[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FS55R73GPY70D626WB71N":3,"skill-same:01M71FS55R73GPY70D626WB71N":90},{"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":46,"commitSha":47,"skillDirectory":48,"forksCount":14,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M71FS55R73GPY70D626WB71N","control-token-spend",null,"ALWAYS invoke this skill when measuring coding-session token consumption, explaining context and cache costs, detecting spending bursts, or managing local usage-report schedules.","outcomeeng\u002Fplugins","outcomeeng","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257335685?v=4","01M71FRVRF36XYR3HRSCGFHK2R","Outcome Engineering","01M71FRVS4BZG17DWANFJ7EPNY",1,"MIT","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"control token spend","token","control","options","detect","cache","Bash","ask","version","when","invoke","schedules","local","tool","session","collect","detecting","python3","usage","spending","2026-11-10 10:12:30",false,"---\nname: control-token-spend\ndescription: >-\n ALWAYS invoke this skill when measuring coding-session token consumption,\n explaining context and cache costs, detecting spending bursts, or managing\n local usage-report schedules.\nargument-hint: \"[report|collect|detect|hourly|install|status|stop|restart] [options]\"\nallowed-tools: Read, Bash(python3 --version), Bash(python3 -B \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fusage_control.py\":*), {{! tool('ask_user') !}}\n---\n\n\u003Cobjective>\n\nDurable local consumption evidence and advisory budget signals from bounded,\ndeterministic transcript processing, with inspectable scheduled-worker state.\n\n\u003C\u002Fobjective>\n\n\u003Cdependencies>\n\n- Python 3.13 or 3.14; standard library only. Check the interpreter before running.\n- Readable Claude Code transcripts; the default source is `~\u002F.claude\u002Fprojects`.\n- macOS launchd for managed scheduling. Other platforms return unsupported.\n- Optional investigation supports `aise 1.0.0-rc.4` with an explicitly selected\n existing database. Accounting works without it. Never install dependencies,\n start TraceRoost, rebuild an index, or invoke a model for these operations.\n\n\u003C\u002Fdependencies>\n\n\u003Ctesting>\n\nRelease verification uses captured native assistant and tool-result records,\ngenerated streaming usage and monetary boundaries, real SQLite partial-row and\ntimestamp-boundary imports, linked report formats, durable alert deduplication,\nretention and overlap checks. Copied assets run with site packages disabled and\nan empty executable search path. Recording command collaborators exercise managed\njob restart and permission failure without changing shared launch agents.\n\n\u003C\u002Ftesting>\n\n\u003Cinput_output>\n\nRead `$ARGUMENTS` as the requested operation and its options. Empty arguments\nselect `report`, covering the preceding hour. Translate natural-language intent\ninto individual CLI arguments; quote each value and never evaluate supplied text\nas shell syntax. Use `--help` for the bundled command's exact option grammar.\n\nPass each configuration value as its option on the granted command, for example\n`python3 -B \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fusage_control.py\" report --reset-at 2026-10-09T00:00:00Z`.\nAn option overrides the matching `SPX_USAGE_*` environment variable — `SPX_USAGE_RESET_AT`,\n`SPX_USAGE_ALERT_USD`, `SPX_USAGE_WEEKLY_BUDGET_USD`, `SPX_USAGE_PRICE_FILE`, `SPX_USAGE_LAUNCHD_NAMESPACE` — and the\nsaved installation configuration.\n\n| Input | Contract |\n| --------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `--reset-at` | Required explicit UTC timestamp anchoring seven-day periods; reuse saved installation configuration when available. Ask for an absent anchor. |\n| `--alert-usd` | Positive estimated API-equivalent threshold for the rolling fifteen-minute detector; default 20. |\n| `--weekly-budget-usd` | Optional positive weekly API-equivalent target; no default. Its absence disables weekly budget and pace signals. |\n| `--price-file` | Optional path to a JSON price-override file whose `prices` object keys a model identifier to its five rates in USD per million tokens. |\n| `--launchd-namespace` | Optional launchd label namespace of the managed jobs, saved with the installation; one or more dot-separated segments of ASCII letters, digits, hyphens and underscores, none empty; default `engineering.outcome.usage-control`. `status`, `stop` and `restart` act only on jobs under the namespace the installation record names; a reinstall under another namespace records the new namespace, replaces only that namespace's jobs and leaves the four most recent earlier namespaces; older ones are stopped and their launch-agent files removed, the plan names those files in `retention_removals`, and a changed launch agent is left in place and reported as a retention gap. |\n| `--root` | Stable operator-owned state root; default `~\u002FLibrary\u002FApplication Support\u002FOutcome Engineering\u002Fusage-control`. |\n| `--projects` | Read-only transcript root, disjoint from the state root. |\n| `--start`, `--end` | Inclusive start and exclusive end, timezone-aware ISO timestamps. Freeze these when comparing reports. |\n| `--aise`, `--aise-database` | Both required when optional investigation is selected; an absent or incompatible tool records a gap. |\n\nThe runtime persists incremental offsets, reconciled requests and bounded evidence\nin SQLite. A report directory contains `report.html`, `measurements.json`,\n`sessions.csv`, and linked `evidence.html` excerpts with original-source references.\n`latest-report.json` identifies the latest report. Detector evidence lives under\n`alerts\u002F`; `worker-status.json` and `retention-status.json` expose operational state.\n\n\u003C\u002Finput_output>\n\n\u003Cavailable_scripts>\n\nRun `python3 -B \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fusage_control.py\"` with the selected\noperation and validated options. Its sibling `usage_accounting.py`,\n`usage_reports.py`, and `usage_schedule.py` supply accounting, rendering and\nscheduling; invoke the entrypoint rather than the sibling modules.\n\n| Operation | Observable result |\n| ----------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| `collect` | One bounded import page and explicit coverage gaps. |\n| `report` | Frozen HTML, JSON and CSV evidence, with an equally sized previous interval. |\n| `detect` | Rolling fifteen-minute and configured weekly advisory signals, with durable identities. |\n| `hourly` | Report for the preceding completed UTC hour. |\n| `install` | Reviewable plan; `--activate` explicitly writes stable assets and activates quarter-hour detection and hourly reporting. |\n| `status` | Actual managed-job observations and the last worker result. |\n| `stop`, `restart` | Managed-job operations with checked outcomes; restart reuses durable state. |\n\n\u003C\u002Favailable_scripts>\n\n\u003Cworkflow>\n\n\u003Cstep name=\"validate\">\n\nResolve the operation, state root, source root, reset anchor and any supplied budget\nfrom the request or saved configuration. Ask only for choices that remain missing.\nBefore an invocation writes to a state root the request does not name, present that\nabsolute state root through {{! tool('ask_user') !}} and run only after the operator\nconfirms it; an empty-argument report follows the same rule.\nReject unsupported interpreter versions before execution. Keep invalid amounts,\ntimestamp order and incomplete investigation options outside the mutation path.\n\n\u003C\u002Fstep>\n\n\u003Cstep name=\"execute\">\n\nRun one finite invocation of the bundled entrypoint. Collection reads at most\n32 MiB across 128 files per invocation, with bounded directory discovery and a\n120-second worker deadline. Incomplete coverage resumes through saved offsets;\nreport that limitation and avoid an unattended whole-history loop. A busy worker\nreturns `overlap_skipped` immediately.\n\nFor scheduling, first obtain the `install` plan and inspect its exact asset root,\ninterpreter, job paths, source and effective configuration, and the absolute path of\nevery launch agent in `retention_removals`, which activation stops and deletes. Present\nthose paths through {{! tool('ask_user') !}} and activate only when the operator has\nauthorized scheduling at the job paths and the removal of those launch agents.\nConfirm with `status`.\nPreserve unrelated launch agents and original transcripts.\n\n\u003C\u002Fstep>\n\n\u003Cstep name=\"interpret\">\n\nRead the generated measurement and selected linked excerpts. Reconcile all four\nusage fields, request and native child shares, pricing gaps, context growth and\ncache creation before drawing conclusions. Large tool results and repeated\narguments establish inspection candidates; they establish no waste or exact\ntool-cost attribution on their own.\n\nTreat API-equivalent cost as a priced estimate. The bundled `model-prices.json`\nprices each model; a listed model in the price-override file replaces its price.\nKeep subscription-allowance\nobservations separate. Compare equally covered windows and qualify late imports,\nunknown pricing and missing evidence. Attribute verified delivered output only\nfrom Applied store state, default-branch merge evidence, or current passing pinned\nverification. Preserve required gates and resource ceilings in every recommendation.\n\n\u003C\u002Fstep>\n\n\u003Cstep name=\"return_evidence\">\n\nReturn the exact UTC interval, coverage, principal measured drivers and clickable\nartifact paths. State the actual installation and worker status when scheduling\nwas requested. Agent-driven feedback, automatic mail delivery and model-routing\nchanges require their own authorized workflow.\n\n\u003C\u002Fstep>\n\n\u003C\u002Fworkflow>\n\n\u003Cerror_handling>\n\n| Observation | Action |\n| ------------------------------------------- | ---------------------------------------------------------------------------------------------------- |\n| Invalid configuration | Name the rejected field and correct it before execution. |\n| Partial import | Report measured totals as partial and preserve offsets for the next finite invocation. |\n| Unknown model or cache duration | Preserve token counts; report unavailable pricing or the documented lower-bound assumption. |\n| Optional investigation failure | Preserve deterministic accounting and name the missing investigation evidence. |\n| Changed or unowned installed assets or jobs | Preserve them, report the exact path, and reconcile ownership before replacement. |\n| Worker or launchd failure | Inspect the saved diagnostics and actual job observations; use `restart` after correcting the cause. |\n\nThe runtime owns atomic-write temporary files and retention of recognized artifacts.\nRun no shell deletion command. A nonzero exit or unknown job state supplies no\nsuccessful-installation claim.\n\n\u003C\u002Ferror_handling>\n\n\u003Csuccess_criteria>\n\n- The selected operation returns an inspectable result with exact bounds and gaps.\n- Reports reconcile their shared frozen measurement and link bounded transcript evidence.\n- Signals retain effective configuration and never predict subscription percentages.\n- Requested scheduling is verified through actual job observations; failures remain visible.\n- Original transcripts, unrelated jobs, required gates and resource ceilings remain preserved.\n\n\u003C\u002Fsuccess_criteria>\n","\u003Cobjective>\n\nDurable local consumption evidence and advisory budget signals from bounded,\ndeterministic transcript processing, with inspectable scheduled-worker state.\n\n\u003C\u002Fobjective>\n\n\u003Cdependencies>\n\n- Python 3.13 or 3.14; standard library only. Check the interpreter before running.\n- Readable Claude Code transcripts; the default source is `~\u002F.claude\u002Fprojects`.\n- macOS launchd for managed scheduling. Other platforms return unsupported.\n- Optional investigation supports `aise 1.0.0-rc.4` with an explicitly selected\n existing database. Accounting works without it. Never install dependencies,\n start TraceRoost, rebuild an index, or invoke a model for these operations.\n\n\u003C\u002Fdependencies>\n\n\u003Ctesting>\n\nRelease verification uses captured native assistant and tool-result records,\ngenerated streaming usage and monetary boundaries, real SQLite partial-row and\ntimestamp-boundary imports, linked report formats, durable alert deduplication,\nretention and overlap checks. Copied assets run with site packages disabled and\nan empty executable search path. Recording command collaborators exercise managed\njob restart and permission failure without changing shared launch agents.\n\n\u003C\u002Ftesting>\n\n\u003Cinput_output>\n\nRead `$ARGUMENTS` as the requested operation and its options. Empty arguments\nselect `report`, covering the preceding hour. Translate natural-language intent\ninto individual CLI arguments; quote each value and never evaluate supplied text\nas shell syntax. Use `--help` for the bundled command's exact option grammar.\n\nPass each configuration value as its option on the granted command, for example\n`python3 -B \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fusage_control.py\" report --reset-at 2026-10-09T00:00:00Z`.\nAn option overrides the matching `SPX_USAGE_*` environment variable — `SPX_USAGE_RESET_AT`,\n`SPX_USAGE_ALERT_USD`, `SPX_USAGE_WEEKLY_BUDGET_USD`, `SPX_USAGE_PRICE_FILE`, `SPX_USAGE_LAUNCHD_NAMESPACE` — and the\nsaved installation configuration.\n\n| Input | Contract |\n| --------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `--reset-at` | Required explicit UTC timestamp anchoring seven-day periods; reuse saved installation configuration when available. Ask for an absent anchor. |\n| `--alert-usd` | Positive estimated API-equivalent threshold for the rolling fifteen-minute detector; default 20. |\n| `--weekly-budget-usd` | Optional positive weekly API-equivalent target; no default. Its absence disables weekly budget and pace signals. |\n| `--price-file` | Optional path to a JSON price-override file whose `prices` object keys a model identifier to its five rates in USD per million tokens. |\n| `--launchd-namespace` | Optional launchd label namespace of the managed jobs, saved with the installation; one or more dot-separated segments of ASCII letters, digits, hyphens and underscores, none empty; default `engineering.outcome.usage-control`. `status`, `stop` and `restart` act only on jobs under the namespace the installation record names; a reinstall under another namespace records the new namespace, replaces only that namespace's jobs and leaves the four most recent earlier namespaces; older ones are stopped and their launch-agent files removed, the plan names those files in `retention_removals`, and a changed launch agent is left in place and reported as a retention gap. |\n| `--root` | Stable operator-owned state root; default `~\u002FLibrary\u002FApplication Support\u002FOutcome Engineering\u002Fusage-control`. |\n| `--projects` | Read-only transcript root, disjoint from the state root. |\n| `--start`, `--end` | Inclusive start and exclusive end, timezone-aware ISO timestamps. Freeze these when comparing reports. |\n| `--aise`, `--aise-database` | Both required when optional investigation is selected; an absent or incompatible tool records a gap. |\n\nThe runtime persists incremental offsets, reconciled requests and bounded evidence\nin SQLite. A report directory contains `report.html`, `measurements.json`,\n`sessions.csv`, and linked `evidence.html` excerpts with original-source references.\n`latest-report.json` identifies the latest report. Detector evidence lives under\n`alerts\u002F`; `worker-status.json` and `retention-status.json` expose operational state.\n\n\u003C\u002Finput_output>\n\n\u003Cavailable_scripts>\n\nRun `python3 -B \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fusage_control.py\"` with the selected\noperation and validated options. Its sibling `usage_accounting.py`,\n`usage_reports.py`, and `usage_schedule.py` supply accounting, rendering and\nscheduling; invoke the entrypoint rather than the sibling modules.\n\n| Operation | Observable result |\n| ----------------- | ------------------------------------------------------------------------------------------------------------------------ |\n| `collect` | One bounded import page and explicit coverage gaps. |\n| `report` | Frozen HTML, JSON and CSV evidence, with an equally sized previous interval. |\n| `detect` | Rolling fifteen-minute and configured weekly advisory signals, with durable identities. |\n| `hourly` | Report for the preceding completed UTC hour. |\n| `install` | Reviewable plan; `--activate` explicitly writes stable assets and activates quarter-hour detection and hourly reporting. |\n| `status` | Actual managed-job observations and the last worker result. |\n| `stop`, `restart` | Managed-job operations with checked outcomes; restart reuses durable state. |\n\n\u003C\u002Favailable_scripts>\n\n\u003Cworkflow>\n\n\u003Cstep name=\"validate\">\n\nResolve the operation, state root, source root, reset anchor and any supplied budget\nfrom the request or saved configuration. Ask only for choices that remain missing.\nBefore an invocation writes to a state root the request does not name, present that\nabsolute state root through {{! tool('ask_user') !}} and run only after the operator\nconfirms it; an empty-argument report follows the same rule.\nReject unsupported interpreter versions before execution. Keep invalid amounts,\ntimestamp order and incomplete investigation options outside the mutation path.\n\n\u003C\u002Fstep>\n\n\u003Cstep name=\"execute\">\n\nRun one finite invocation of the bundled entrypoint. Collection reads at most\n32 MiB across 128 files per invocation, with bounded directory discovery and a\n120-second worker deadline. Incomplete coverage resumes through saved offsets;\nreport that limitation and avoid an unattended whole-history loop. A busy worker\nreturns `overlap_skipped` immediately.\n\nFor scheduling, first obtain the `install` plan and inspect its exact asset root,\ninterpreter, job paths, source and effective configuration, and the absolute path of\nevery launch agent in `retention_removals`, which activation stops and deletes. Present\nthose paths through {{! tool('ask_user') !}} and activate only when the operator has\nauthorized scheduling at the job paths and the removal of those launch agents.\nConfirm with `status`.\nPreserve unrelated launch agents and original transcripts.\n\n\u003C\u002Fstep>\n\n\u003Cstep name=\"interpret\">\n\nRead the generated measurement and selected linked excerpts. Reconcile all four\nusage fields, request and native child shares, pricing gaps, context growth and\ncache creation before drawing conclusions. Large tool results and repeated\narguments establish inspection candidates; they establish no waste or exact\ntool-cost attribution on their own.\n\nTreat API-equivalent cost as a priced estimate. The bundled `model-prices.json`\nprices each model; a listed model in the price-override file replaces its price.\nKeep subscription-allowance\nobservations separate. Compare equally covered windows and qualify late imports,\nunknown pricing and missing evidence. Attribute verified delivered output only\nfrom Applied store state, default-branch merge evidence, or current passing pinned\nverification. Preserve required gates and resource ceilings in every recommendation.\n\n\u003C\u002Fstep>\n\n\u003Cstep name=\"return_evidence\">\n\nReturn the exact UTC interval, coverage, principal measured drivers and clickable\nartifact paths. State the actual installation and worker status when scheduling\nwas requested. Agent-driven feedback, automatic mail delivery and model-routing\nchanges require their own authorized workflow.\n\n\u003C\u002Fstep>\n\n\u003C\u002Fworkflow>\n\n\u003Cerror_handling>\n\n| Observation | Action |\n| ------------------------------------------- | ---------------------------------------------------------------------------------------------------- |\n| Invalid configuration | Name the rejected field and correct it before execution. |\n| Partial import | Report measured totals as partial and preserve offsets for the next finite invocation. |\n| Unknown model or cache duration | Preserve token counts; report unavailable pricing or the documented lower-bound assumption. |\n| Optional investigation failure | Preserve deterministic accounting and name the missing investigation evidence. |\n| Changed or unowned installed assets or jobs | Preserve them, report the exact path, and reconcile ownership before replacement. |\n| Worker or launchd failure | Inspect the saved diagnostics and actual job observations; use `restart` after correcting the cause. |\n\nThe runtime owns atomic-write temporary files and retention of recognized artifacts.\nRun no shell deletion command. A nonzero exit or unknown job state supplies no\nsuccessful-installation claim.\n\n\u003C\u002Ferror_handling>\n\n\u003Csuccess_criteria>\n\n- The selected operation returns an inspectable result with exact bounds and gaps.\n- Reports reconcile their shared frozen measurement and link bounded transcript evidence.\n- Signals retain effective configuration and never predict subscription percentages.\n- Requested scheduling is verified through actual job observations; failures remain visible.\n- Original transcripts, unrelated jobs, required gates and resource ceilings remain preserved.\n\n\u003C\u002Fsuccess_criteria>\n",{"name":5,"description":7,"allowed-tools":44,"argument-hint":45},"Read, Bash(python3 --version), Bash(python3 -B \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fusage_control.py\":*), {{! tool('ask_user') !}}","[report|collect|detect|hourly|install|status|stop|restart] [options]","main","978d51c51d68c99cffb2ba48f7cad9d2f07e5738","src\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins","https:\u002F\u002Fgithub.com\u002Foutcomeeng","https:\u002F\u002Foutcome.engineering","Spec-driven development for AI-assisted engineering","2026-11-13 22:49:15",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add outcomeeng\u002Fplugins --skill control-token-spend",{"tool":60,"command":61},"bunx","bunx skills add outcomeeng\u002Fplugins --skill control-token-spend",{"tool":63,"command":64},"pnpm","pnpm dlx skills add outcomeeng\u002Fplugins --skill control-token-spend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002FSKILL.md",true,[68,74,78,82,86],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fmodel-prices.json","SCRIPT","脚本",26,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002Fscripts\u002Fmodel-prices.json",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fusage_accounting.py",54115,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002Fscripts\u002Fusage_accounting.py",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fusage_control.py",18319,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002Fscripts\u002Fusage_control.py",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fusage_reports.py",27966,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002Fscripts\u002Fusage_reports.py",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Fusage_schedule.py",29405,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fcoding-agents\u002Fskills\u002Fcontrol-token-spend\u002Fscripts\u002Fusage_schedule.py",[91,97,132,148,165,178],{"skillNo":92,"name":93,"nameZh":6,"description":6,"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":96,"publishedAt":39},"01M71G25RZTPQG9KJ00JCHC1F7","plugin","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Ftemplates\u002Fplugin\u002FSKILL.md",[],[93],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":113,"publishedAt":39},"01M71G23DCX3SV60H63HBBKQ6J","sanitize-powerpoint","ALWAYS invoke this skill when sanitizing, cleaning up, auditing, or aligning a PowerPoint (.pptx) deck — slide-master and layout structure, layout type attributes, stray fonts, non-theme colors, or layout naming. NEVER hand-edit pptx XML without this skill.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fwork\u002Fskills\u002Fsanitize-powerpoint\u002FSKILL.md",[103,108],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000003","演示文稿","SCENARIO","使用场景",{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,29,28],"sanitize powerpoint","powerpoint","sanitize","fonts","type","cleaning","structure","never","attributes","theme","pptx","naming","layout","deck","up","edit","xml","master",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":39},"01M71G21PQKBCDECHGVYSKPJW5","draw-excalidraw","ALWAYS invoke this skill when creating Excalidraw diagrams, visualizing workflows, architectures, or concepts. NEVER generate Excalidraw JSON without this skill.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fwork\u002Fskills\u002Fdraw-excalidraw\u002FSKILL.md",[],[139,140,141,142,143,121,29,144,145,28,146,147],"draw excalidraw","excalidraw","draw","diagrams","architectures","generate","workflows","concepts","json",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":39},"01M71G1ZMNGFD37RZYM620XM2C","typescript-test-standards","TypeScript test standards enforced across all skills. Loaded by other skills, not invoked directly.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Ftypescript\u002Fskills\u002Ftypescript-test-standards\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000008","测试与质量",[158,159,160,161,162,163,164],"typescript","typescript test standards","test","standards","false","read","across",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":174,"publishedAt":39},"01M71G1XBH0X1VCTR7269MDGSY","typescript-code-standards","TypeScript code standards enforced across all skills. Loaded by other skills, not invoked directly.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Ftypescript\u002Fskills\u002Ftypescript-code-standards\u002FSKILL.md",[171],{"categoryNo":172,"categoryName":173,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000030","开发工程师",[158,175,176,177,161,162,163,164],"code","typescript code standards","code standards",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":39},"01M71G1TQ3VN45SJ75DFMJDB9W","typescript-architecture-standards","TypeScript ADR conventions enforced across architect and auditor skills. Loaded by other skills, not invoked directly.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Ftypescript\u002Fskills\u002Ftypescript-architecture-standards\u002FSKILL.md",[],[185,161,186,187,158,188,189,164,163,190,162,191],"architecture standards","typescript architecture standards","architecture","adr","architect","auditor","conventions"]