[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATB92JVD1FTTYPF4M5509D":3,"skill-same:01M7ATB92JVD1FTTYPF4M5509D":50},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7ATB92JVD1FTTYPF4M5509D","parallel-execution-optimizer",null,"Turn an urgent multi-part task into a lane matrix keyed on write-surface collisions, run the non-colliding lanes together, and finish with a verification table instead of a speed claim. Use when the user wants work done much faster through concurrent reads, batched checks, parallel subagents, or isolated worktrees, and correctness must not slip.","coltonbearden\u002Fawakened","coltonbearden","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F208834784?v=4","01M7ATATS86H87M6N7DGFWJXWA","Colton Bearden","01M7ATATSYZ652XPQKRKYQ3Q3P",0,"MIT","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fbankai\u002Fskills\u002Fparallel-execution-optimizer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: parallel-execution-optimizer\ndescription: Turn an urgent multi-part task into a lane matrix keyed on write-surface collisions, run the non-colliding lanes together, and finish with a verification table instead of a speed claim. Use when the user wants work done much faster through concurrent reads, batched checks, parallel subagents, or isolated worktrees, and correctness must not slip.\nallowed-tools: [Read, Grep, Glob, Agent]\n---\n\n# Parallel Execution Optimizer\n\n## Purpose\n\nSpeed comes from doing independent work at the same time; damage comes from doing colliding work at the same\ntime. This skill makes the difference explicit before anything runs: every lane of work is classified by what it\nwrites to, lanes whose write surfaces do not overlap run together, lanes that share a surface run in order, and\nthe report at the end shows what was verified rather than how fast it felt.\n\nThis skill schedules; it does not decide what the work is. Dispatch mechanics for independent investigations\nlive in `dispatching-parallel-agents`; per-task implementation loops live in `subagent-driven-development`.\n\n## Trigger Conditions\n\nUse this skill when a task fans out into repository scans, file reads, status checks, build or test lanes, and\nimplementation passes that could overlap, and the user has asked for speed. Use it before any large push that\ntouches more than one subsystem.\n\nDo not use it for a single sequential change, and never apply it to destructive commands, migrations, writes to\none table or file from two lanes, or customer-facing deploys; those get an explicit gate, not concurrency.\n\n## Workflow\n\n1. **Write the objective and the done signal** in one line each. A lane that cannot be tied to the done signal\n   is not a lane; drop it.\n2. **Split the work into lanes** and build the matrix below. Every row needs a write surface, even if that\n   surface is \"none\".\n3. **Classify each lane** as parallel (no shared write surface), sequential (shares a surface with another\n   lane), or gated (needs a human decision or evidence from another lane before it may start).\n4. **Run the read-only lanes together**: batch file reads, searches, status checks, and metadata queries into\n   the same response. Where a lane needs its own context, dispatch it as a session-scoped subagent through the\n   Agent tool (`bankai:codebase-explorer` for repository scans, `bankai:code-reviewer` for a review lane) and\n   issue the independent dispatches in one response; if no matching agent is available, run the lane inline.\n5. **Keep writes isolated** by file, directory, branch, worktree, service, or dataset. Two lanes that would\n   edit the same file are one lane.\n6. **Re-plan on blockers.** When a lane learns something that changes the plan, pause the lanes that depend on\n   it, amend the matrix, and only then continue.\n7. **Merge on evidence**, not on completion: a lane is compatible with another when its verification column is\n   filled in, not when it reports done.\n8. **Report** in the output contract below.\n\n## Lane Matrix\n\n| Lane | Parallel? | Write surface | Risk | Verification |\n|---|---|---|---|---|\n| Repository scan | yes | none | low | search and status output |\n| Backend patch | with frontend only | server source directory | medium | unit tests |\n| Frontend patch | with backend only | component directory | medium | rendered check |\n| Build and test | after both patches | build output | medium | exit status and log |\n| Deploy readback | gated on build | remote service | high | live check and logs |\n\nLanes may run together only when their write-surface cells do not overlap.\n\n## Boundaries on Time\n\nEvery lane finishes inside the turn that started it. No process this skill starts outlives the turn: no\ndetached jobs, no watchers, no polling loops left running for later. A long build or test lane is run\nin the foreground, bounded by a timeout, and its result read before the turn ends; if it cannot finish inside\nthe turn, it is reported as an incomplete lane rather than left running. A subagent dispatched through the Agent\ntool is session-scoped and ends with the session; that is the only concurrency this skill uses.\n\n## Output Contract\n\n1. **Lanes** — run, completed, and blocked, with the blocker named\n2. **Fast path** — which batching or parallelism actually saved time\n3. **Verification** — one line per lane: the check performed and its result; skipped checks are listed as\n   skipped, never folded into a success summary\n4. **Open items** — anything left incomplete when the turn ended\n\n## Failure Modes\n\n- Concurrency that produces conflicting edits because a write surface was left blank.\n- Benchmarking the tooling instead of finishing the task.\n- Calling the work done because it was fast, before the verification column is full.\n- Hiding a skipped check behind a green summary.\n","# Parallel Execution Optimizer\n\n## Purpose\n\nSpeed comes from doing independent work at the same time; damage comes from doing colliding work at the same\ntime. This skill makes the difference explicit before anything runs: every lane of work is classified by what it\nwrites to, lanes whose write surfaces do not overlap run together, lanes that share a surface run in order, and\nthe report at the end shows what was verified rather than how fast it felt.\n\nThis skill schedules; it does not decide what the work is. Dispatch mechanics for independent investigations\nlive in `dispatching-parallel-agents`; per-task implementation loops live in `subagent-driven-development`.\n\n## Trigger Conditions\n\nUse this skill when a task fans out into repository scans, file reads, status checks, build or test lanes, and\nimplementation passes that could overlap, and the user has asked for speed. Use it before any large push that\ntouches more than one subsystem.\n\nDo not use it for a single sequential change, and never apply it to destructive commands, migrations, writes to\none table or file from two lanes, or customer-facing deploys; those get an explicit gate, not concurrency.\n\n## Workflow\n\n1. **Write the objective and the done signal** in one line each. A lane that cannot be tied to the done signal\n   is not a lane; drop it.\n2. **Split the work into lanes** and build the matrix below. Every row needs a write surface, even if that\n   surface is \"none\".\n3. **Classify each lane** as parallel (no shared write surface), sequential (shares a surface with another\n   lane), or gated (needs a human decision or evidence from another lane before it may start).\n4. **Run the read-only lanes together**: batch file reads, searches, status checks, and metadata queries into\n   the same response. Where a lane needs its own context, dispatch it as a session-scoped subagent through the\n   Agent tool (`bankai:codebase-explorer` for repository scans, `bankai:code-reviewer` for a review lane) and\n   issue the independent dispatches in one response; if no matching agent is available, run the lane inline.\n5. **Keep writes isolated** by file, directory, branch, worktree, service, or dataset. Two lanes that would\n   edit the same file are one lane.\n6. **Re-plan on blockers.** When a lane learns something that changes the plan, pause the lanes that depend on\n   it, amend the matrix, and only then continue.\n7. **Merge on evidence**, not on completion: a lane is compatible with another when its verification column is\n   filled in, not when it reports done.\n8. **Report** in the output contract below.\n\n## Lane Matrix\n\n| Lane | Parallel? | Write surface | Risk | Verification |\n|---|---|---|---|---|\n| Repository scan | yes | none | low | search and status output |\n| Backend patch | with frontend only | server source directory | medium | unit tests |\n| Frontend patch | with backend only | component directory | medium | rendered check |\n| Build and test | after both patches | build output | medium | exit status and log |\n| Deploy readback | gated on build | remote service | high | live check and logs |\n\nLanes may run together only when their write-surface cells do not overlap.\n\n## Boundaries on Time\n\nEvery lane finishes inside the turn that started it. No process this skill starts outlives the turn: no\ndetached jobs, no watchers, no polling loops left running for later. A long build or test lane is run\nin the foreground, bounded by a timeout, and its result read before the turn ends; if it cannot finish inside\nthe turn, it is reported as an incomplete lane rather than left running. A subagent dispatched through the Agent\ntool is session-scoped and ends with the session; that is the only concurrency this skill uses.\n\n## Output Contract\n\n1. **Lanes** — run, completed, and blocked, with the blocker named\n2. **Fast path** — which batching or parallelism actually saved time\n3. **Verification** — one line per lane: the check performed and its result; skipped checks are listed as\n   skipped, never folded into a success summary\n4. **Open items** — anything left incomplete when the turn ended\n\n## Failure Modes\n\n- Concurrency that produces conflicting edits because a write surface was left blank.\n- Benchmarking the tooling instead of finishing the task.\n- Calling the work done because it was fast, before the verification column is full.\n- Hiding a skipped check behind a green summary.\n",{"name":5,"description":7,"allowed-tools":24},[25,26,27,28],"Read","Grep","Glob","Agent","main","b192e49d15e524b1a88cd89bc42ed677c1019c9f","plugins\u002Fbankai\u002Fskills\u002Fparallel-execution-optimizer","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened","https:\u002F\u002Fgithub.com\u002Fcoltonbearden","https:\u002F\u002Fcoltonbearden.com\u002F","2026-09-25 06:56:45",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add coltonbearden\u002Fawakened --skill parallel-execution-optimizer",{"tool":42,"command":43},"bunx","bunx skills add coltonbearden\u002Fawakened --skill parallel-execution-optimizer",{"tool":45,"command":46},"pnpm","pnpm dlx skills add coltonbearden\u002Fawakened --skill parallel-execution-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fbankai\u002Fskills\u002Fparallel-execution-optimizer\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7ATJM35P1TKP3CPE240A8KY","good-skill","Fixture - a skill whose name equals its directory and whose description clears the forty-character floor (N-2).","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7ATJJYPD2HBMA6H5KQ28YNM","wrong-name","Too short.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fbad-skill\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7ATJG19YSBW0PZCP9YN2S0K","\u003Cskill-name>","\u003CWhat the skill does, then the situations that should trigger it. Concrete and situational, third person, never marketing. Minimum 40 characters — this text is the auto-invocation surface (N-2).>","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Ftemplates\u002Fskill.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7ATJCEBSD2HYJAC4BE22AR1","writing-plans","Turns an agreed design or spec into a step-by-step implementation plan that an engineer with no context could execute. Use when a multi-step change is understood well enough to sequence but no plan exists yet, before touching code. Produces a plan file with exact paths, test-first steps, interfaces between tasks, and no placeholders.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7ATJ8AF6T9VWJH3NXY5QRS7","verification-before-completion","Gate that runs before any claim that work is done, fixed, passing, or shipped. Identifies the command that would prove the claim, runs it fresh, reads the whole output, and only then reports — with the evidence attached and any gap stated. Use before committing, opening a pull request, marking a task complete, or telling the user something works.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7ATJ2AAB7VS5AVNPT6E9YNQ","using-skills","Session discipline that fires before the first action of any task. Checks whether an installed skill or command already covers the job, keeps every action inside the requested scope, and reports verification as evidence rather than confidence. Use at the start of a conversation, before answering a question, before exploring a codebase, and whenever a task changes shape mid-session.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fusing-skills\u002FSKILL.md",[],[]]