[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BZT3FEGMSPCCA40QJWYFXQ":3,"skill-same:01M7BZT3FEGMSPCCA40QJWYFXQ":48},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7BZT3FEGMSPCCA40QJWYFXQ","shift-dev",null,"Build, test and debug Shift itself — the Guile module layout, the compiled-vs-source trap, running one suite instead of all of them, and where a new module has to be registered. Use when editing anything under src\u002Flive-agent, extensions\u002Fshift, or agent\u002F.","thrashr888\u002Fshift","thrashr888","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10213?v=4","01M7BZSZGHT71RQ58BNZX66ACN","Paul Thrasher","01M7BZSZH5MARAKQHD9SR9VXVJ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002F.shift-plugin\u002Fskills\u002Fshift-dev\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: shift-dev\ndescription: Build, test and debug Shift itself — the Guile module layout, the compiled-vs-source trap, running one suite instead of all of them, and where a new module has to be registered. Use when editing anything under src\u002Flive-agent, extensions\u002Fshift, or agent\u002F.\n---\n\n# Working on Shift\n\n## Layout\n\n| Path | What it is |\n| --- | --- |\n| `src\u002Flive-agent\u002F*.scm` | the permanent runtime: authority, transport, tools, session |\n| `extensions\u002Fshift\u002F*.scm` | trusted built-ins reached through `builtin-ref`, including tracing and the provider adapters |\n| `agent\u002Fdefault.scm` | the live image. User-owned data, not runtime code: bindings here are what `live_eval` rewrites at runtime |\n| `test\u002F*.scm` | SRFI-64 suites |\n| `test\u002F*.py` | integration tests that drive `bin\u002Fshift-agent` against a fake provider |\n\n## Build before you test\n\n```sh\nmake build\n```\n\n`bin\u002Fshift-agent` and the tests load compiled modules from `build\u002F` **and fall\nback to source when a `.go` is stale**. The fallback is silent, so an edit you\nforgot to compile does not fail — it just tests the old module in some paths\nand the new one in others. Run `make build` after editing any `.scm` under\n`src\u002F` or `extensions\u002F`. `make -n build` lists what is stale without compiling,\nand the DEV pane shows the same thing.\n\n## Tests\n\n```sh\nmake test          # every Guile suite plus every Python test; ~3 minutes\nmake check         # the same target\n```\n\n`make test` runs longer than a default command timeout, so give it room or run\nit in the background rather than assuming it hung.\n\nOne suite at a time:\n\n```sh\nguile -L src -L extensions -C build test\u002Frun.scm test\u002Freceipt.scm\n```\n\nThis asks for approval every time and is meant to. `test\u002Frun.scm` loads\nwhatever path follows it, so allowlisting any prefix that reaches it would let\na file be written and then executed without approval — the shell boundary this\nproject keeps closed. `make build`, `make test`, `make check` and `make -n` are\nallowlisted instead.\n\n## Registering a new module or suite\n\n- A new `src\u002Flive-agent\u002FNAME.scm` is compiled automatically: the Makefile globs\n  `CORE_SOURCES`.\n- A new `test\u002FNAME.scm` is **not** run automatically. Add `NAME` to the suite\n  list in the Makefile's `test:` target or the suite never runs, and a green\n  `make test` will mean nothing about it.\n- A new `test\u002FNAME.py` likewise needs its own `python3 test\u002FNAME.py` line.\n\n## Two traps worth knowing\n\n**SRFI-64 tests after `test-end` are silently skipped.** Appending a case below\n`(test-end \"name\")` leaves it unexecuted while the suite still reports success,\nwith the pass count unchanged. If a case you just added does not appear in the\noutput, check that it sits above `test-end`.\n\n**Tool schemas are charged on every request.** Several integration tests pin a\ntight `context-limit`, so lengthening a tool description in\n`src\u002Flive-agent\u002Ftools.scm` can push an unrelated turn over its budget and fail\nit with \"Context still exceeds the budget\". Put instructions the model needs\nonly after calling a tool in that tool's *output* rather than its description.\n\n## Debugging a session\n\n`traces.jsonl` in the session folder holds every span. In a session, the\n`traces` tool searches it and fetches a span by `span_id`; outside one,\n`python3 scripts\u002Fevals.py session NAME` gives a per-turn review with rounds,\nfailures, waits and judge disagreements.\n","# Working on Shift\n\n## Layout\n\n| Path | What it is |\n| --- | --- |\n| `src\u002Flive-agent\u002F*.scm` | the permanent runtime: authority, transport, tools, session |\n| `extensions\u002Fshift\u002F*.scm` | trusted built-ins reached through `builtin-ref`, including tracing and the provider adapters |\n| `agent\u002Fdefault.scm` | the live image. User-owned data, not runtime code: bindings here are what `live_eval` rewrites at runtime |\n| `test\u002F*.scm` | SRFI-64 suites |\n| `test\u002F*.py` | integration tests that drive `bin\u002Fshift-agent` against a fake provider |\n\n## Build before you test\n\n```sh\nmake build\n```\n\n`bin\u002Fshift-agent` and the tests load compiled modules from `build\u002F` **and fall\nback to source when a `.go` is stale**. The fallback is silent, so an edit you\nforgot to compile does not fail — it just tests the old module in some paths\nand the new one in others. Run `make build` after editing any `.scm` under\n`src\u002F` or `extensions\u002F`. `make -n build` lists what is stale without compiling,\nand the DEV pane shows the same thing.\n\n## Tests\n\n```sh\nmake test          # every Guile suite plus every Python test; ~3 minutes\nmake check         # the same target\n```\n\n`make test` runs longer than a default command timeout, so give it room or run\nit in the background rather than assuming it hung.\n\nOne suite at a time:\n\n```sh\nguile -L src -L extensions -C build test\u002Frun.scm test\u002Freceipt.scm\n```\n\nThis asks for approval every time and is meant to. `test\u002Frun.scm` loads\nwhatever path follows it, so allowlisting any prefix that reaches it would let\na file be written and then executed without approval — the shell boundary this\nproject keeps closed. `make build`, `make test`, `make check` and `make -n` are\nallowlisted instead.\n\n## Registering a new module or suite\n\n- A new `src\u002Flive-agent\u002FNAME.scm` is compiled automatically: the Makefile globs\n  `CORE_SOURCES`.\n- A new `test\u002FNAME.scm` is **not** run automatically. Add `NAME` to the suite\n  list in the Makefile's `test:` target or the suite never runs, and a green\n  `make test` will mean nothing about it.\n- A new `test\u002FNAME.py` likewise needs its own `python3 test\u002FNAME.py` line.\n\n## Two traps worth knowing\n\n**SRFI-64 tests after `test-end` are silently skipped.** Appending a case below\n`(test-end \"name\")` leaves it unexecuted while the suite still reports success,\nwith the pass count unchanged. If a case you just added does not appear in the\noutput, check that it sits above `test-end`.\n\n**Tool schemas are charged on every request.** Several integration tests pin a\ntight `context-limit`, so lengthening a tool description in\n`src\u002Flive-agent\u002Ftools.scm` can push an unrelated turn over its budget and fail\nit with \"Context still exceeds the budget\". Put instructions the model needs\nonly after calling a tool in that tool's *output* rather than its description.\n\n## Debugging a session\n\n`traces.jsonl` in the session folder holds every span. In a session, the\n`traces` tool searches it and fetches a span by `span_id`; outside one,\n`python3 scripts\u002Fevals.py session NAME` gives a per-turn review with rounds,\nfailures, waits and judge disagreements.\n",{"name":5,"description":7},"main","9c095495f5562627526cdf6f0673419a760c1d3e",".shift-plugin\u002Fskills\u002Fshift-dev",0,"https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift","https:\u002F\u002Fthrashr888.github.io\u002Fshift\u002F","https:\u002F\u002Fgithub.com\u002Fthrashr888","https:\u002F\u002Fpaul.thrasher.dev\u002F","Building many websites.","2026-09-25 11:00:23",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add thrashr888\u002Fshift --skill shift-dev",{"tool":40,"command":41},"bunx","bunx skills add thrashr888\u002Fshift --skill shift-dev",{"tool":43,"command":44},"pnpm","pnpm dlx skills add thrashr888\u002Fshift --skill shift-dev","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002F.shift-plugin\u002Fskills\u002Fshift-dev\u002FSKILL.md",true,[],[49,55,62,69,76,82],{"skillNo":50,"name":51,"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":52,"categories":53,"keywords":54,"publishedAt":19},"01M7BZV5FJS0T12SJB2X3V8K2B","tauri-browser","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002Fplugins\u002Ftauri-browser\u002Fskills\u002Ftauri-browser\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7BZV2R1DK48G0BVA9HPZFDT","ripwire","Answer \"who calls this\", \"is it safe to change\", \"which tests cover it\" and \"where do I start in this repo\" from a call graph instead of grepping and reading files. Use before editing a symbol, when a test fails with a trace, and when landing in an unfamiliar codebase; not for Scheme, which it cannot parse.","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002Fplugins\u002Fripwire\u002Fskills\u002Fripwire\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7BZTZ8JTQBWYR1Z9XMPWWAJ","onepassword","Work with the user's 1Password through the op CLI for non-secret operations (which vaults and items exist, whether a session is signed in) and know how Shift gets secrets from it. Use when a server or command needs a credential, or the user asks about their vaults.","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002Fplugins\u002Fonepassword\u002Fskills\u002Fonepassword\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7BZTWX2AS9CHHR300PNQ389","kanban","Keep and change this project's board — read the columns, move a card, add or retire one. Use when asked what is in progress, what to pick up next, or to move a card between columns.","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002Fplugins\u002Fkanban\u002Fskills\u002Fkanban\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"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":79,"categories":80,"keywords":81,"publishedAt":19},"01M7BZTW46MQVNWJKNN4QAZ99C","cortex","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002Fplugins\u002Fcortex\u002Fskills\u002Fcortex\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7BZTRZ7Y48S3SYY5PDNBFZ6","cider","Read and act on macOS Apple apps (Calendar, Reminders, Contacts, Notes, Mail, Music, Safari, Home and 30 more) with the cider CLI, which prints JSON. Use when the user asks about their calendar, reminders, contacts, notes, mail or Mac state, or wants one of those changed.","https:\u002F\u002Fgithub.com\u002Fthrashr888\u002Fshift\u002Fblob\u002Fmain\u002Fplugins\u002Fcider\u002Fskills\u002Fcider\u002FSKILL.md",[],[]]