[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79AEQNPB4MCKAVXG4CZSNH2":3,"skill-same:01M79AEQNPB4MCKAVXG4CZSNH2":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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79AEQNPB4MCKAVXG4CZSNH2","spur-trace",null,"Runs a project's pipeline or test suite once under a tracer and renders one static HTML page per run: per step the command, a call tree of the project's own functions, every file read and written with its sha256, which step's output fed which, and a hash-chain check; also exports W3C PROV-JSON. Use when a reviewer asks how a result was produced, which files a step read, or whether one step's output is really the next step's input — 'trace this pipeline', 'show provenance for this run', 'which step wrote this file', 'prove the outputs chain'. Writes only under analysis\u002Fspur\u002F (one directory per run) and never edits the traced code. Not for whether tests would catch a bug (zeugnis-assertion-audit) or for proving and fixing a handoff between stages (andon-verify).","Anselmoo\u002Fwerkstoff","Anselmoo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13209783?v=4","01M799YTB3D7RZ4P3B8CSR2X85","Anselm Hahn","01M799YTBRAM6719D9V0NRGB4R",1,"MIT","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fspur\u002Fskills\u002Fspur-trace\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spur-trace\ndescription: \"Runs a project's pipeline or test suite once under a tracer and renders one static HTML page per run: per step the command, a call tree of the project's own functions, every file read and written with its sha256, which step's output fed which, and a hash-chain check; also exports W3C PROV-JSON. Use when a reviewer asks how a result was produced, which files a step read, or whether one step's output is really the next step's input — 'trace this pipeline', 'show provenance for this run', 'which step wrote this file', 'prove the outputs chain'. Writes only under analysis\u002Fspur\u002F (one directory per run) and never edits the traced code. Not for whether tests would catch a bug (zeugnis-assertion-audit) or for proving and fixing a handoff between stages (andon-verify).\"\n---\n\nRecord one run of the pipeline as it actually happened. This skill changes no source\nfile: the tracer is loaded beside the program, never into it.\n\nThe rule above the others: **the traced run must behave exactly like an untraced one.**\nIf a traced run fails where a plain run succeeds, stop and report it as a spur defect —\ndo not work around it by editing the project.\n\n## Steps\n\n1. **Detect the stack.**\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fspur_trace.py\" detect\n   ```\n\n   Exit `0` names each stack found and the adapter it gets; exit `4` found none. Python is\n   traced in-process. Rust, Node and Go have no in-process adapter: read\n   [`references\u002Fadapters.md`](..\u002F..\u002Freferences\u002Fadapters.md) before tracing one, and say\n   to the user which parts of the record will be missing.\n\n2. **Find the one command that runs the pipeline**, in this order: a documented pipeline\n   command in the README, a `Makefile`\u002F`justfile` target, a driver script, the test suite\n   (`pytest`, `cargo test`, `npm test`). Ask the user only when none of these names it.\n   One command, run once: every step must be a process that command starts.\n\n3. **Run it under the tracer** from the project root.\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fspur_trace.py\" run -- \u003Ccommand> [args...]\n   ```\n\n   Exit codes, which decide the next step:\n\n   | exit | meaning | next |\n   |---|---|---|\n   | `0` | the command succeeded and every link verified | step 4 |\n   | `3` | a link is **broken**: a file changed between producer and consumer | step 4, lead with it |\n   | `4` | incomplete (an input is unverified) or empty (no step read another's output) | step 4; never call it a pass |\n   | `2` | usage or instrument error | fix the invocation, rerun step 3 |\n   | other | the command's own exit code: the pipeline failed | step 4, lead with the failing step |\n\n   On stderr it prints the summary and the run directory:\n\n   ```text\n   spur: 6 step(s), chain broken (2 verified, 1 broken, 1 unverified, 1 source)\n   spur: wrote analysis\u002Fspur\u002F20261030T183037Z\u002F{trace.json,prov.json,spur-report.html}\n   ```\n\n4. **Report from `trace.json`, not from memory.** Read\n   `analysis\u002Fspur\u002F\u003CrunId>\u002Ftrace.json` (the format is in\n   [`references\u002Ftrace-format.md`](..\u002F..\u002Freferences\u002Ftrace-format.md)) and tell the user:\n   - the chain verdict in one sentence, naming each `broken` input as\n     `producer → path@version → consumer` with its `note` (it names any untraced step that\n     ran in between);\n   - every `unverified` input, and every untraced step with its `why`;\n   - any step whose `exit.code` is non-zero, and the run's `dropped` count if it is not 0;\n   - the path of `spur-report.html` to open, and `prov.json` for PROV tools.\n\n   Show two or three inputs with their sha256 and status as evidence, verbatim from the\n   record. Never round a `broken` or `unverified` input into \"mostly fine\".\n\n5. **Only if the user asks whether the outputs are still the ones the run produced**, run\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fspur_trace.py\" verify analysis\u002Fspur\u002F\u003CrunId>\n   ```\n\n   Exit `0` every final output matches its recorded hash; `3` names each `DRIFT` file. Drift\n   after the run is not a chain break — the run was fine, the files changed since.\n\n## What the record holds, and what it does not\n\n- **Recorded:** argv of every process, the project's own function calls (code under the\n  root; the interpreter, site-packages and the tracer itself are excluded), sha256 of every\n  data file read and written, the code files it loaded (hashed, kept out of the chain),\n  renames and removals.\n- **Never recorded:** environment values, file contents, anything under the home directory\n  in readable form (it becomes `~`). The raw per-process fragments hold absolute paths and\n  are deleted after the merge unless `--keep-fragments` is passed.\n- **Not observable:** a process started with `python -I`\u002F`-E`, or given its own `env=`\n  without `PYTHONPATH`, and any non-Python program. Each still appears as an untraced step.\n","Record one run of the pipeline as it actually happened. This skill changes no source\nfile: the tracer is loaded beside the program, never into it.\n\nThe rule above the others: **the traced run must behave exactly like an untraced one.**\nIf a traced run fails where a plain run succeeds, stop and report it as a spur defect —\ndo not work around it by editing the project.\n\n## Steps\n\n1. **Detect the stack.**\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fspur_trace.py\" detect\n   ```\n\n   Exit `0` names each stack found and the adapter it gets; exit `4` found none. Python is\n   traced in-process. Rust, Node and Go have no in-process adapter: read\n   [`references\u002Fadapters.md`](..\u002F..\u002Freferences\u002Fadapters.md) before tracing one, and say\n   to the user which parts of the record will be missing.\n\n2. **Find the one command that runs the pipeline**, in this order: a documented pipeline\n   command in the README, a `Makefile`\u002F`justfile` target, a driver script, the test suite\n   (`pytest`, `cargo test`, `npm test`). Ask the user only when none of these names it.\n   One command, run once: every step must be a process that command starts.\n\n3. **Run it under the tracer** from the project root.\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fspur_trace.py\" run -- \u003Ccommand> [args...]\n   ```\n\n   Exit codes, which decide the next step:\n\n   | exit | meaning | next |\n   |---|---|---|\n   | `0` | the command succeeded and every link verified | step 4 |\n   | `3` | a link is **broken**: a file changed between producer and consumer | step 4, lead with it |\n   | `4` | incomplete (an input is unverified) or empty (no step read another's output) | step 4; never call it a pass |\n   | `2` | usage or instrument error | fix the invocation, rerun step 3 |\n   | other | the command's own exit code: the pipeline failed | step 4, lead with the failing step |\n\n   On stderr it prints the summary and the run directory:\n\n   ```text\n   spur: 6 step(s), chain broken (2 verified, 1 broken, 1 unverified, 1 source)\n   spur: wrote analysis\u002Fspur\u002F20261030T183037Z\u002F{trace.json,prov.json,spur-report.html}\n   ```\n\n4. **Report from `trace.json`, not from memory.** Read\n   `analysis\u002Fspur\u002F\u003CrunId>\u002Ftrace.json` (the format is in\n   [`references\u002Ftrace-format.md`](..\u002F..\u002Freferences\u002Ftrace-format.md)) and tell the user:\n   - the chain verdict in one sentence, naming each `broken` input as\n     `producer → path@version → consumer` with its `note` (it names any untraced step that\n     ran in between);\n   - every `unverified` input, and every untraced step with its `why`;\n   - any step whose `exit.code` is non-zero, and the run's `dropped` count if it is not 0;\n   - the path of `spur-report.html` to open, and `prov.json` for PROV tools.\n\n   Show two or three inputs with their sha256 and status as evidence, verbatim from the\n   record. Never round a `broken` or `unverified` input into \"mostly fine\".\n\n5. **Only if the user asks whether the outputs are still the ones the run produced**, run\n\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fspur_trace.py\" verify analysis\u002Fspur\u002F\u003CrunId>\n   ```\n\n   Exit `0` every final output matches its recorded hash; `3` names each `DRIFT` file. Drift\n   after the run is not a chain break — the run was fine, the files changed since.\n\n## What the record holds, and what it does not\n\n- **Recorded:** argv of every process, the project's own function calls (code under the\n  root; the interpreter, site-packages and the tracer itself are excluded), sha256 of every\n  data file read and written, the code files it loaded (hashed, kept out of the chain),\n  renames and removals.\n- **Never recorded:** environment values, file contents, anything under the home directory\n  in readable form (it becomes `~`). The raw per-process fragments hold absolute paths and\n  are deleted after the merge unless `--keep-fragments` is passed.\n- **Not observable:** a process started with `python -I`\u002F`-E`, or given its own `env=`\n  without `PYTHONPATH`, and any non-Python program. Each still appears as an untraced step.\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fspur\u002Fskills\u002Fspur-trace",0,"https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff","https:\u002F\u002Fanselmoo.github.io\u002Fwerkstoff\u002F","https:\u002F\u002Fgithub.com\u002FAnselmoo","Likes to Develop","2026-11-02 04:20:59",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Anselmoo\u002Fwerkstoff --skill spur-trace",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill spur-trace",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill spur-trace","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fspur\u002Fskills\u002Fspur-trace\u002FSKILL.md",true,[],[48,55,62,67,72,77],{"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},"01M79AJTRBNBX03WWKYJ8ENM45","toy-check","A skill that checks things in the repository and reports what it finds.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fworkflows\u002Ffixtures\u002Ftoy-plugin\u002Fskills\u002Ftoy-check\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},"01M79AJS292F3HTDRXWZVRSN5B","demo-check","Reports which generated files changed since the last generation run. Use when the user asks what drifted. Read-only; never edits a file.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-uncompleted-run\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":63,"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":64,"categories":65,"keywords":66,"publishedAt":19},"01M79AJP4TFQXKT1AAK1WC1JYK","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-stale-lock\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":68,"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":69,"categories":70,"keywords":71,"publishedAt":19},"01M79AJM6Y50WP3G2BR4H0M60Z","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-preflight-mixed\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":73,"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":74,"categories":75,"keywords":76,"publishedAt":19},"01M79AJGR6DMT8KCCK071V78XM","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-hooks-shape\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79AJBJ4CHC4PZVWKERWF3HF","zirkel-verify-assumptions","Checks exactly ONE named assumption against real evidence in at most 3 steps and reports one outcome: confidence raised (>=90), reading changed, or still unresolved. Use to resolve a single load-bearing uncertainty — typically a blocking entry surfaced by zirkel-clarify-scope: \"verify this one assumption\", \"is it actually true that X\", \"check this before we rely on it\". For multiple uncertainties, invoke once per uncertainty — the step budget is never shared.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzirkel\u002Fskills\u002Fzirkel-verify-assumptions\u002FSKILL.md",[],[]]