LOG_*`, and similar) → P0: must document\n- Internal-only (test vars, build vars) → P2: note but don't require\n- Standard (`HOME`, `PATH`, `SHELL`, `TERM`) → ignore\n\n### Check 3: CLI Flag Completeness\n\n**Source extraction:**\n\n```bash\n# Quoted flag strings — works across most CLI frameworks\ngrep -roE '\"--[a-z][a-z0-9-]+\"' \u003Csource-root> | sort -u\n\n# Framework-specific definitions:\n#   Rust\u002Fclap:    .arg(\"--flag-name\")\n#   Python\u002Fargparse: add_argument(\"--flag-name\")\n#   Go\u002Fflag:      flag.StringVar(&v, \"--flag-name\", ...)\ngrep -roE '\\.arg\\(\"--[a-z-]+\"|add_argument\\(\"--[a-z-]+\"|flag\\.\\w+Var\\([^,]+,\\s*\"--[a-z-]+\"' \u003Csource-root>\n```\n\n**Spec extraction:** every `--flag` name in the CLI contract spec.\n\n**Diff:** every flag must appear. Hidden flags should be documented as hidden.\n\n### Check 4: Subcommand Completeness\n\nApplies to CLIs or REPLs with a subcommand surface.\n\n**Source extraction:** target-dependent. For subcommand CLIs, grep for the subcommand registration or dispatch table (clap subcommands, Cobra, argparse subparsers). For REPL-style interfaces, grep for the command-prefix pattern (e.g., `\u002Fhelp`, `:quit`).\n\n**Spec extraction:** every subcommand from the CLI interface spec.\n\n**Diff:** every registered subcommand must appear.\n\n### Check 5: Event Dispatch Completeness\n\nApplies to targets that dispatch named events — common shapes include observer patterns, signals, message buses, and webhook emission.\n\n**Source extraction:** grep for event dispatch calls and event-type string constants. Common shapes: `emit(\"event-name\", ...)`, `dispatch(EventType.X)`, `pubsub.publish(\"...\", ...)`, signal\u002Fslot registrations, `raise EventName(...)`.\n\n**Spec extraction:** every event type documented in the extensibility or eventing spec.\n\n**Diff:** every dispatched event type must be documented.\n\n### Check 6: Config Key Completeness\n\n**Source extraction:** Search for settings property accesses and config key strings.\n\n**Spec extraction:** Extract all config keys from the configuration spec.\n\n**Diff:** User-configurable keys must appear. Internal state keys are P2.\n\n### Check 7: Error Category Completeness\n\n**Source extraction:** Search for error class definitions, error type enums, and error message constants.\n\n**Spec extraction:** Extract all documented error categories.\n\n**Diff:** User-visible errors must be documented.\n\n## Report Format\n\n```markdown\n# Source-to-Spec Completeness Report\n\n## Summary\n| Check | Source Count | Spec Count | Missing | Extra |\n|-------|-------------|------------|---------|-------|\n| Registered commands\u002Ftools | N | N | N | N |\n| Env Vars | N | N | N | N |\n| CLI Flags | N | N | N | N |\n| Subcommands | N | N | N | N |\n| Events dispatched | N | N | N | N |\n| Config Keys | N | N | N | N |\n| Error Categories | N | N | N | N |\n\n## P0-CRITICAL Gaps (must fix)\n[List all missing user-facing surfaces]\n\n## P1 Gaps (should fix)\n[List missing non-critical surfaces]\n\n## P2 Gaps (advisory)\n[List internal-only surfaces]\n\n## Verdict: PASS | FAIL\nPASS requires zero P0 gaps.\n```\n\n## Agent Dispatch Pattern\n\nDispatch as `moe-backstory:analyzer` since it needs to read both source code and specs. Can be parallelized:\n- One agent per check (7 agents), or\n- Batch checks 1-3 (commands\u002Ftools, env vars, CLI flags) and checks 4-7 (subcommands, events, config keys, errors) into 2 agents\n\n## Relationship to Other Validations\n\n```\nSource Code → [Layer 1-3 analysis] → Raw Specs → [Layer 5 sanitization] → Output Specs\n                                          ↑                                        ↑\n                                    source-completeness                     fidelity-validation\n                                    (source → raw)                      (raw → clean)\n                                          ↑                                        ↑\n                                    \"Did we capture it?\"                   \"Did we preserve it?\"\n```\n\nTogether these two validations form a complete chain: source-completeness ensures nothing was missed during analysis, and fidelity-validation ensures nothing was lost during sanitization.\n\n## Integration with Public Documentation\n\nWhen public documentation is available (docs mode was active), cross-reference the source findings against official docs:\n- Features documented in official docs but missing from specs → P0 gap\n- Features in source but not in official docs → likely internal, lower priority\n- Features in official docs but not in source → version mismatch or deprecated\n\nThis cross-reference is especially valuable because official documentation represents the **intended** user-facing surface, while source extraction finds the **actual** surface. Discrepancies in either direction are informative.\n",{"name":5,"description":7},"main","728894f3f85fbd4e788f015ddfd72bb6155d5dd5","plugins\u002Fmoe-backstory\u002F.opencode\u002Fskills\u002Fsource-completeness",1,"https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe","https:\u002F\u002Fgithub.com\u002Fzak-keown","2026-09-05 06:29:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zak-keown\u002Fmoe --skill source-completeness",{"tool":36,"command":37},"bunx","bunx skills add zak-keown\u002Fmoe --skill source-completeness",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zak-keown\u002Fmoe --skill source-completeness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe-backstory\u002F.opencode\u002Fskills\u002Fsource-completeness\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"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},"01M7C1Z5362Y8NVRZ69HWP0ZD0","write-skill","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-skill\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},"01M7C1YZ9966WK9R6ZRPCGWF3G","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-plan\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},"01M7C1YMR4SJD7BPBBPXZCVGVH","write-clearly","Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwrite-clearly\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7C1YH9805YSM0N20VQAVSXF","windows-vm","Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fwindows-vm\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7C1YD87SCNEJ2C9B8HFR2NQ","verify-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fverify-completion\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7C1YARDEHT0TJ9BRG30ZCF4","using-moe","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fzak-keown\u002Fmoe\u002Fblob\u002Fmain\u002Fplugins\u002Fmoe\u002Fskills\u002Fusing-moe\u002FSKILL.md",[],[]]