[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77XVQYAF4VPXFS47QG2SRCF":3,"skill-same:01M77XVQYAF4VPXFS47QG2SRCF":52},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M77XVQYAF4VPXFS47QG2SRCF","run-sortify",null,"Run, start, launch, drive, screenshot or smoke-test Sortify (Smart AutoSorter AI Pro) - the Textual TUI and the smart-autosorter CLI (sort, scan, undo, dry-run). Use to see a UI or sorting change working in the real app, not just in pytest.","fderuiter\u002Fsortify","fderuiter","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F127706008?v=4","01M6C40AWP9EPQBS3EG0RF5DRD","Frederick de Ruiter","01M77XTFJ8Z9PYD53GSE5XHS2P",1,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-sortify\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run-sortify\ndescription: Run, start, launch, drive, screenshot or smoke-test Sortify (Smart AutoSorter AI Pro) - the Textual TUI and the smart-autosorter CLI (sort, scan, undo, dry-run). Use to see a UI or sorting change working in the real app, not just in pytest.\n---\n\n# Run Sortify\n\nSortify is a Python 3.12 file organizer with two user surfaces: the\n`smart-autosorter` CLI (headless `sort`\u002F`scan`\u002F`undo`) and a Textual TUI\n(`app\u002Fui\u002Ftui.py`). The agent path for the TUI is\n`.agents\u002Fskills\u002Frun-sortify\u002Fdriver.py`: it boots `AutoSorterTUI` under\nTextual's Pilot (no TTY), in a throwaway app dir + `HOME`, against a\ngenerated 8-file corpus, and takes key presses \u002F screenshots \u002F tree dumps\nas commands. The CLI is driven directly.\n\nAll paths are relative to the repo root. Verified on Linux (Ubuntu\ncontainer), Python 3.12.13 via uv, Textual 8.2.8.\n\n## Prerequisites\n\n`uv` on PATH. Nothing from apt was needed. PNG screenshots use the\npre-installed Chromium at `\u002Fopt\u002Fpw-browsers\u002Fchromium-1194\u002Fchrome-linux\u002Fchrome`\n(falls back to `chromium` on PATH; without either you still get the SVG).\n\n## Build\n\n```bash\nuv sync --frozen --all-groups   # ~15s; Python 3.12 is fetched by uv per .python-version\n```\n\nUse `--all-groups`, as CI does: a plain `uv sync` leaves out test plugins,\nand about 60 async tests then fail with \"async def functions are not\nnatively supported\". The `[ml]` extra (torch, easyocr, llama-cpp...) is not needed: ML imports\nare lazy and TF-IDF clustering works without it.\n\n## Run the TUI (agent path)\n\nOne-shot, commands as `-c` flags (stderr is keyring noise, drop it):\n\n```bash\nuv run python .agents\u002Fskills\u002Frun-sortify\u002Fdriver.py \\\n  -c \"press ctrl+s\" -c \"idle\" -c \"tree\" -c \"press down down\" -c \"ss planned\" \\\n  -c \"press ctrl+e\" -c \"idle\" -c \"screen\" -c \"ss executed\" -c \"files\" 2>\u002Fdev\u002Fnull\n```\n\nThat is the full user flow: scan (Ctrl+S) and plan the corpus into `Budget-Balance\u002F` and\n`Cluster-Backend\u002F`, show it in the tree, execute the moves (Ctrl+E), land\non the `AuditReportModal` with 8 `[PASS]` rows, and list the moved files.\nScreenshots go to `.sortify-driver\u002F\u003Cname>.svg` + `.png` (gitignored).\n**Look at the PNG** with the Read tool.\n\nCommands (`--script FILE` for a file of them, or pipe on stdin for a REPL):\n\n| Command | Does |\n|---|---|\n| `press KEY...` | Textual key names: `ctrl+s`, `ctrl+e`, `ctrl+o`, `down`, `enter`, `escape`, `G` |\n| `type TEXT` | type literal characters into the focused widget |\n| `click SELECTOR` | click by CSS selector, e.g. `#btn-execute` |\n| `idle [SECS]` | wait for all workers (scan\u002Fexecute run in threads) |\n| `wait SECS` | let the app run |\n| `ss NAME` | screenshot to `.sortify-driver\u002FNAME.{svg,png}` |\n| `tree` \u002F `plan` \u002F `screen` \u002F `files` | dump plan tree, `app.plan` JSON, active screen + focus + status bar, target dir |\n| `eval PY` | eval\u002Fexec with `app`, `pilot`, `target` in scope |\n\nOptions: `--dir PATH` (sort your own folder - it **moves files** on\n`ctrl+e`), `--width\u002F--height` (default 120x36), `--out DIR`,\n`--keep-state` (reuse the caller's `AUTOSORTER_APP_DIR`\u002F`HOME`).\n\nREPL mode under tmux, for poking around interactively:\n\n```bash\ntmux new-session -d -s drv -x 200 -y 50 \"uv run python .agents\u002Fskills\u002Frun-sortify\u002Fdriver.py 2>\u002Fdev\u002Fnull\"\nuntil tmux capture-pane -t drv -p | grep -q \"sortify>\"; do sleep 1; done\ntmux send-keys -t drv \"press ctrl+f\" Enter \"type fin 2\" Enter \"eval app.query_one('#tree-search-input').value\" Enter\ntmux send-keys -t drv \"press ctrl+o\" Enter \"screen\" Enter \"ss settings\" Enter\nuntil tmux capture-pane -t drv -p | grep -q \"saved\"; do sleep 1; done\ntmux capture-pane -t drv -p | grep -v '^$' | tail\ntmux send-keys -t drv \"quit\" Enter\n```\n\n## Run the real TUI binary in tmux\n\nUse this when the bug might be in startup\u002Fargument handling rather than in\n`AutoSorterTUI` itself. Ctrl+S should show `Budget-Balance` and\n`Cluster-Backend` in the tree; `C-e` then moves the files:\n\n```bash\nD=$(mktemp -d); mkdir $D\u002Finbox; for i in 1 2 3 4; do\n  echo \"Quarterly revenue budget invoice tax ledger profit expense accounting balance sheet fiscal report $i\" > $D\u002Finbox\u002Ffin$i.txt\n  echo \"Python kubernetes docker server deployment API database backend microservice cluster code $i\" > $D\u002Finbox\u002Ftech$i.txt; done\ntmux new-session -d -s sortify -x 120 -y 36 \\\n  \"AUTOSORTER_APP_DIR=$D\u002Fapp uv run smart-autosorter sort $D\u002Finbox --tui --skip-wizard --accept-ai-consent; sleep 600\"\nsleep 8; tmux send-keys -t sortify C-s; sleep 10\ntmux capture-pane -t sortify -p | head -25\ntmux kill-session -t sortify\n```\n\n## Run the CLI\n\nReuses the `$D\u002Finbox` corpus from the block above:\n\n```bash\nexport AUTOSORTER_APP_DIR=$D\u002Fapp        # always isolate state\nuv run smart-autosorter sort $D\u002Finbox --dry-run --json --accept-ai-consent --non-interactive 2>\u002Fdev\u002Fnull > $D\u002Fplan.json\nuv run smart-autosorter sort $D\u002Finbox --accept-ai-consent --non-interactive   # really moves files\nuv run smart-autosorter undo --list\nuv run smart-autosorter undo --latest   # \"Rollback completed successfully for session ...\"\n```\n\nThe `--json` output has keys `status, dry_run, target_directory,\ndestination_directory, plan`; stdout is clean JSON when stderr is\nredirected. A sort of the 8-file corpus takes ~13s.\n\n## Test\n\n```bash\nuv run pytest -m \"not slow\" -n auto tests\u002F -q  # what CI runs; ~5 min\nuv run pytest tests\u002Ftest_visual_snapshots.py   # TUI SVG snapshots (slow marker)\n```\n\n## Gotchas\n\n- **Clustering spawns a subprocess, which breaks inside Textual** unless\n  multiprocessing's resource tracker is started before Textual replaces\n  `sys.stderr`: `ValueError: bad value(s) in fds_to_keep` in\n  `autosorter.log`, a `{}` plan, and an \"Empty Workspace\" tree while the\n  status bar says \"Analyzed 8 files\". `run_tui` starts the tracker (#792);\n  the driver does the same before `run_test()`. If you see that symptom,\n  grep `autosorter.log` for `fds_to_keep`.\n- Ctrl+S runs `MetadataPass` first; files it routes by rule (keywords,\n  extensions) skip text extraction, and the rest go through\n  `build_corpus_generator` + `partial_fit` (`run_scan_worker` in\n  `app\u002Fui\u002Ftui.py`), the same as CLI `sort`.\n- **Never redirect stderr of the real TUI** (`2>file`): Textual draws to\n  stderr, so the whole UI goes into the file and tmux shows raw escapes.\n- **State leaks across runs.** Sessions live under `AUTOSORTER_APP_DIR`\n  (default `~\u002F.autosorter`); key files go to `~\u002F.sortify\u002Fkeys` regardless.\n  A crashed or killed sort shows up as \"Interrupted Session Detected\" on\n  the next TUI start. The driver isolates both by\n  default; for the CLI set `AUTOSORTER_APP_DIR` (and `HOME`) to a temp dir.\n- Textual SVGs pull Fira Code from cdnjs, which the container proxy\n  blocks; the PNG renders with a fallback monospace font. Proxy\n  \"connect_rejected\" notices for cdnjs\u002Fgoogle during `ss` are that, harmless.\n- **No OS keyring in the container**: every DB open logs \"Keyring lookup\n  failed ... No recommended backend\" to stderr. Harmless; keys fall back to\n  files. That is why the commands above use `2>\u002Fdev\u002Fnull`.\n- **`undo` leaves the empty generated folders behind**; only files move back.\n- After Ctrl+E the TUI rescans the now-sorted folder, so the status bar\n  shows the scan message, not the move result. Check `files` or the modal.\n\n## Troubleshooting\n\n| Symptom | Fix |\n|---|---|\n| tmux pane full of `[?1049h[48;5;17m...` | you redirected stderr of the TUI; remove `2>` |\n| Tree shows \"Empty Workspace\" after `press ctrl+s` + `idle` | `fds_to_keep` in `autosorter.log` (resource tracker not pre-started), or fewer than 3 text files in `--dir` |\n| ~60 async tests fail with \"async def functions are not natively supported\" | `uv sync --frozen --all-groups` |\n| `ss` prints \"png conversion failed\" | no Chromium found; open the `.svg` instead |\n| Startup shows \"Interrupted Session Detected\" | stale `AUTOSORTER_APP_DIR`; use a fresh one (driver default) |\n","# Run Sortify\n\nSortify is a Python 3.12 file organizer with two user surfaces: the\n`smart-autosorter` CLI (headless `sort`\u002F`scan`\u002F`undo`) and a Textual TUI\n(`app\u002Fui\u002Ftui.py`). The agent path for the TUI is\n`.agents\u002Fskills\u002Frun-sortify\u002Fdriver.py`: it boots `AutoSorterTUI` under\nTextual's Pilot (no TTY), in a throwaway app dir + `HOME`, against a\ngenerated 8-file corpus, and takes key presses \u002F screenshots \u002F tree dumps\nas commands. The CLI is driven directly.\n\nAll paths are relative to the repo root. Verified on Linux (Ubuntu\ncontainer), Python 3.12.13 via uv, Textual 8.2.8.\n\n## Prerequisites\n\n`uv` on PATH. Nothing from apt was needed. PNG screenshots use the\npre-installed Chromium at `\u002Fopt\u002Fpw-browsers\u002Fchromium-1194\u002Fchrome-linux\u002Fchrome`\n(falls back to `chromium` on PATH; without either you still get the SVG).\n\n## Build\n\n```bash\nuv sync --frozen --all-groups   # ~15s; Python 3.12 is fetched by uv per .python-version\n```\n\nUse `--all-groups`, as CI does: a plain `uv sync` leaves out test plugins,\nand about 60 async tests then fail with \"async def functions are not\nnatively supported\". The `[ml]` extra (torch, easyocr, llama-cpp...) is not needed: ML imports\nare lazy and TF-IDF clustering works without it.\n\n## Run the TUI (agent path)\n\nOne-shot, commands as `-c` flags (stderr is keyring noise, drop it):\n\n```bash\nuv run python .agents\u002Fskills\u002Frun-sortify\u002Fdriver.py \\\n  -c \"press ctrl+s\" -c \"idle\" -c \"tree\" -c \"press down down\" -c \"ss planned\" \\\n  -c \"press ctrl+e\" -c \"idle\" -c \"screen\" -c \"ss executed\" -c \"files\" 2>\u002Fdev\u002Fnull\n```\n\nThat is the full user flow: scan (Ctrl+S) and plan the corpus into `Budget-Balance\u002F` and\n`Cluster-Backend\u002F`, show it in the tree, execute the moves (Ctrl+E), land\non the `AuditReportModal` with 8 `[PASS]` rows, and list the moved files.\nScreenshots go to `.sortify-driver\u002F\u003Cname>.svg` + `.png` (gitignored).\n**Look at the PNG** with the Read tool.\n\nCommands (`--script FILE` for a file of them, or pipe on stdin for a REPL):\n\n| Command | Does |\n|---|---|\n| `press KEY...` | Textual key names: `ctrl+s`, `ctrl+e`, `ctrl+o`, `down`, `enter`, `escape`, `G` |\n| `type TEXT` | type literal characters into the focused widget |\n| `click SELECTOR` | click by CSS selector, e.g. `#btn-execute` |\n| `idle [SECS]` | wait for all workers (scan\u002Fexecute run in threads) |\n| `wait SECS` | let the app run |\n| `ss NAME` | screenshot to `.sortify-driver\u002FNAME.{svg,png}` |\n| `tree` \u002F `plan` \u002F `screen` \u002F `files` | dump plan tree, `app.plan` JSON, active screen + focus + status bar, target dir |\n| `eval PY` | eval\u002Fexec with `app`, `pilot`, `target` in scope |\n\nOptions: `--dir PATH` (sort your own folder - it **moves files** on\n`ctrl+e`), `--width\u002F--height` (default 120x36), `--out DIR`,\n`--keep-state` (reuse the caller's `AUTOSORTER_APP_DIR`\u002F`HOME`).\n\nREPL mode under tmux, for poking around interactively:\n\n```bash\ntmux new-session -d -s drv -x 200 -y 50 \"uv run python .agents\u002Fskills\u002Frun-sortify\u002Fdriver.py 2>\u002Fdev\u002Fnull\"\nuntil tmux capture-pane -t drv -p | grep -q \"sortify>\"; do sleep 1; done\ntmux send-keys -t drv \"press ctrl+f\" Enter \"type fin 2\" Enter \"eval app.query_one('#tree-search-input').value\" Enter\ntmux send-keys -t drv \"press ctrl+o\" Enter \"screen\" Enter \"ss settings\" Enter\nuntil tmux capture-pane -t drv -p | grep -q \"saved\"; do sleep 1; done\ntmux capture-pane -t drv -p | grep -v '^$' | tail\ntmux send-keys -t drv \"quit\" Enter\n```\n\n## Run the real TUI binary in tmux\n\nUse this when the bug might be in startup\u002Fargument handling rather than in\n`AutoSorterTUI` itself. Ctrl+S should show `Budget-Balance` and\n`Cluster-Backend` in the tree; `C-e` then moves the files:\n\n```bash\nD=$(mktemp -d); mkdir $D\u002Finbox; for i in 1 2 3 4; do\n  echo \"Quarterly revenue budget invoice tax ledger profit expense accounting balance sheet fiscal report $i\" > $D\u002Finbox\u002Ffin$i.txt\n  echo \"Python kubernetes docker server deployment API database backend microservice cluster code $i\" > $D\u002Finbox\u002Ftech$i.txt; done\ntmux new-session -d -s sortify -x 120 -y 36 \\\n  \"AUTOSORTER_APP_DIR=$D\u002Fapp uv run smart-autosorter sort $D\u002Finbox --tui --skip-wizard --accept-ai-consent; sleep 600\"\nsleep 8; tmux send-keys -t sortify C-s; sleep 10\ntmux capture-pane -t sortify -p | head -25\ntmux kill-session -t sortify\n```\n\n## Run the CLI\n\nReuses the `$D\u002Finbox` corpus from the block above:\n\n```bash\nexport AUTOSORTER_APP_DIR=$D\u002Fapp        # always isolate state\nuv run smart-autosorter sort $D\u002Finbox --dry-run --json --accept-ai-consent --non-interactive 2>\u002Fdev\u002Fnull > $D\u002Fplan.json\nuv run smart-autosorter sort $D\u002Finbox --accept-ai-consent --non-interactive   # really moves files\nuv run smart-autosorter undo --list\nuv run smart-autosorter undo --latest   # \"Rollback completed successfully for session ...\"\n```\n\nThe `--json` output has keys `status, dry_run, target_directory,\ndestination_directory, plan`; stdout is clean JSON when stderr is\nredirected. A sort of the 8-file corpus takes ~13s.\n\n## Test\n\n```bash\nuv run pytest -m \"not slow\" -n auto tests\u002F -q  # what CI runs; ~5 min\nuv run pytest tests\u002Ftest_visual_snapshots.py   # TUI SVG snapshots (slow marker)\n```\n\n## Gotchas\n\n- **Clustering spawns a subprocess, which breaks inside Textual** unless\n  multiprocessing's resource tracker is started before Textual replaces\n  `sys.stderr`: `ValueError: bad value(s) in fds_to_keep` in\n  `autosorter.log`, a `{}` plan, and an \"Empty Workspace\" tree while the\n  status bar says \"Analyzed 8 files\". `run_tui` starts the tracker (#792);\n  the driver does the same before `run_test()`. If you see that symptom,\n  grep `autosorter.log` for `fds_to_keep`.\n- Ctrl+S runs `MetadataPass` first; files it routes by rule (keywords,\n  extensions) skip text extraction, and the rest go through\n  `build_corpus_generator` + `partial_fit` (`run_scan_worker` in\n  `app\u002Fui\u002Ftui.py`), the same as CLI `sort`.\n- **Never redirect stderr of the real TUI** (`2>file`): Textual draws to\n  stderr, so the whole UI goes into the file and tmux shows raw escapes.\n- **State leaks across runs.** Sessions live under `AUTOSORTER_APP_DIR`\n  (default `~\u002F.autosorter`); key files go to `~\u002F.sortify\u002Fkeys` regardless.\n  A crashed or killed sort shows up as \"Interrupted Session Detected\" on\n  the next TUI start. The driver isolates both by\n  default; for the CLI set `AUTOSORTER_APP_DIR` (and `HOME`) to a temp dir.\n- Textual SVGs pull Fira Code from cdnjs, which the container proxy\n  blocks; the PNG renders with a fallback monospace font. Proxy\n  \"connect_rejected\" notices for cdnjs\u002Fgoogle during `ss` are that, harmless.\n- **No OS keyring in the container**: every DB open logs \"Keyring lookup\n  failed ... No recommended backend\" to stderr. Harmless; keys fall back to\n  files. That is why the commands above use `2>\u002Fdev\u002Fnull`.\n- **`undo` leaves the empty generated folders behind**; only files move back.\n- After Ctrl+E the TUI rescans the now-sorted folder, so the status bar\n  shows the scan message, not the move result. Check `files` or the modal.\n\n## Troubleshooting\n\n| Symptom | Fix |\n|---|---|\n| tmux pane full of `[?1049h[48;5;17m...` | you redirected stderr of the TUI; remove `2>` |\n| Tree shows \"Empty Workspace\" after `press ctrl+s` + `idle` | `fds_to_keep` in `autosorter.log` (resource tracker not pre-started), or fewer than 3 text files in `--dir` |\n| ~60 async tests fail with \"async def functions are not natively supported\" | `uv sync --frozen --all-groups` |\n| `ss` prints \"png conversion failed\" | no Chromium found; open the `.svg` instead |\n| Startup shows \"Interrupted Session Detected\" | stale `AUTOSORTER_APP_DIR`; use a fresh one (driver default) |\n",{"name":5,"description":7},"main","b644650dc64859af9e971e948b8ac5c45ec8c4c2",".agents\u002Fskills\u002Frun-sortify",0,"https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify","https:\u002F\u002Fgithub.com\u002Ffderuiter","Clinical Data Specialist at @Bright-Research \r\n\r\nInterests in Photogrammetry, Data Analytics + Pipelines, Mathematics, and AI\u002FML.\r\n\r\nPython, Rust, TS.","2026-11-15 04:49:18",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add fderuiter\u002Fsortify --skill run-sortify",{"tool":38,"command":39},"bunx","bunx skills add fderuiter\u002Fsortify --skill run-sortify",{"tool":41,"command":42},"pnpm","pnpm dlx skills add fderuiter\u002Fsortify --skill run-sortify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-sortify\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"driver.py","SCRIPT","脚本",8801,"https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frun-sortify\u002Fdriver.py",[53,61,68,75,82,89],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M77XWVRSTFGKD6NBPD65PWBZ","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","MIT","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-shape\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":57,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M77XWTDXNRHN5RZWGAKGW34D","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-fragments\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":57,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M77XWRJBGHDR198QMFE3E778","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-for-agents\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":57,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M77XWPX0G5Y06DTEYN10F5WQ","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-beats\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":57,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M77XWM148XMNZ39ARDVZ0HTX","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":57,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M77XWGPQP0AJK8XXZTS1NSKF","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Ffderuiter\u002Fsortify\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]