[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E6NABR572P35ZJSJSHYSTC":3,"skill-same:01M7E6NABR572P35ZJSJSHYSTC":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7E6NABR572P35ZJSJSHYSTC","retro",null,"Use when the user asks for a retrospective at the end of a work session on a Godot game.","nick-vas\u002Fhyperdot","nick-vas","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7181961?v=4","01M7E6F6F0BQ49V0JZHX9BXCBD","Nikolaos Vasilikiotis","01M7E6F6FZW8SW1AJ1S7ARFE89",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fretro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retro\ndescription: Use when the user asks for a retrospective at the end of a work session on a Godot game.\ndisable-model-invocation: true\n---\n\n# Retro: lessons from this session\n\nCurated lessons make agents better; lessons an agent writes for itself, unchecked, make them worse (SkillsBench measured\n-1 to -11 points for self-written skills against +16 for curated ones). So every lesson here needs evidence, the user's\napproval, and, for kit changes, a measured result. Never write a new skill from scratch.\n\n## 1. Gather evidence (read, do not summarise from memory)\n\n- The run history: `.godot\u002Fhyperdot-history.jsonl` in the project. Error codes and failed runners that recur.\n- The handoff log: `.godot\u002Fhyperdot-handoffs.jsonl` (or `handoffs` in `status -Json`), what the subagents were asked and\n  answered. A `FAIL` verdict followed by \"done\" with no passing handoff or test run after it, or the same check asked\n  again and again, is evidence.\n- This conversation: where the user corrected you, where you retried a command, where a fix was reverted.\n- Auto memory: `MEMORY.md` in this project's Claude Code memory folder, if it exists.\n- `git log --oneline -30` and reverted or amended work.\n- `docs\u002Flessons.md` in the game, so nothing is recorded twice.\n- `docs\u002Fkit-notes.md` in the game: one line each time the kit got in the way. Each line without a pull request link is a\n  kit candidate (step 3), with the line itself as its evidence.\n- For a whole-project post-mortem: the people (or agents) who built it, over a playthrough recording or a `playthrough`\n  log, not memory. Take each account separately before merging, and record disagreements instead of averaging them:\n  \"Sometimes those contradictions are because one person is wrong. But sometimes, everyone is correct.\" (Yusaku\n  Yamamoto, *Untold History*).\n\n- **The team's shape and its recurring jobs.** Who did what this time (the user, agents, subagents, scheduled jobs), and\n  the jobs that come back every week or release: the build, playtests, the store page, the board, backups, answering\n  players. Ask the user: \"What recurring job has no owner?\" A job nobody owns is a lesson with its evidence (the last\n  time it was done, from git or the history). Note the answer in `docs\u002Flessons.md`, the job and who now owns it.\n\n## 2. Write each lesson as one line with its evidence\n\n`\u003Cwhat to do differently> - evidence: \u003Clog line, error code with count, or the user's words>`. Drop anything without\nevidence, anything Claude would do anyway, and project overviews (they do not help agents and cost tokens).\n\n## 3. Sort them\n\n- **About this game** (its scenes, its rules, its quirks): append to the game's `docs\u002Flessons.md`.\n- **About Godot or the kit** (true for any game): a candidate kit change. Name the smallest place it fits: one row in\n  `godot-pitfalls`, one line in an existing skill, a `doctor` check, a test, a script fix. Not a new skill.\n\n## 4. Ask the user\n\nOne multiple-choice question per kit candidate: the exact proposed text or diff, the evidence, and the options\n\"Open a kit PR\", \"Keep it game-only\", \"Drop it\". Nothing is changed without a choice.\n\n## 5. Prove a kit change before proposing it\n\nWork in the kit clone (the folder above `ci\u002Fgodot\u002Fhyperdot.ps1`; AGENTS.md names it). Never on `main`:\n\n```powershell\ngit -C \u003Ckit> switch -c feature\u002F\u003Csix random lowercase letters or digits> origin\u002Fmain\n# make the change, then:\npwsh \u003Ckit>\u002Fci\u002Fgodot\u002Ftools\u002FTest-Skills.ps1\npwsh \u003Ckit>\u002Ftests\u002FTest-SkillFixtures.ps1\n```\n\nIf the change touches a skill, agent or hook, run the kit's evals before and after (from the kit folder):\n`claude plugin eval . --runs 3 --scaffold --trust-plugin --allow-tools Bash Edit Write --no-publish` (the flags of the kit's\n`.github\u002Fworkflows\u002Fevals.yml`). Put both score tables (with, without, delta, cost) in the PR description. Do not open\nthe PR if the validators fail or the score went down; tell the user instead.\n\nCommit as the user, with no AI attribution, push the branch and open a pull request (`gh pr create` when `gh` is installed;\notherwise print the branch and the compare URL). Never merge it.\n\n## 6. Clean up\n\nRemove promoted lessons from auto memory, so they are not loaded twice. Add each kit PR's link at the end of the\n`docs\u002Fkit-notes.md` lines it answers; delete lines the user chose to drop. Report: lessons recorded, PRs opened with links,\ncandidates dropped and why, kit files committed or left (step 7).\n\n## 7. Leave the game clean\n\nThe kit writes files into the game (`AGENTS.md`, `CLAUDE.md`, `docs\u002Fkit-help.md`, `.claude\u002Fsettings.json`, the workflow and\nthe like), and a fresh clone lacks them until they are committed. Read what git sees as new or changed:\n\n```powershell\npwsh \u003Ckit>\u002Fci\u002Fgodot\u002Fhyperdot.ps1 doctor -Json -Quiet -Project \u003Cgame>\n```\n\n`uncommittedKitFiles[]` in the result is empty: say so and stop. Otherwise ask one multiple-choice question that lists the\nfiles, marks each with `machinePath: true` as naming a path of this machine, and offers \"Commit them on a `bugfix\u002F` branch\",\n\"Keep them local\" and \"Leave them\". Commit only the files without a machine path, plus any the user names; commit as the user\nwith no AI attribution and do not push. Keep a file local with a line in `.git\u002Finfo\u002Fexclude`. Never commit\n`.claude\u002Fsettings.local.json`. To tell the kit's maintainers, `doctor -ReportIssue` shows the issue and files it only after a\nyes: run it when the user asks, not by yourself.\n","# Retro: lessons from this session\n\nCurated lessons make agents better; lessons an agent writes for itself, unchecked, make them worse (SkillsBench measured\n-1 to -11 points for self-written skills against +16 for curated ones). So every lesson here needs evidence, the user's\napproval, and, for kit changes, a measured result. Never write a new skill from scratch.\n\n## 1. Gather evidence (read, do not summarise from memory)\n\n- The run history: `.godot\u002Fhyperdot-history.jsonl` in the project. Error codes and failed runners that recur.\n- The handoff log: `.godot\u002Fhyperdot-handoffs.jsonl` (or `handoffs` in `status -Json`), what the subagents were asked and\n  answered. A `FAIL` verdict followed by \"done\" with no passing handoff or test run after it, or the same check asked\n  again and again, is evidence.\n- This conversation: where the user corrected you, where you retried a command, where a fix was reverted.\n- Auto memory: `MEMORY.md` in this project's Claude Code memory folder, if it exists.\n- `git log --oneline -30` and reverted or amended work.\n- `docs\u002Flessons.md` in the game, so nothing is recorded twice.\n- `docs\u002Fkit-notes.md` in the game: one line each time the kit got in the way. Each line without a pull request link is a\n  kit candidate (step 3), with the line itself as its evidence.\n- For a whole-project post-mortem: the people (or agents) who built it, over a playthrough recording or a `playthrough`\n  log, not memory. Take each account separately before merging, and record disagreements instead of averaging them:\n  \"Sometimes those contradictions are because one person is wrong. But sometimes, everyone is correct.\" (Yusaku\n  Yamamoto, *Untold History*).\n\n- **The team's shape and its recurring jobs.** Who did what this time (the user, agents, subagents, scheduled jobs), and\n  the jobs that come back every week or release: the build, playtests, the store page, the board, backups, answering\n  players. Ask the user: \"What recurring job has no owner?\" A job nobody owns is a lesson with its evidence (the last\n  time it was done, from git or the history). Note the answer in `docs\u002Flessons.md`, the job and who now owns it.\n\n## 2. Write each lesson as one line with its evidence\n\n`\u003Cwhat to do differently> - evidence: \u003Clog line, error code with count, or the user's words>`. Drop anything without\nevidence, anything Claude would do anyway, and project overviews (they do not help agents and cost tokens).\n\n## 3. Sort them\n\n- **About this game** (its scenes, its rules, its quirks): append to the game's `docs\u002Flessons.md`.\n- **About Godot or the kit** (true for any game): a candidate kit change. Name the smallest place it fits: one row in\n  `godot-pitfalls`, one line in an existing skill, a `doctor` check, a test, a script fix. Not a new skill.\n\n## 4. Ask the user\n\nOne multiple-choice question per kit candidate: the exact proposed text or diff, the evidence, and the options\n\"Open a kit PR\", \"Keep it game-only\", \"Drop it\". Nothing is changed without a choice.\n\n## 5. Prove a kit change before proposing it\n\nWork in the kit clone (the folder above `ci\u002Fgodot\u002Fhyperdot.ps1`; AGENTS.md names it). Never on `main`:\n\n```powershell\ngit -C \u003Ckit> switch -c feature\u002F\u003Csix random lowercase letters or digits> origin\u002Fmain\n# make the change, then:\npwsh \u003Ckit>\u002Fci\u002Fgodot\u002Ftools\u002FTest-Skills.ps1\npwsh \u003Ckit>\u002Ftests\u002FTest-SkillFixtures.ps1\n```\n\nIf the change touches a skill, agent or hook, run the kit's evals before and after (from the kit folder):\n`claude plugin eval . --runs 3 --scaffold --trust-plugin --allow-tools Bash Edit Write --no-publish` (the flags of the kit's\n`.github\u002Fworkflows\u002Fevals.yml`). Put both score tables (with, without, delta, cost) in the PR description. Do not open\nthe PR if the validators fail or the score went down; tell the user instead.\n\nCommit as the user, with no AI attribution, push the branch and open a pull request (`gh pr create` when `gh` is installed;\notherwise print the branch and the compare URL). Never merge it.\n\n## 6. Clean up\n\nRemove promoted lessons from auto memory, so they are not loaded twice. Add each kit PR's link at the end of the\n`docs\u002Fkit-notes.md` lines it answers; delete lines the user chose to drop. Report: lessons recorded, PRs opened with links,\ncandidates dropped and why, kit files committed or left (step 7).\n\n## 7. Leave the game clean\n\nThe kit writes files into the game (`AGENTS.md`, `CLAUDE.md`, `docs\u002Fkit-help.md`, `.claude\u002Fsettings.json`, the workflow and\nthe like), and a fresh clone lacks them until they are committed. Read what git sees as new or changed:\n\n```powershell\npwsh \u003Ckit>\u002Fci\u002Fgodot\u002Fhyperdot.ps1 doctor -Json -Quiet -Project \u003Cgame>\n```\n\n`uncommittedKitFiles[]` in the result is empty: say so and stop. Otherwise ask one multiple-choice question that lists the\nfiles, marks each with `machinePath: true` as naming a path of this machine, and offers \"Commit them on a `bugfix\u002F` branch\",\n\"Keep them local\" and \"Leave them\". Commit only the files without a machine path, plus any the user names; commit as the user\nwith no AI attribution and do not push. Keep a file local with a line in `.git\u002Finfo\u002Fexclude`. Never commit\n`.claude\u002Fsettings.local.json`. To tell the kit's maintainers, `doctor -ReportIssue` shows the issue and files it only after a\nyes: run it when the user asks, not by yourself.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","5fa4c2262d814d50f72198a95b8c483ff195f90f",".agents\u002Fskills\u002Fretro",0,"https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot","https:\u002F\u002Fnick-vas.github.io\u002Fhyperdot\u002F","https:\u002F\u002Fgithub.com\u002Fnick-vas","https:\u002F\u002Fcommon-beef.itch.io\u002F","2026-11-13 18:55:29",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add nick-vas\u002Fhyperdot --skill retro",{"tool":40,"command":41},"bunx","bunx skills add nick-vas\u002Fhyperdot --skill retro",{"tool":43,"command":44},"pnpm","pnpm dlx skills add nick-vas\u002Fhyperdot --skill retro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fretro\u002FSKILL.md",[],[48,55,61,68,75,82],{"skillNo":49,"name":50,"nameZh":6,"description":51,"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},"01M7E6RF2S03S92PB9RZB4S4W0","over-budget","Use when a fixture exceeds the size budget.","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002Ftests\u002Fskill-fixtures\u002Fover-budget\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"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":58,"categories":59,"keywords":60,"publishedAt":19},"01M7E6RBY8SDNMA3ZARE8MAH0G","bad-yaml","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002Ftests\u002Fskill-fixtures\u002Fbad-yaml\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7E6R9S9YHTC552SR41RQAJ1","bad-workflow-description","Use when testing; runs the kit and then reads the JSON.","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002Ftests\u002Fskill-fixtures\u002Fbad-workflow-description\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7E6R6CWSAN48C80130CM1AK","bad-version","Use when a fixture quotes a stale package version.","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002Ftests\u002Fskill-fixtures\u002Fbad-version\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"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},"01M7E6R2C0E24TC133ESHKZT9R","bad-value","Use when a fixture passes a value outside a parameter's set.","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002Ftests\u002Fskill-fixtures\u002Fbad-value\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},"01M7E6QYM81V061X7DSQ94CZRP","bad-trigger","Helps with Godot tests.","https:\u002F\u002Fgithub.com\u002Fnick-vas\u002Fhyperdot\u002Fblob\u002Fmain\u002Ftests\u002Fskill-fixtures\u002Fbad-trigger\u002FSKILL.md",[],[]]