[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FTPEZ2S6JAERG6642NW3P":3,"skill-same:01M70FTPEZ2S6JAERG6642NW3P":73},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M70FTPEZ2S6JAERG6642NW3P","staxtrace-memory",null,"Search local coding-agent session history before acting. Use BEFORE an Edit or Write to a file, BEFORE a non-trivial Bash command (a build, migration, or destructive\u002Flong-running command), and whenever the user references a past decision (\"what did we decide about X\", \"why is this done this way\", \"didn't we agree to Y\"), a specific file, or \"what worked last time\" — cases where a prior session on this machine may already hold the decision, the failure mode, or the exact working command. Queries the local `stax memory` CLI (staxtrace) across every past Claude Code \u002F Codex \u002F Cursor session so you do not re-derive an answer, contradict an earlier choice, or repeat a known failure. Local and read-only; nothing leaves the machine.","0bserver07\u002Fstaxtrace","0bserver07","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2153691?v=4","01M70FQJ6N9V6HY96M6KDPX9JZ","Yad Konrad","01M70FQJ7SBVFGQ6TP4DMB7NPX",2,"MIT","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Fskills\u002Fstaxtrace-memory\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"memory","staxtrace memory","done","cli","agent session","mode","re","you","local","across","time","code","references","only","command","decide","choice","decision","Bash","search","2026-11-10 10:12:30",false,"---\nname: staxtrace-memory\ndescription: Search local coding-agent session history before acting. Use BEFORE an Edit or Write to a file, BEFORE a non-trivial Bash command (a build, migration, or destructive\u002Flong-running command), and whenever the user references a past decision (\"what did we decide about X\", \"why is this done this way\", \"didn't we agree to Y\"), a specific file, or \"what worked last time\" — cases where a prior session on this machine may already hold the decision, the failure mode, or the exact working command. Queries the local `stax memory` CLI (staxtrace) across every past Claude Code \u002F Codex \u002F Cursor session so you do not re-derive an answer, contradict an earlier choice, or repeat a known failure. Local and read-only; nothing leaves the machine.\n---\n\n# staxtrace — query your past coding sessions before acting\n\nThis machine indexes every past coding-agent session locally with staxtrace.\nThe sessions are stateless; the history is not. A decision, a failure mode, or the\nexact command you need may already be recorded. Before re-deriving something,\ncheck whether the answer is already there.\n\n## When to reach for this\n\nCheck history **before** you act, whenever a prior session plausibly knows something:\n\n- **Before you Edit or Write a file** — run `stax memory file \u003Cpath>` first. Past\n  failure modes on that file (\"broke CI the last 3 of 5 times it was touched\") and\n  who changed it and why are the highest-signal context for a non-trivial edit.\n- **Before a non-trivial Bash command** — a build, a migration, anything\n  destructive or long-running — `stax memory worked \"\u003Caction>\"` shows whether it\n  succeeded before and what the working invocation was.\n- **When the user references a past decision** — \"what did we decide about\n  caching?\", \"why is X done this way?\", \"didn't we agree to Y?\" — `stax memory\n  decisions \"\u003Ctopic>\"` finds the session where it was decided.\n- **When picking up work in a repo** — `stax memory sessions` lists recent sessions\n  here so you neither duplicate nor contradict them.\n- **For an open-ended recall** — `stax memory ask \"\u003Cquestion>\"` runs a\n  natural-language search over the whole history.\n\nSkip it for pure read\u002Fexplain questions about the current code, greenfield work\nwith no history, or when the user already gave you the answer this turn. The check\nis cheap (local SQLite, no network) and an empty result is itself a useful signal.\n\n## The command menu\n\n```\nstax memory decisions \"\u003Ctopic>\"   # past decisions on a topic\nstax memory file \u003Cpath>           # a file's history: failure modes, who touched it, risk\nstax memory worked \"\u003Caction>\"     # past sessions where an action succeeded, with evidence\nstax memory sessions [path]       # recent sessions in this project (or touching a file)\nstax memory ask \"\u003Cquestion>\"      # natural-language query over all history\n```\n\nNarrowing flags on every command: `--since 30d` (tighten the window), `--limit N`\n(cap results), `--project \u003Cslug>` (scope). `--project` defaults to the current\ndirectory's project, so inside a repo these Just Work.\n\n`stax` is the short command. The long form `stax memory …` is identical\nand works anywhere `stax` is not on PATH.\n\n## Prefer text output; `--json` is for scripts only\n\nRun these commands **without** `--json`. The default text output is compact and\nreadable — meant to be scanned by you, the agent. **JSON output is large and can\nconsume the context window**: it is the stable, token-bounded envelope\n(`schema: stackunderflow.memory\u002F1`) for a *script or hook* that parses the result\nprogrammatically, not for splicing into a conversation. Reach for `--json` only\nwhen something downstream actually parses the output.\n\n## Cite what you surface\n\nWhen a result changes your answer, or you report it to the user, cite it: the\n**session id** and its **provider** (claude \u002F codex \u002F cursor), plus the date. A\nrecall the user can verify against the linked session is trustworthy; an uncited\nparaphrase reads as a guess. For example: \"On 2026-04-25 (codex session\n`def456…`) the prior session landed on SQLite because [snippet] — proceeding on\nthat basis.\"\n\n## Safety\n\n- **Do not overclaim.** Report a decision as made only if the surfaced snippet\n  actually says so. If the search comes up empty, say so and ask — never fabricate\n  a prior decision or a past outcome to fill the gap.\n- **Do not paste secrets or large payloads.** Surface the short excerpt you need;\n  do not dump raw session logs, tokens, keys, or large result blobs into the\n  conversation.\n- **The store is private and local.** `~\u002F.stackunderflow` is this machine's local\n  index. Every `stax memory` query is read-only and nothing leaves the machine —\n  do not write to it and do not exfiltrate its contents.\n","# staxtrace — query your past coding sessions before acting\n\nThis machine indexes every past coding-agent session locally with staxtrace.\nThe sessions are stateless; the history is not. A decision, a failure mode, or the\nexact command you need may already be recorded. Before re-deriving something,\ncheck whether the answer is already there.\n\n## When to reach for this\n\nCheck history **before** you act, whenever a prior session plausibly knows something:\n\n- **Before you Edit or Write a file** — run `stax memory file \u003Cpath>` first. Past\n  failure modes on that file (\"broke CI the last 3 of 5 times it was touched\") and\n  who changed it and why are the highest-signal context for a non-trivial edit.\n- **Before a non-trivial Bash command** — a build, a migration, anything\n  destructive or long-running — `stax memory worked \"\u003Caction>\"` shows whether it\n  succeeded before and what the working invocation was.\n- **When the user references a past decision** — \"what did we decide about\n  caching?\", \"why is X done this way?\", \"didn't we agree to Y?\" — `stax memory\n  decisions \"\u003Ctopic>\"` finds the session where it was decided.\n- **When picking up work in a repo** — `stax memory sessions` lists recent sessions\n  here so you neither duplicate nor contradict them.\n- **For an open-ended recall** — `stax memory ask \"\u003Cquestion>\"` runs a\n  natural-language search over the whole history.\n\nSkip it for pure read\u002Fexplain questions about the current code, greenfield work\nwith no history, or when the user already gave you the answer this turn. The check\nis cheap (local SQLite, no network) and an empty result is itself a useful signal.\n\n## The command menu\n\n```\nstax memory decisions \"\u003Ctopic>\"   # past decisions on a topic\nstax memory file \u003Cpath>           # a file's history: failure modes, who touched it, risk\nstax memory worked \"\u003Caction>\"     # past sessions where an action succeeded, with evidence\nstax memory sessions [path]       # recent sessions in this project (or touching a file)\nstax memory ask \"\u003Cquestion>\"      # natural-language query over all history\n```\n\nNarrowing flags on every command: `--since 30d` (tighten the window), `--limit N`\n(cap results), `--project \u003Cslug>` (scope). `--project` defaults to the current\ndirectory's project, so inside a repo these Just Work.\n\n`stax` is the short command. The long form `stax memory …` is identical\nand works anywhere `stax` is not on PATH.\n\n## Prefer text output; `--json` is for scripts only\n\nRun these commands **without** `--json`. The default text output is compact and\nreadable — meant to be scanned by you, the agent. **JSON output is large and can\nconsume the context window**: it is the stable, token-bounded envelope\n(`schema: stackunderflow.memory\u002F1`) for a *script or hook* that parses the result\nprogrammatically, not for splicing into a conversation. Reach for `--json` only\nwhen something downstream actually parses the output.\n\n## Cite what you surface\n\nWhen a result changes your answer, or you report it to the user, cite it: the\n**session id** and its **provider** (claude \u002F codex \u002F cursor), plus the date. A\nrecall the user can verify against the linked session is trustworthy; an uncited\nparaphrase reads as a guess. For example: \"On 2026-04-25 (codex session\n`def456…`) the prior session landed on SQLite because [snippet] — proceeding on\nthat basis.\"\n\n## Safety\n\n- **Do not overclaim.** Report a decision as made only if the surfaced snippet\n  actually says so. If the search comes up empty, say so and ask — never fabricate\n  a prior decision or a past outcome to fill the gap.\n- **Do not paste secrets or large payloads.** Surface the short excerpt you need;\n  do not dump raw session logs, tokens, keys, or large result blobs into the\n  conversation.\n- **The store is private and local.** `~\u002F.stackunderflow` is this machine's local\n  index. Every `stax memory` query is read-only and nothing leaves the machine —\n  do not write to it and do not exfiltrate its contents.\n",{"name":5,"description":7},"main","46546e71e94f94900c93ce3eb2f933866509593b","skills\u002Fstaxtrace-memory",1,"https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace","https:\u002F\u002Fstaxtrace.com","https:\u002F\u002Fgithub.com\u002F0bserver07","yadkonrad.com","- Coding Agents & Agent Driven Systems. \r\n\r\n- Program Synthesis.\r\n\r\n- ML\u002FData Infra.\r\n- Off. Sec. Research.\r\n\r\nElsewhere:\r\n- Creative Writing \u002F Standup Comedian","2026-10-19 15:40:37",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add 0bserver07\u002Fstaxtrace --skill staxtrace-memory",{"tool":65,"command":66},"bunx","bunx skills add 0bserver07\u002Fstaxtrace --skill staxtrace-memory",{"tool":68,"command":69},"pnpm","pnpm dlx skills add 0bserver07\u002Fstaxtrace --skill staxtrace-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Fskills\u002Fstaxtrace-memory\u002FSKILL.md",true,[],[74,81,90,103,116,125],{"skillNo":75,"name":76,"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":77,"categories":78,"keywords":79,"publishedAt":44},"01M70FTJYHWW5Z48VXETHR77YM","handwritten","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Frust\u002Fparity\u002Fhomes\u002Fskills-installed\u002F.claude\u002Fskills\u002Fhandwritten\u002FSKILL.md",[],[76,80],"true",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":44},"01M70FTGPRBK787GK8TDD00ZVE","auto-undated","no stamp","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Frust\u002Fparity\u002Fhomes\u002Fskills-installed\u002F.claude\u002Fskills\u002Fauto-undated\u002FSKILL.md",[],[88,89,80],"auto undated","auto",{"skillNo":91,"name":92,"nameZh":6,"description":93,"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":44},"01M70FTD81JPTDM2394ENGX3C3","auto-recent-thing","A recently generated skill.","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Frust\u002Fparity\u002Fhomes\u002Fskills-installed\u002F.claude\u002Fskills\u002Fauto-recent-thing\u002FSKILL.md",[],[89,97,98,99,80,100,101,102],"auto recent thing","jan","generated","sessions","tool","generated skill",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":44},"01M70FT8X06DZE5WS5B808N2N3","auto-old-thing","An auto-generated skill from a previous run.","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Frust\u002Fparity\u002Fhomes\u002Fskills-installed\u002F.claude\u002Fskills\u002Fauto-old-thing\u002FSKILL.md",[],[110,89,99,98,111,112,80,100,113,114,115,102],"auto old thing","parity","proj","2026","run","auto-generated",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":44},"01M70FT6RRH22GQ40N05JFYPVK","auto-hand-written","mine","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Frust\u002Fparity\u002Fhomes\u002Fskills-installed\u002F.claude\u002Fskills\u002Fauto-hand-written\u002FSKILL.md",[],[123,124,89,119],"hand","auto hand written",{"skillNo":126,"name":76,"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":127,"categories":128,"keywords":129,"publishedAt":44},"01M70FT1GSE8PBQWV9XS2E881J","https:\u002F\u002Fgithub.com\u002F0bserver07\u002Fstaxtrace\u002Fblob\u002Fmain\u002Frust\u002Fparity\u002Fhomes\u002Fskills-both\u002F.claude\u002Fskills\u002Fhandwritten\u002FSKILL.md",[],[76,80]]