[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DGS5V8Z7AYKKGMSWF7FMK0":3,"skill-same:01M7DGS5V8Z7AYKKGMSWF7FMK0":44},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7DGS5V8Z7AYKKGMSWF7FMK0","cli-software",null,"Use for any task whose prompt is a multi-part specification for a CLI tool or program (numbered requirements, commands, options, output formats, error handling, examples), especially when built incrementally across several checkpoints and graded by hidden tests. Load before reading the spec in detail.","jemdiggity\u002Fkojo","jemdiggity","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1940552?v=4","01M7DGK797SRB0B74KVSKQ44GZ","Jeremy Hale","01M7DGK7ABQPV6AA6CPDC2NNP7",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dbm\u002Fround1\u002Fs1a-enumerate-examples\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cli-software\ndescription: Use for any task whose prompt is a multi-part specification for a CLI tool or program (numbered requirements, commands, options, output formats, error handling, examples), especially when built incrementally across several checkpoints and graded by hidden tests. Load before reading the spec in detail.\n---\n\n# CLI software: enumerate, then execute\n\nYou are building against a written spec and hidden tests. Most lost points come from\nspec bullets that were read but never exercised. Work in this order.\n\n## 1. Read the spec, then write the checklist (before any code)\n\nCreate or update `NOTES.md` in the workspace. Under a `## Checklist` heading, write one\nline per obligation, in the spec's own words, for **every**:\n\n- requirement \u002F feature bullet\n- constraint, validation rule, and \"must\"\u002F\"must not\" sentence\n- error-handling bullet (each is a separate line: trigger -> expected message\u002Fexit code)\n- example command in the spec (copy the command verbatim as its own line)\n- output field or event shape mentioned anywhere\n\nDo not summarize or merge lines. If the spec has 30 bullets, the checklist has 30+ lines.\nLater checkpoints: append the new section's lines; keep old ones (earlier tests are re-run).\n\n## 2. Implement against the checklist\n\nGo down the list. When a line is implemented, mark it `[x]`. When a line reveals an\nambiguity, implement it so that every plausible reading is accepted, note the decision\ninline, and move on. Do not stop to ask; the run is non-interactive.\n\n## 3. Execute every line before finishing\n\nVerification is not \"run the happy path once\". For each checklist line, run at least one\nreal command that exercises it and observe the actual output:\n\n- **Examples: run verbatim.** Copy the spec's example command exactly (same option order,\n  same argument shapes, same file layout) and compare your output to the expected output\n  character by character where the spec shows it.\n- **Then run one perturbation per example.** Change exactly one thing and confirm it still\n  works: options in a different position on the command line, a different working\n  directory or path style (relative\u002Fabsolute, inside\u002Foutside a directory), a null\u002Fempty\u002F\n  missing optional value, a quoted string vs a bare word or number, and an equivalent\n  spelling the spec would reasonably accept.\n- **Error bullets: trigger each one.** Craft the bad input, run it, and check the message,\n  the stream (stderr vs stdout), and the exit code. An error path you never triggered\n  counts as unimplemented.\n- **Undo\u002Freverse\u002Fcleanup paths:** apply, reverse, then inspect the resulting state directly\n  (query it, list it, cat it) rather than trusting your own success message.\n\nRecord results as a short line under each checklist item (`ok`, or what broke). A line you\ncannot run is a red flag; say why in the notes and reconsider the implementation.\n\n## 4. Finish\n\nBefore your final message, re-scan the checklist for any unmarked line and any line marked\nwithout a run. Fix those first. Then state, briefly, what you verified and what remains\nuntested. Never claim coverage you did not execute.\n\n## Habits that cost points (avoid)\n\n- Reading a section header like \"Constraints\" and treating it as background text. Every\n  bullet under it is a test.\n- Testing only inputs your own code generated earlier. Hand-craft inputs literally from the\n  spec's description too.\n- Catching broad exceptions around the command entry point and reporting them as usage\n  errors. Usage errors come only from argument parsing; everything else is an explicit\n  `Error:` message on stderr with a non-zero exit.\n- Silently narrowing a guaranteed property when a shortcut fails. If the cheap path cannot\n  preserve the property, use the thorough path or report an error.\n- Treating the spec's example output as the full set of fields. Examples are a floor:\n  include every identifying field the operation carries.\n","# CLI software: enumerate, then execute\n\nYou are building against a written spec and hidden tests. Most lost points come from\nspec bullets that were read but never exercised. Work in this order.\n\n## 1. Read the spec, then write the checklist (before any code)\n\nCreate or update `NOTES.md` in the workspace. Under a `## Checklist` heading, write one\nline per obligation, in the spec's own words, for **every**:\n\n- requirement \u002F feature bullet\n- constraint, validation rule, and \"must\"\u002F\"must not\" sentence\n- error-handling bullet (each is a separate line: trigger -> expected message\u002Fexit code)\n- example command in the spec (copy the command verbatim as its own line)\n- output field or event shape mentioned anywhere\n\nDo not summarize or merge lines. If the spec has 30 bullets, the checklist has 30+ lines.\nLater checkpoints: append the new section's lines; keep old ones (earlier tests are re-run).\n\n## 2. Implement against the checklist\n\nGo down the list. When a line is implemented, mark it `[x]`. When a line reveals an\nambiguity, implement it so that every plausible reading is accepted, note the decision\ninline, and move on. Do not stop to ask; the run is non-interactive.\n\n## 3. Execute every line before finishing\n\nVerification is not \"run the happy path once\". For each checklist line, run at least one\nreal command that exercises it and observe the actual output:\n\n- **Examples: run verbatim.** Copy the spec's example command exactly (same option order,\n  same argument shapes, same file layout) and compare your output to the expected output\n  character by character where the spec shows it.\n- **Then run one perturbation per example.** Change exactly one thing and confirm it still\n  works: options in a different position on the command line, a different working\n  directory or path style (relative\u002Fabsolute, inside\u002Foutside a directory), a null\u002Fempty\u002F\n  missing optional value, a quoted string vs a bare word or number, and an equivalent\n  spelling the spec would reasonably accept.\n- **Error bullets: trigger each one.** Craft the bad input, run it, and check the message,\n  the stream (stderr vs stdout), and the exit code. An error path you never triggered\n  counts as unimplemented.\n- **Undo\u002Freverse\u002Fcleanup paths:** apply, reverse, then inspect the resulting state directly\n  (query it, list it, cat it) rather than trusting your own success message.\n\nRecord results as a short line under each checklist item (`ok`, or what broke). A line you\ncannot run is a red flag; say why in the notes and reconsider the implementation.\n\n## 4. Finish\n\nBefore your final message, re-scan the checklist for any unmarked line and any line marked\nwithout a run. Fix those first. Then state, briefly, what you verified and what remains\nuntested. Never claim coverage you did not execute.\n\n## Habits that cost points (avoid)\n\n- Reading a section header like \"Constraints\" and treating it as background text. Every\n  bullet under it is a test.\n- Testing only inputs your own code generated earlier. Hand-craft inputs literally from the\n  spec's description too.\n- Catching broad exceptions around the command entry point and reporting them as usage\n  errors. Usage errors come only from argument parsing; everything else is an explicit\n  `Error:` message on stderr with a non-zero exit.\n- Silently narrowing a guaranteed property when a shortcut fails. If the cheap path cannot\n  preserve the property, use the thorough path or report an error.\n- Treating the spec's example output as the full set of fields. Examples are a floor:\n  include every identifying field the operation carries.\n",{"name":5,"description":7},"main","90c4e234b13d749b2f69ddcb1c759e5f667f6413","skills\u002Fsonnet-dbm\u002Fround1\u002Fs1a-enumerate-examples","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo","https:\u002F\u002Fgithub.com\u002Fjemdiggity","2026-11-01 06:04:44",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add jemdiggity\u002Fkojo --skill cli-software",{"tool":36,"command":37},"bunx","bunx skills add jemdiggity\u002Fkojo --skill cli-software",{"tool":39,"command":40},"pnpm","pnpm dlx skills add jemdiggity\u002Fkojo --skill cli-software","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dbm\u002Fround1\u002Fs1a-enumerate-examples\u002FSKILL.md",true,[],[45,52,57,62,67,72],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7DGWAMS2Z08G9S6KYEBM4YG","service-spec","Invoke before reading any code, for any task whose prompt is a multi-part spec for a service, API or CLI built up over successive parts (part 1, part 2, ... each adding or changing behavior). Apply its rules while reading the spec literally and while choosing behavior where the spec is silent.","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dcs\u002Fround3\u002Fd3e-accept\u002FSKILL.md",[],[],{"skillNo":53,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7DGW5T9M4EXVHNTNW1NY6MR","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dcs\u002Fround3\u002Fd3d-exact-words\u002FSKILL.md",[],[],{"skillNo":58,"name":47,"nameZh":6,"description":48,"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},"01M7DGW1S560QM0M72BSYP42XB","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dcs\u002Fround3\u002Fd3c-omit\u002FSKILL.md",[],[],{"skillNo":63,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7DGVXQS07PEJQBS7VJC9B7R","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dcs\u002Fround3\u002Fd3b-inherit\u002FSKILL.md",[],[],{"skillNo":68,"name":47,"nameZh":6,"description":48,"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},"01M7DGVSEXFX35NZPSPBN9833Q","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dcs\u002Fround3\u002Fd3a-gate-lean\u002FSKILL.md",[],[],{"skillNo":73,"name":47,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7DGVNNTDB3EGQHJXTNM986H","Use for any task whose prompt is a multi-part spec for a service, API, or CLI built up over successive parts (part 1, part 2, ... each adding or changing behavior). Guides literal reading of the spec and the choices to make where it is silent.","https:\u002F\u002Fgithub.com\u002Fjemdiggity\u002Fkojo\u002Fblob\u002Fmain\u002Fskills\u002Fsonnet-dcs\u002Fround2\u002Fd2e-lean\u002FSKILL.md",[],[]]