[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EV9MFE63B9KQM9SS7VFDNT":3,"skill-same:01M7EV9MFE63B9KQM9SS7VFDNT":46},{"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":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EV9MFE63B9KQM9SS7VFDNT","database-update",null,"Update a stored object in the lmfdb database by pulling it into Magma, applying user-specified recomputations or field changes, and writing it back. Use whenever the user wants to update a DB entry (e.g. relabel, enrich a field, recompute an invariant) without rerunning the full make script.","tdupu\u002Fagent-skills-public","tdupu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3440403?v=4","01M7EV32X9J0EFE5T4P8TKQTCQ","Taylor Dupuy","01M7EV32XZ1Z4MDBYAFRCJD3BP",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fdatabase-update\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: database-update\ndescription: Update a stored object in the lmfdb database by pulling it into Magma, applying user-specified recomputations or field changes, and writing it back. Use whenever the user wants to update a DB entry (e.g. relabel, enrich a field, recompute an invariant) without rerunning the full make script.\n---\n\n# database-update\n\n## Dependency check\n\n```bash\n# Discover conf: project root first, hecke fallback\nCONF=\"\"\nfor candidate in \\\n    \"$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)\u002Flmfdb-pipeline.conf\" \\\n    \"magma\u002Fscripts\u002Fdata-generation.conf\"; do\n  [ -f \"$candidate\" ] && { CONF=\"$candidate\"; break; }\ndone\nif [ -z \"$CONF\" ]; then\n  echo \"I'm sorry, I can't do that — no database pipeline conf found.\"\n  echo \"Run \u002Fconfigure-database (mathcity-lmfdb.configure-database) to create lmfdb-pipeline.conf at your project root.\"\n  echo \"(This conf holds your PostgreSQL and DATA_DIR settings for the LMFDB pipeline.)\"\n  exit 1\nfi\nsource \"$CONF\"\n```\n\n```magma\nZ := Integers(); Q := Rationals();\nAttachSpec(\"hecke.spec\");\nSetLMFDBRootFolder(\".\");\n\ndb := OpenDB(\"clifford_bianchi_local\");\n\n\u002F\u002F Lookup → mutate → upsert:\nX := LookUpLMFDB(db, \"LMFDBCliffOrd\", \"2.1.m4.1.2.1.1.2.1.1\");\nX`timing := Sprintf(\"%o\", Cputime());\nAddLMFDB(db, \"LMFDBCliffOrd\", [X] : overwrite := true);\n\n\u002F\u002F Generic (Assoc-level) update:\nq := AssociativeArray(); q[\"label\"] := \"2.1.m4.1.2.1.1.2.1.1\";\nchanges := AssociativeArray(); changes[\"timing\"] := \"123.4\";\nUpdate(db, \"clifford_orders\", q, changes);\n\n\u002F\u002F Batch update via SearchLMFDB:\nq := AssociativeArray(); q[\"order\"] := \"2.1.m4.1.2.1.1.2.1.1\";\nobjs := SearchLMFDB(db, \"LMFDBPSL2GrpCliffSub\", q);\nfor X in objs do\n    X`timing := Sprintf(\"%o\", Cputime());\n    AddLMFDB(db, \"LMFDBPSL2GrpCliffSub\", [X] : overwrite := true);\nend for;\n```\n\nNote: `AddLMFDB` requires `overwrite := true` when the label already exists. Default `overwrite := false` will error if the label is already in the table.\n\n## Legacy approach (pre-package-textfiles \u002F pre-package-database)\n\n**Purpose:** Round-trip pipeline for updating a stored object:\n\n```\nlmfdb.* → pipe string → LMFDBXxx → native Magma object\n                                          ↓\n                              [user-specified update commands]\n                                          ↓\n                          LMFDBXxx → lmfdb.* (or DATA\u002F file)\n```\n\nThis composes:\n`\u002Fdatabase-to-lmfdb-object` → `\u002Flmfdb-object-to-magma` → [updates] →\n`\u002Fmagma-to-lmfdb-object` → `\u002Flmfdb-object-to-database`\n\n(Or replace the last step with `\u002Flmfdb-object-to-textfile` + `\u002Ftextfile-to-database` to also\narchive to DATA\u002F.)\n\n### Step 1 — Pull the object from the database\n\nUse `\u002Fdatabase-to-lmfdb-object` to query and deserialize. Example for an order:\n\n```magma\nZ := Integers(); Q := Rationals();\nAttachSpec(\"..\u002Fhecke.spec\");\nSetLMFDBRootFolder(\"..\");\n\n\u002F\u002F Emit pipe string from DB (run beforehand):\n\u002F\u002F   psql clifford_bianchi_local -t -A -F '|' --null='\\N' -c \"\n\u002F\u002F       SELECT basis, clifford_algebra, dimension, discriminant,\n\u002F\u002F              is_maximal, is_norm_euclidean, is_star_invariant, label, timing\n\u002F\u002F       FROM lmfdb.clifford_orders WHERE label = '\u003Clabel>'\n\u002F\u002F   \" > \u002Ftmp\u002Fdb_update_obj.txt\n\nline := [H : H in Split(Read(\"\u002Ftmp\u002Fdb_update_obj.txt\"), \"\\n\") | #H gt 0][1];\nX    := load_lmfdb_clifford_order(line);   \u002F\u002F → LMFDBCliffOrd\n```\n\nFor other object types, use `load_lmfdb_sl2`, `load_lmfdb_gamma0`, or\n`load_lmfdb_psl2_grp_cliff_sub` with the corresponding SELECT from the right table.\n\n### Step 2 — Restore the native Magma object\n\nUse `\u002Flmfdb-object-to-magma`:\n\n```magma\nO := clifford_order(X);                   \u002F\u002F LMFDBCliffOrd → CliffOrd\n\u002F\u002F PSL2O := clifford_bianchi_group(X`label);  \u002F\u002F LMFDBGrpSL2Cliff → GrpPSL2Cliff\n```\n\n### Step 3 — Apply update commands\n\nThis is the user-specified step. State clearly what is being recomputed or changed.\n\n**Common pattern: relabel (compute new LMFDB label)**\n```magma\nold_label := X`label;\nnew_label := get_label(O);               \u002F\u002F default method := \"lmfdb\"\nX`label   := new_label;\nprintf \"label map: %o -> %o\\n\", old_label, new_label;\n```\n\n**Common pattern: update a scalar field**\n```magma\nX`timing := Sprintf(\"%o\", Cputime(T0));\n```\n\n**Common pattern: recompute a jsonb field from the native object**\n```magma\nX`basis := SaveJsonb(jsonify_order_basis(O));\n```\n\n**If the native object itself needs recomputation** (e.g. re-running a make step):\n```magma\nT0 := Cputime();\n\u002F\u002F ... expensive recomputation ...\nX_new := create_lmfdb_object(O_new: timing := Sprintf(\"%o\", Cputime(T0)));\n```\n\n### Step 4 — Serialize the updated object\n\nUse `\u002Fmagma-to-lmfdb-object` if you rebuilt the native object, or just update `X`'s attributes\ndirectly (faster for field-only changes):\n\n```magma\nline_new := SaveLMFDBObject(X);\nprint_file(\"\u002Ftmp\u002Fdb_update_obj_new.txt\", line_new: overwrite := true);\n```\n\n### Step 5 — Write back to the database\n\nUse `\u002Flmfdb-object-to-database`:\n\n```bash\ncd magma\u002Fpython\npython3 -c \"\nimport io, db_config\nfrom db_load import ORDERS_ATTRS, _staging_cols, _preprocess_field\n\nline = open('\u002Ftmp\u002Fdb_update_obj_new.txt').read().strip()\n# ... call insert_lmfdb_object(line, 'staging.orders_src', ORDERS_ATTRS)\n\"\npython3 db_migrate.py --action populate_ledger\npython3 db_migrate.py --action promote_to_lmfdb\n```\n\n`promote_to_lmfdb` uses `ON CONFLICT (label) DO UPDATE` — if the label changed (e.g. relabeling),\nthe old label entry remains and a new one is added. To remove the old label entry:\n```sql\nDELETE FROM lmfdb.clifford_orders WHERE label = '\u003Cold_label>';\n-- Do this AFTER updating all FK references (clifford_sl2, clifford_gamma0, clifford_subgroups)\n```\n\n### Optional: also archive to DATA\u002F\n\nIf you want the updated object in both the DB and DATA\u002F:\n```magma\ncl := dejsonify_clifford_algebra(X`clifford_algebra);\nwrite_lmfdb_clifford_order(cl, X: overwrite := false);\n```\n\n### Worked example: relabeling a single order\n\n```magma\n\u002F\u002F 1. Pull from DB (run psql dump first — see Step 1)\nline := [H : H in Split(Read(\"\u002Ftmp\u002Fdb_update_obj.txt\"), \"\\n\") | #H gt 0][1];\nX    := load_lmfdb_clifford_order(line);\nO    := clifford_order(X);\n\n\u002F\u002F 2. Relabel\nold_label := X`label;\nX`label   := get_label(O);\nprintf \"Relabeled: %o -> %o\\n\", old_label, X`label;\n\n\u002F\u002F 3. Serialize\nprint_file(\"\u002Ftmp\u002Fdb_update_obj_new.txt\", SaveLMFDBObject(X): overwrite := true);\n```\n\nThen in Python: load label_map, load new file, promote.\n\n### Object type reference\n\n| Object type | Load intrinsic                   | Native type    | Serialize           |\n|-------------|----------------------------------|----------------|---------------------|\n| order       | `load_lmfdb_clifford_order`      | `CliffOrd`     | `SaveLMFDBObject`   |\n| sl2         | `load_lmfdb_sl2`                 | `GrpPSL2Cliff` | `SaveLMFDBObject`   |\n| gamma0      | `load_lmfdb_gamma0`              | `GrpFP`        | `SaveLMFDBObject`   |\n| subgroup    | `load_lmfdb_psl2_grp_cliff_sub`  | —              | `SaveLMFDBObject`   |\n\n## When to use legacy vs. new\n\nUse the new `LookUpLMFDB` \u002F `AddLMFDB` \u002F `Update` \u002F `SearchLMFDB` API (new) for any update that can be expressed within a single Magma session — it avoids the psql shell round-trip, temp files, and the Python staging pipeline entirely. Fall back to the legacy approach only when you need to recompute a native Magma object mid-pipeline (e.g., a full make-step rerun), when you need to handle FK cleanup after a relabeling, or when batch-promoting via `db_migrate.py` is already part of an existing workflow.\n","# database-update\n\n## Dependency check\n\n```bash\n# Discover conf: project root first, hecke fallback\nCONF=\"\"\nfor candidate in \\\n    \"$(git rev-parse --show-toplevel 2>\u002Fdev\u002Fnull)\u002Flmfdb-pipeline.conf\" \\\n    \"magma\u002Fscripts\u002Fdata-generation.conf\"; do\n  [ -f \"$candidate\" ] && { CONF=\"$candidate\"; break; }\ndone\nif [ -z \"$CONF\" ]; then\n  echo \"I'm sorry, I can't do that — no database pipeline conf found.\"\n  echo \"Run \u002Fconfigure-database (mathcity-lmfdb.configure-database) to create lmfdb-pipeline.conf at your project root.\"\n  echo \"(This conf holds your PostgreSQL and DATA_DIR settings for the LMFDB pipeline.)\"\n  exit 1\nfi\nsource \"$CONF\"\n```\n\n```magma\nZ := Integers(); Q := Rationals();\nAttachSpec(\"hecke.spec\");\nSetLMFDBRootFolder(\".\");\n\ndb := OpenDB(\"clifford_bianchi_local\");\n\n\u002F\u002F Lookup → mutate → upsert:\nX := LookUpLMFDB(db, \"LMFDBCliffOrd\", \"2.1.m4.1.2.1.1.2.1.1\");\nX`timing := Sprintf(\"%o\", Cputime());\nAddLMFDB(db, \"LMFDBCliffOrd\", [X] : overwrite := true);\n\n\u002F\u002F Generic (Assoc-level) update:\nq := AssociativeArray(); q[\"label\"] := \"2.1.m4.1.2.1.1.2.1.1\";\nchanges := AssociativeArray(); changes[\"timing\"] := \"123.4\";\nUpdate(db, \"clifford_orders\", q, changes);\n\n\u002F\u002F Batch update via SearchLMFDB:\nq := AssociativeArray(); q[\"order\"] := \"2.1.m4.1.2.1.1.2.1.1\";\nobjs := SearchLMFDB(db, \"LMFDBPSL2GrpCliffSub\", q);\nfor X in objs do\n    X`timing := Sprintf(\"%o\", Cputime());\n    AddLMFDB(db, \"LMFDBPSL2GrpCliffSub\", [X] : overwrite := true);\nend for;\n```\n\nNote: `AddLMFDB` requires `overwrite := true` when the label already exists. Default `overwrite := false` will error if the label is already in the table.\n\n## Legacy approach (pre-package-textfiles \u002F pre-package-database)\n\n**Purpose:** Round-trip pipeline for updating a stored object:\n\n```\nlmfdb.* → pipe string → LMFDBXxx → native Magma object\n                                          ↓\n                              [user-specified update commands]\n                                          ↓\n                          LMFDBXxx → lmfdb.* (or DATA\u002F file)\n```\n\nThis composes:\n`\u002Fdatabase-to-lmfdb-object` → `\u002Flmfdb-object-to-magma` → [updates] →\n`\u002Fmagma-to-lmfdb-object` → `\u002Flmfdb-object-to-database`\n\n(Or replace the last step with `\u002Flmfdb-object-to-textfile` + `\u002Ftextfile-to-database` to also\narchive to DATA\u002F.)\n\n### Step 1 — Pull the object from the database\n\nUse `\u002Fdatabase-to-lmfdb-object` to query and deserialize. Example for an order:\n\n```magma\nZ := Integers(); Q := Rationals();\nAttachSpec(\"..\u002Fhecke.spec\");\nSetLMFDBRootFolder(\"..\");\n\n\u002F\u002F Emit pipe string from DB (run beforehand):\n\u002F\u002F   psql clifford_bianchi_local -t -A -F '|' --null='\\N' -c \"\n\u002F\u002F       SELECT basis, clifford_algebra, dimension, discriminant,\n\u002F\u002F              is_maximal, is_norm_euclidean, is_star_invariant, label, timing\n\u002F\u002F       FROM lmfdb.clifford_orders WHERE label = '\u003Clabel>'\n\u002F\u002F   \" > \u002Ftmp\u002Fdb_update_obj.txt\n\nline := [H : H in Split(Read(\"\u002Ftmp\u002Fdb_update_obj.txt\"), \"\\n\") | #H gt 0][1];\nX    := load_lmfdb_clifford_order(line);   \u002F\u002F → LMFDBCliffOrd\n```\n\nFor other object types, use `load_lmfdb_sl2`, `load_lmfdb_gamma0`, or\n`load_lmfdb_psl2_grp_cliff_sub` with the corresponding SELECT from the right table.\n\n### Step 2 — Restore the native Magma object\n\nUse `\u002Flmfdb-object-to-magma`:\n\n```magma\nO := clifford_order(X);                   \u002F\u002F LMFDBCliffOrd → CliffOrd\n\u002F\u002F PSL2O := clifford_bianchi_group(X`label);  \u002F\u002F LMFDBGrpSL2Cliff → GrpPSL2Cliff\n```\n\n### Step 3 — Apply update commands\n\nThis is the user-specified step. State clearly what is being recomputed or changed.\n\n**Common pattern: relabel (compute new LMFDB label)**\n```magma\nold_label := X`label;\nnew_label := get_label(O);               \u002F\u002F default method := \"lmfdb\"\nX`label   := new_label;\nprintf \"label map: %o -> %o\\n\", old_label, new_label;\n```\n\n**Common pattern: update a scalar field**\n```magma\nX`timing := Sprintf(\"%o\", Cputime(T0));\n```\n\n**Common pattern: recompute a jsonb field from the native object**\n```magma\nX`basis := SaveJsonb(jsonify_order_basis(O));\n```\n\n**If the native object itself needs recomputation** (e.g. re-running a make step):\n```magma\nT0 := Cputime();\n\u002F\u002F ... expensive recomputation ...\nX_new := create_lmfdb_object(O_new: timing := Sprintf(\"%o\", Cputime(T0)));\n```\n\n### Step 4 — Serialize the updated object\n\nUse `\u002Fmagma-to-lmfdb-object` if you rebuilt the native object, or just update `X`'s attributes\ndirectly (faster for field-only changes):\n\n```magma\nline_new := SaveLMFDBObject(X);\nprint_file(\"\u002Ftmp\u002Fdb_update_obj_new.txt\", line_new: overwrite := true);\n```\n\n### Step 5 — Write back to the database\n\nUse `\u002Flmfdb-object-to-database`:\n\n```bash\ncd magma\u002Fpython\npython3 -c \"\nimport io, db_config\nfrom db_load import ORDERS_ATTRS, _staging_cols, _preprocess_field\n\nline = open('\u002Ftmp\u002Fdb_update_obj_new.txt').read().strip()\n# ... call insert_lmfdb_object(line, 'staging.orders_src', ORDERS_ATTRS)\n\"\npython3 db_migrate.py --action populate_ledger\npython3 db_migrate.py --action promote_to_lmfdb\n```\n\n`promote_to_lmfdb` uses `ON CONFLICT (label) DO UPDATE` — if the label changed (e.g. relabeling),\nthe old label entry remains and a new one is added. To remove the old label entry:\n```sql\nDELETE FROM lmfdb.clifford_orders WHERE label = '\u003Cold_label>';\n-- Do this AFTER updating all FK references (clifford_sl2, clifford_gamma0, clifford_subgroups)\n```\n\n### Optional: also archive to DATA\u002F\n\nIf you want the updated object in both the DB and DATA\u002F:\n```magma\ncl := dejsonify_clifford_algebra(X`clifford_algebra);\nwrite_lmfdb_clifford_order(cl, X: overwrite := false);\n```\n\n### Worked example: relabeling a single order\n\n```magma\n\u002F\u002F 1. Pull from DB (run psql dump first — see Step 1)\nline := [H : H in Split(Read(\"\u002Ftmp\u002Fdb_update_obj.txt\"), \"\\n\") | #H gt 0][1];\nX    := load_lmfdb_clifford_order(line);\nO    := clifford_order(X);\n\n\u002F\u002F 2. Relabel\nold_label := X`label;\nX`label   := get_label(O);\nprintf \"Relabeled: %o -> %o\\n\", old_label, X`label;\n\n\u002F\u002F 3. Serialize\nprint_file(\"\u002Ftmp\u002Fdb_update_obj_new.txt\", SaveLMFDBObject(X): overwrite := true);\n```\n\nThen in Python: load label_map, load new file, promote.\n\n### Object type reference\n\n| Object type | Load intrinsic                   | Native type    | Serialize           |\n|-------------|----------------------------------|----------------|---------------------|\n| order       | `load_lmfdb_clifford_order`      | `CliffOrd`     | `SaveLMFDBObject`   |\n| sl2         | `load_lmfdb_sl2`                 | `GrpPSL2Cliff` | `SaveLMFDBObject`   |\n| gamma0      | `load_lmfdb_gamma0`              | `GrpFP`        | `SaveLMFDBObject`   |\n| subgroup    | `load_lmfdb_psl2_grp_cliff_sub`  | —              | `SaveLMFDBObject`   |\n\n## When to use legacy vs. new\n\nUse the new `LookUpLMFDB` \u002F `AddLMFDB` \u002F `Update` \u002F `SearchLMFDB` API (new) for any update that can be expressed within a single Magma session — it avoids the psql shell round-trip, temp files, and the Python staging pipeline entirely. Fall back to the legacy approach only when you need to recompute a native Magma object mid-pipeline (e.g., a full make-step rerun), when you need to handle FK cleanup after a relabeling, or when batch-promoting via `db_migrate.py` is already part of an existing workflow.\n",{"name":5,"description":7},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Fdatabase-update","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public","https:\u002F\u002Fgithub.com\u002Ftdupu","https:\u002F\u002Ftdupu.github.io\u002Findex.html","Associate Professor, Department of Mathematics and Statistics, University of Vermont --- last updated Fall 2019","2026-11-13 09:07:19",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add tdupu\u002Fagent-skills-public --skill database-update",{"tool":38,"command":39},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill database-update",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill database-update","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fdatabase-update\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EW4PT586KKE7VRCAD80Z9K","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"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},"01M7EW4HV5V74AF3PTV8N4T0PS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-plans\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},"01M7EW4DNKGP5CR1RAJP2J9PHA","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fverification-before-completion\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},"01M7EW4BA2QP88VBFVXDVJM7XQ","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-superpowers\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},"01M7EW47F2JG5FBESDJNP3PKMV","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-git-worktrees\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},"01M7EW44N8556Y556NX9HJT4KP","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]