[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7577TFFTF71W56X3KZ41KCF":3,"skill-same:01M7577TFFTF71W56X3KZ41KCF":152},{"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":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M7577TFFTF71W56X3KZ41KCF","deep-clean",null,"Deep structural cleanup and simplification: remove dead code, merge duplicate files, run a 4-lens sweep, and audit maintainability over a named path. Use for pre-merge or post-refactor work across Python, Rust, and TypeScript. Also triggered by \u002Fsimplify.","rakaarwaky\u002Fagents-arwaky","rakaarwaky","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F245127434?v=4","01M7574QFJB21S6PPNCK78WX68","Raka Arwaky","01M7574QG54PRT44Q4KMQFXY6B",0,"MIT","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: deep-clean\ndescription: \"Deep structural cleanup and simplification: remove dead code, merge duplicate files, run a 4-lens sweep, and audit maintainability over a named path. Use for pre-merge or post-refactor work across Python, Rust, and TypeScript. Also triggered by \u002Fsimplify.\"\nwhen-to-use: \"Use before merge, before release, or after refactoring a path, package, crate, or file. Remove dead code (ruff\u002Fvulture\u002Fknip\u002Fclippy\u002Fudeps), consolidate overlapping files into single cohesive modules, run a 4-reviewer sweep (reuse, quality, efficiency, altitude), and execute a strict maintainability audit. Answers 'is this codebase drifting toward spaghetti?' — run over a path, step by step, all aspects. Do not use for routine lint\u002Ftype-check runs (those are CI gates) or for style nits without a structural angle. `--dry-run` (explicit) reports without executing; without it the run is headless and autonomous — no permission prompts.\"\nargument-hint: \"\u003Cpath> [--dry-run]\"\nmetadata:\n  tags:\n    - python\n    - rust\n    - typescript\n    - cleanup\n    - consolidation\n    - bloat\n    - stubs\n    - thin-wrappers\n    - dead-code\n    - orphan\n    - unused-files\n    - merge\n    - deduplication\n    - code-review\n    - refactor\n    - delegation\n    - subagent\n    - parallel\n    - simplify\n    - spaghetti\n    - maintainability\n    - code-judo\n    - giant-files\n    - reuse\n    - efficiency\n    - altitude\n  related_skills:\n    - lint-arwaky\n    - systematic-debugging\n---\n\n# deep-clean\n\nRuns a 7-step pipeline over a named path: path audit capture → per-language dead-code cleanup → per-language file consolidation → 4-lens sweep → reviewer prompts + structural audit → apply per tier → verification gates → report. Language variants are picked per step (`1a`\u002F`1b`\u002F`1c`, `2a`\u002F`2b`\u002F`2c`) by the target language. This file is the lane identification step only; the working method lives in `references\u002Fhermes\u002F` and `references\u002Fgrok\u002F`.\n\n## Global Rules\n\nThe lane is determined from a physical signal, not by self-identification. Each agent's launcher stamps a fixed attribution env var into every command it runs; the model cannot set these.\n\n```bash\nif [[ -n \"${HERMES_AGENT:-}\" ]]; then echo HERMES\nelif [[ -n \"${GROK_AGENT:-}\" ]]; then echo GROK\nelse echo UNSET; fi\n```\n\n- `HERMES` → **Hermes lane.** Read `references\u002Fhermes\u002F`. Stop.\n- `GROK` → **Grok lane.** Read `references\u002Fgrok\u002F`. Stop.\n- `UNSET` → stop and report. Do not guess the lane.\n\nMarker provenance:\n\n- **Hermes** re-exports `AI_AGENT=hermes-agent` and `HERMES_AGENT=true` on every command.\n- **Grok Build** runs with `GROK_AGENT=1`.\n\nRead only the winning lane's references. Do not read the other lane's.\n\n## Pitfalls and Lessons\n\n- **Relocate, don't delete, shared templates consumed by linters.** When stripping an embedded feature, check whether any removed files are also read by other linters or tests (e.g. doc templates under the removed dir that feed AES601-AES610 doc-shape checks). Relocate them to a non-feature path and update every path reference in build scripts, tests, and dispatchers — deleting them breaks linters that still expect them.\n- **Feature-stripping cascades.** Removing an embedded feature breaks every caller of its modules, constants, traits, and CLI variants. Fix all callers, not just the obvious ones — `cargo build` and `cargo clippy -D warnings` will surface the rest. Don't declare done until the binary compiles and the full test suite passes.\n- **Grok Build can hit max turns on large refactors.** Verify progress in the worktree directory (`git status --short`, `git log --oneline -3`, `git diff \u003Cbase>..HEAD`), not the TUI stream — an empty stream doesn't mean idle. Send a focused follow-up brief listing only the remaining files, and drive rounds with a shrinking grep count of the feature's key symbols (constant names, fn names, CLI variants — not the generic word) until it hits 0. Never re-send the full original brief each round — the agent re-reads from scratch and burns the turn budget. The full recipe lives in the `grok-build` skill (\"Multi-round large refactor recipe\").\n- **When relocating a directory, search the whole tree for path strings, not just code.** Doc-comment prose, generated-file headers (build-script-emitted `\u002F\u002F Source: \u003Cpath>` lines), test helper path joins, and stale references to deleted files (e.g. a doc comment citing a SKILL.md removed in the same cleanup) all carry the old path and survive a code-only sweep. Grep the old path string across `*.rs`, `*.md`, and `*.sh` (excluding `target\u002F`) after moving files, and rewrite every hit — `cargo test` passes even with stale doc comments, so the gate will not catch them.\n- **lint-arwaky verification gates (Rust workspace):** `CARGO_INCREMENTAL=0 cargo fmt --all -- --check`, `CARGO_INCREMENTAL=0 cargo clippy --all-targets -- -D warnings`, `CARGO_INCREMENTAL=0 cargo build --bin lint-arwaky-cli`, `CARGO_INCREMENTAL=0 cargo nextest run --workspace --lib --tests -j 2`. Run all four before declaring a deep-clean done.\n\n## Routing\n\n### Hermes lane (Steps 0–3)\n\n| Step | Reference                                                                     | Purpose                                                                                                  |\n| ----: | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |\n| 0    | [`references\u002Fhermes\u002Fstep-0-plan-and-spawn.md`](references\u002Fhermes\u002Fstep-0-plan-and-spawn.md) | Detect language from `\u003Cpath>`; plan the brief (mode, acceptance criteria); create the Orca worktree with `--agent grok`; drop `\u002Fdeep-clean \u003Cpath>` |\n| 1    | [`references\u002Fhermes\u002Fstep-1-wait-grok.md`](references\u002Fhermes\u002Fstep-1-wait-grok.md) | Wait for Grok to finish the pipeline; read its step 7 report and commit                                |\n| 2    | [`references\u002Fhermes\u002Fstep-2-verify-and-ship.md`](references\u002Fhermes\u002Fstep-2-verify-and-ship.md) | Re-run the language's verification gates on the clean committed tree; surface bugs + RISKY items; push\u002FPR if asked |\n| 3    | [`references\u002Fhermes\u002Fstep-3-final-report.md`](references\u002Fhermes\u002Fstep-3-final-report.md) | Final report to the user (cleanup counts, bugs, RISKY items, commit\u002FPR, worktree teardown)             |\n\n### Grok lane (Steps 0–7, run by Grok Build)\n\n| Step | Reference | Purpose |\n| ---- | --------- | ------- |\n| Step 0: path audit capture | [`references\u002Fgrok\u002Fstep-0-scope.md`](references\u002Fgrok\u002Fstep-0-scope.md) | Path validation, audit scope, headless vs `--dry-run` mode gate. |\n| Step 1: dead code (language variants) | [`step-1a-dead-code-python.md`](references\u002Fgrok\u002Fstep-1a-dead-code-python.md), [`step-1b-dead-code-rust.md`](references\u002Fgrok\u002Fstep-1b-dead-code-rust.md), [`step-1c-dead-code-typescript.md`](references\u002Fgrok\u002Fstep-1c-dead-code-typescript.md) | Phase 1 per-language dead-code detection, workflow, exceptions. |\n| Step 2: consolidation (language variants) | [`step-2a-consolidate-python.md`](references\u002Fgrok\u002Fstep-2a-consolidate-python.md), [`step-2b-consolidate-rust.md`](references\u002Fgrok\u002Fstep-2b-consolidate-rust.md), [`step-2c-consolidate-typescript.md`](references\u002Fgrok\u002Fstep-2c-consolidate-typescript.md) | Phase 2 per-language consolidation workflow, verification, commit, checklists. |\n| Step 3: 4-lens sweep | [`references\u002Fgrok\u002Fstep-3-lens-sweep.md`](references\u002Fgrok\u002Fstep-3-lens-sweep.md) | Execution model, the four lenses, evidence standard, finding format, sweep pitfalls. |\n| Step 4: reviewer prompts | [`references\u002Fgrok\u002Fstep-4-reviewer-prompts.md`](references\u002Fgrok\u002Fstep-4-reviewer-prompts.md) | Full prompt text for each of the four reviewer lenses. |\n| Step 4: audit standards | [`references\u002Fgrok\u002Fstep-4-audit-standards.md`](references\u002Fgrok\u002Fstep-4-audit-standards.md) | Non-negotiable audit standards, primary audit questions, what to flag aggressively, preferred remedies, approval bar; tone and output prioritization live in [`references\u002Fgrok\u002Fstep-4-review-tone.md`](references\u002Fgrok\u002Fstep-4-review-tone.md). |\n| Step 5: apply per tier | [`references\u002Fgrok\u002Fstep-5-apply-per-tier.md`](references\u002Fgrok\u002Fstep-5-apply-per-tier.md) | Strict tier order, per-file test gates, dry-run presentation, house-style folding. |\n| Step 6: verification gates | [`references\u002Fgrok\u002Fstep-6-verification-gates.md`](references\u002Fgrok\u002Fstep-6-verification-gates.md) | Gate order, per-language exact commands, verification checklist, common mistakes, bugs-found section rules. |\n| Step 7: report | [`references\u002Fgrok\u002Fstep-7-report-format.md`](references\u002Fgrok\u002Fstep-7-report-format.md) | Final report section shape and worked example. |\n","# deep-clean\n\nRuns a 7-step pipeline over a named path: path audit capture → per-language dead-code cleanup → per-language file consolidation → 4-lens sweep → reviewer prompts + structural audit → apply per tier → verification gates → report. Language variants are picked per step (`1a`\u002F`1b`\u002F`1c`, `2a`\u002F`2b`\u002F`2c`) by the target language. This file is the lane identification step only; the working method lives in `references\u002Fhermes\u002F` and `references\u002Fgrok\u002F`.\n\n## Global Rules\n\nThe lane is determined from a physical signal, not by self-identification. Each agent's launcher stamps a fixed attribution env var into every command it runs; the model cannot set these.\n\n```bash\nif [[ -n \"${HERMES_AGENT:-}\" ]]; then echo HERMES\nelif [[ -n \"${GROK_AGENT:-}\" ]]; then echo GROK\nelse echo UNSET; fi\n```\n\n- `HERMES` → **Hermes lane.** Read `references\u002Fhermes\u002F`. Stop.\n- `GROK` → **Grok lane.** Read `references\u002Fgrok\u002F`. Stop.\n- `UNSET` → stop and report. Do not guess the lane.\n\nMarker provenance:\n\n- **Hermes** re-exports `AI_AGENT=hermes-agent` and `HERMES_AGENT=true` on every command.\n- **Grok Build** runs with `GROK_AGENT=1`.\n\nRead only the winning lane's references. Do not read the other lane's.\n\n## Pitfalls and Lessons\n\n- **Relocate, don't delete, shared templates consumed by linters.** When stripping an embedded feature, check whether any removed files are also read by other linters or tests (e.g. doc templates under the removed dir that feed AES601-AES610 doc-shape checks). Relocate them to a non-feature path and update every path reference in build scripts, tests, and dispatchers — deleting them breaks linters that still expect them.\n- **Feature-stripping cascades.** Removing an embedded feature breaks every caller of its modules, constants, traits, and CLI variants. Fix all callers, not just the obvious ones — `cargo build` and `cargo clippy -D warnings` will surface the rest. Don't declare done until the binary compiles and the full test suite passes.\n- **Grok Build can hit max turns on large refactors.** Verify progress in the worktree directory (`git status --short`, `git log --oneline -3`, `git diff \u003Cbase>..HEAD`), not the TUI stream — an empty stream doesn't mean idle. Send a focused follow-up brief listing only the remaining files, and drive rounds with a shrinking grep count of the feature's key symbols (constant names, fn names, CLI variants — not the generic word) until it hits 0. Never re-send the full original brief each round — the agent re-reads from scratch and burns the turn budget. The full recipe lives in the `grok-build` skill (\"Multi-round large refactor recipe\").\n- **When relocating a directory, search the whole tree for path strings, not just code.** Doc-comment prose, generated-file headers (build-script-emitted `\u002F\u002F Source: \u003Cpath>` lines), test helper path joins, and stale references to deleted files (e.g. a doc comment citing a SKILL.md removed in the same cleanup) all carry the old path and survive a code-only sweep. Grep the old path string across `*.rs`, `*.md`, and `*.sh` (excluding `target\u002F`) after moving files, and rewrite every hit — `cargo test` passes even with stale doc comments, so the gate will not catch them.\n- **lint-arwaky verification gates (Rust workspace):** `CARGO_INCREMENTAL=0 cargo fmt --all -- --check`, `CARGO_INCREMENTAL=0 cargo clippy --all-targets -- -D warnings`, `CARGO_INCREMENTAL=0 cargo build --bin lint-arwaky-cli`, `CARGO_INCREMENTAL=0 cargo nextest run --workspace --lib --tests -j 2`. Run all four before declaring a deep-clean done.\n\n## Routing\n\n### Hermes lane (Steps 0–3)\n\n| Step | Reference                                                                     | Purpose                                                                                                  |\n| ----: | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |\n| 0    | [`references\u002Fhermes\u002Fstep-0-plan-and-spawn.md`](references\u002Fhermes\u002Fstep-0-plan-and-spawn.md) | Detect language from `\u003Cpath>`; plan the brief (mode, acceptance criteria); create the Orca worktree with `--agent grok`; drop `\u002Fdeep-clean \u003Cpath>` |\n| 1    | [`references\u002Fhermes\u002Fstep-1-wait-grok.md`](references\u002Fhermes\u002Fstep-1-wait-grok.md) | Wait for Grok to finish the pipeline; read its step 7 report and commit                                |\n| 2    | [`references\u002Fhermes\u002Fstep-2-verify-and-ship.md`](references\u002Fhermes\u002Fstep-2-verify-and-ship.md) | Re-run the language's verification gates on the clean committed tree; surface bugs + RISKY items; push\u002FPR if asked |\n| 3    | [`references\u002Fhermes\u002Fstep-3-final-report.md`](references\u002Fhermes\u002Fstep-3-final-report.md) | Final report to the user (cleanup counts, bugs, RISKY items, commit\u002FPR, worktree teardown)             |\n\n### Grok lane (Steps 0–7, run by Grok Build)\n\n| Step | Reference | Purpose |\n| ---- | --------- | ------- |\n| Step 0: path audit capture | [`references\u002Fgrok\u002Fstep-0-scope.md`](references\u002Fgrok\u002Fstep-0-scope.md) | Path validation, audit scope, headless vs `--dry-run` mode gate. |\n| Step 1: dead code (language variants) | [`step-1a-dead-code-python.md`](references\u002Fgrok\u002Fstep-1a-dead-code-python.md), [`step-1b-dead-code-rust.md`](references\u002Fgrok\u002Fstep-1b-dead-code-rust.md), [`step-1c-dead-code-typescript.md`](references\u002Fgrok\u002Fstep-1c-dead-code-typescript.md) | Phase 1 per-language dead-code detection, workflow, exceptions. |\n| Step 2: consolidation (language variants) | [`step-2a-consolidate-python.md`](references\u002Fgrok\u002Fstep-2a-consolidate-python.md), [`step-2b-consolidate-rust.md`](references\u002Fgrok\u002Fstep-2b-consolidate-rust.md), [`step-2c-consolidate-typescript.md`](references\u002Fgrok\u002Fstep-2c-consolidate-typescript.md) | Phase 2 per-language consolidation workflow, verification, commit, checklists. |\n| Step 3: 4-lens sweep | [`references\u002Fgrok\u002Fstep-3-lens-sweep.md`](references\u002Fgrok\u002Fstep-3-lens-sweep.md) | Execution model, the four lenses, evidence standard, finding format, sweep pitfalls. |\n| Step 4: reviewer prompts | [`references\u002Fgrok\u002Fstep-4-reviewer-prompts.md`](references\u002Fgrok\u002Fstep-4-reviewer-prompts.md) | Full prompt text for each of the four reviewer lenses. |\n| Step 4: audit standards | [`references\u002Fgrok\u002Fstep-4-audit-standards.md`](references\u002Fgrok\u002Fstep-4-audit-standards.md) | Non-negotiable audit standards, primary audit questions, what to flag aggressively, preferred remedies, approval bar; tone and output prioritization live in [`references\u002Fgrok\u002Fstep-4-review-tone.md`](references\u002Fgrok\u002Fstep-4-review-tone.md). |\n| Step 5: apply per tier | [`references\u002Fgrok\u002Fstep-5-apply-per-tier.md`](references\u002Fgrok\u002Fstep-5-apply-per-tier.md) | Strict tier order, per-file test gates, dry-run presentation, house-style folding. |\n| Step 6: verification gates | [`references\u002Fgrok\u002Fstep-6-verification-gates.md`](references\u002Fgrok\u002Fstep-6-verification-gates.md) | Gate order, per-language exact commands, verification checklist, common mistakes, bugs-found section rules. |\n| Step 7: report | [`references\u002Fgrok\u002Fstep-7-report-format.md`](references\u002Fgrok\u002Fstep-7-report-format.md) | Final report section shape and worked example. |\n",{"name":5,"metadata":24,"description":7,"when-to-use":55,"argument-hint":56},{"tags":25,"related_skills":52},[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"python","rust","typescript","cleanup","consolidation","bloat","stubs","thin-wrappers","dead-code","orphan","unused-files","merge","deduplication","code-review","refactor","delegation","subagent","parallel","simplify","spaghetti","maintainability","code-judo","giant-files","reuse","efficiency","altitude",[53,54],"lint-arwaky","systematic-debugging","Use before merge, before release, or after refactoring a path, package, crate, or file. Remove dead code (ruff\u002Fvulture\u002Fknip\u002Fclippy\u002Fudeps), consolidate overlapping files into single cohesive modules, run a 4-reviewer sweep (reuse, quality, efficiency, altitude), and execute a strict maintainability audit. Answers 'is this codebase drifting toward spaghetti?' — run over a path, step by step, all aspects. Do not use for routine lint\u002Ftype-check runs (those are CI gates) or for style nits without a structural angle. `--dry-run` (explicit) reports without executing; without it the run is headless and autonomous — no permission prompts.","\u003Cpath> [--dry-run]","main","e0708985ab2d620bc6e8fe741eaa4ec1960269e3","skills\u002Fcode-quality\u002Fdeep-clean","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky","https:\u002F\u002Fgithub.com\u002Frakaarwaky","https:\u002F\u002Fbuymeacoffee.com\u002Frakaarwaky","2026-11-15 04:28:37",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add rakaarwaky\u002Fagents-arwaky --skill deep-clean",{"tool":70,"command":71},"bunx","bunx skills add rakaarwaky\u002Fagents-arwaky --skill deep-clean",{"tool":73,"command":74},"pnpm","pnpm dlx skills add rakaarwaky\u002Fagents-arwaky --skill deep-clean","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002FSKILL.md",true,[78,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fgrok\u002Fstep-0-scope.md","REFERENCE","参考文档",1838,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-0-scope.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fgrok\u002Fstep-1a-dead-code-python.md",21903,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-1a-dead-code-python.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fgrok\u002Fstep-1b-dead-code-rust.md",16350,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-1b-dead-code-rust.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fgrok\u002Fstep-1c-dead-code-typescript.md",33613,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-1c-dead-code-typescript.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fgrok\u002Fstep-2a-consolidate-python.md",15152,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-2a-consolidate-python.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fgrok\u002Fstep-2b-consolidate-rust.md",14313,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-2b-consolidate-rust.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fgrok\u002Fstep-2c-consolidate-typescript.md",20248,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-2c-consolidate-typescript.md",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fgrok\u002Fstep-3-lens-sweep.md",4490,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-3-lens-sweep.md",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fgrok\u002Fstep-4-audit-standards.md",7727,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-4-audit-standards.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fgrok\u002Fstep-4-review-tone.md",1844,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-4-review-tone.md",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fgrok\u002Fstep-4-reviewer-prompts.md",3905,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-4-reviewer-prompts.md",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fgrok\u002Fstep-5-apply-per-tier.md",2624,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-5-apply-per-tier.md",{"path":129,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fgrok\u002Fstep-6-verification-gates.md",1926,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-6-verification-gates.md",{"path":133,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fgrok\u002Fstep-7-report-format.md",1288,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fgrok\u002Fstep-7-report-format.md",{"path":137,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fhermes\u002Fstep-0-plan-and-spawn.md",2970,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fhermes\u002Fstep-0-plan-and-spawn.md",{"path":141,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Fhermes\u002Fstep-1-wait-grok.md",1530,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fhermes\u002Fstep-1-wait-grok.md",{"path":145,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fhermes\u002Fstep-2-verify-and-ship.md",2136,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fhermes\u002Fstep-2-verify-and-ship.md",{"path":149,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":150,"sourceHtmlUrl":151},"references\u002Fhermes\u002Fstep-3-final-report.md",722,"https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fcode-quality\u002Fdeep-clean\u002Freferences\u002Fhermes\u002Fstep-3-final-report.md",[153,161,168,175,182,189],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":160},"01M78SFXSH86CW16Z5FEXMSJXH","github-workflow","Umbrella for GitHub auth, repo management, issues, PRs, Mergify, and releases. Subsumes github-auth and repo-manager.","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fgit\u002Fgithub-workflow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":160},"01M78SF81R7NVSCXAT8YQ255HM","brave-automation","baa CLI: Brave profiles, Google sessions, credentials.","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fbrave-automation\u002Fbrave-automation\u002FSKILL.md",[],[],{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":160},"01M78SEY7TS908JM8KVPBM6HBN","aes","AES docs, layers, rule fixes, and legacy migration.","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Farchitechture\u002Faes\u002FSKILL.md",[],[],{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":19},"01M757HBGFCMTJTQB45JQFXCC0","pretext","Build creative browser demos with DOM-free text layout.","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design\u002Fpretext\u002FSKILL.md",[],[],{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":19},"01M757H8K38ETN8F4ANBBRWY4G","popular-web-designs","54 real design systems (Stripe, Linear, Vercel) as HTML\u002FCSS.","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design\u002Fpopular-web-designs\u002FSKILL.md",[],[],{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":19},"01M757H5DM7QPN9H391572NH5B","p5js","p5.js sketches: gen art, shaders, interactive, 3D.","https:\u002F\u002Fgithub.com\u002Frakaarwaky\u002Fagents-arwaky\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design\u002Fp5js\u002FSKILL.md",[],[]]