[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BZRT1WFTJKP0QHFJ9BC43W":3,"skill-same:01M6BZRT1WFTJKP0QHFJ9BC43W":48},{"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":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M6BZRT1WFTJKP0QHFJ9BC43W","session-conversation",null,"Send messages to and receive replies from another active opencode session. Use when orchestrating multi-session dialogues, relaying turns between two sessions, or injecting a user message into a separately running session.","twidxuga\u002Fdotfiles","twidxuga","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12471681?v=4","01M6BZR45BH8JCC79Q9SKSS6SC","Ricardo Santos","01M6BZR49CRKSBZYQD1WNQWCXW",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fsession-conversation\u002FSKILL.md",[],[19,20,21],"session conversation","sessions","messages","2026-11-10 10:12:30",false,"---\nname: session-conversation\ndescription: Send messages to and receive replies from another active opencode session. Use when orchestrating multi-session dialogues, relaying turns between two sessions, or injecting a user message into a separately running session.\n---\n\n# Session Conversation Skill\n\nThis skill enables one opencode session to send messages to and receive replies from another session — enabling inter-session communication, multi-agent dialogues, and cross-session orchestration.\n\n## How It Works\n\nThere are two ways to inject a message into another session. **Pick based on the target's agent:**\n\n| Method | Works with primary agents (e.g. Sisyphus)? | Use when |\n|---|---|---|\n| **A — `task(session_id=...)`** | ❌ No — errors `Cannot delegate to primary agent \"...\" via task` | Target runs a delegatable **subagent** you spawned |\n| **B — opencode web HTTP API** | ✅ Yes — no agent restriction | Target runs **any** agent, including primary Sisyphus (the common case) |\n\nMost interactive sessions run a primary agent (Sisyphus), so **Method B is the default**. Method A is only viable for subagent sessions.\n\nBoth deliver the message as a normal user turn; the target processes it and returns its response. Method B is also cross-project: the opencode web server addresses **every** session by ID regardless of which project directory it lives in.\n\n## Step 1 — Find the Target Session\n\n### Option A: session_list (current project, fast)\n\n```typescript\nsession_list(limit=20)\n```\n\nReturns sessions scoped to the current working directory. Check the title and agent columns to identify the right one.\n\n### Option B: find-session skill (cross-project, SQLite)\n\nLoad the `find-session` skill for cross-project search. Or query directly:\n\n```bash\nsqlite3 ~\u002F.local\u002Fshare\u002Fopencode\u002Fopencode.db \\\n  \"SELECT id, title, directory, datetime(time_updated\u002F1000,'unixepoch') as last_active\n   FROM session\n   ORDER BY time_updated DESC\n   LIMIT 20;\"\n```\n\n### Option C: Verify identity before sending\n\nRead the first few messages to confirm it's the right session:\n\n```typescript\nsession_read(session_id=\"ses_abc123\", limit=5)\n```\n\nCheck the opening messages — the user typically sets the session's role\u002Finstructions there.\n\n## Step 2 — Send a Message\n\n### Method B — opencode web HTTP API (RECOMMENDED; works with Sisyphus)\n\nThe `opencode web` server exposes a REST API that injects a message into any session by ID, with **no primary-agent restriction**. This is how the web UI itself sends messages, so it works for Sisyphus and every other agent.\n\n**1. Find the opencode web server port** (default `4096`; discover if not running there):\n\n```bash\n# Default is 4096. To discover: probe opencode listening ports for the one that serves \u002Fsession.\nPORT=4096\nfor p in 4096 $(lsof -nP -iTCP -sTCP:LISTEN 2>\u002Fdev\u002Fnull | grep -i opencode \\\n      | grep -oE '127\\.0\\.0\\.1:[0-9]+' | cut -d: -f2 | sort -u); do\n  if curl -s -m 2 \"http:\u002F\u002F127.0.0.1:$p\u002Fsession\" | grep -q '\"id\":\"ses_'; then PORT=$p; break; fi\ndone\necho \"opencode web port: $PORT\"\n```\n\n**2. POST the message** — only `parts` is required; the session reuses its own agent + model:\n\n```bash\nSID=ses_abc123\ncurl -s -m 180 -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"Your message here\"}]}'\n```\n\nThe call blocks until the target finishes its turn, then returns the full assistant message as JSON (text is in `.parts[].text`). Extract the reply:\n\n```bash\ncurl -s -m 180 -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"Your message here\"}]}' \\\n  | python3 -c \"import sys,json;print(''.join(p.get('text','') for p in json.load(sys.stdin)['parts'] if p.get('type')=='text'))\"\n```\n\nVerify the target is reachable first with `GET \u002Fsession\u002F$SID` (returns its `title` and `agent`).\n\n### Method A — `task(session_id=...)` (subagent sessions only)\n\nOnly works if the target runs a delegatable subagent. Against a primary agent (Sisyphus) it errors `Cannot delegate to primary agent \"...\" via task`.\n\n```typescript\ntask(\n  session_id=\"ses_abc123\",                  \u002F\u002F target session ID\n  subagent_type=\"Sisyphus (Ultraworker)\",   \u002F\u002F must match the agent in that session\n  load_skills=[],\n  run_in_background=false,                  \u002F\u002F MUST be false — see Limitations\n  description=\"Brief label for this turn\",\n  prompt=\"Your message here\"\n)\n```\n\nThe call blocks until the target session responds. The full response text is returned.\n\n## Step 3 — Continue the Conversation\n\nRepeat the same call with the same `session_id` for each subsequent turn. The session retains full context across calls — no re-introduction needed.\n\n```bash\n# Method B — each POST to the same SID is one more turn; context is preserved\ncurl -s -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"Follow-up based on their reply\"}]}'\n```\n\n## Multi-Session Dialogue Pattern\n\nTo orchestrate a back-and-forth between two independently running sessions (e.g. Bot A and Bot B), the **orchestrating session acts as the relay**:\n\n```\nUser\n └─► Session A (you, the orchestrator)\n       ├─► task(session_id=B) → B replies\n       ├─► formulate A's response\n       ├─► task(session_id=B) → B replies again\n       └─► ... repeat for N turns\n```\n\nEach POST (Method B) or `task()` call (Method A) is one conversational turn. You receive B's reply, generate A's next message, and send it back. Display both sides to the user as you go.\n\n```bash\n# Method B relay — orchestrator drives each turn against Bot B's session\nSID_B=ses_B\nreply=$(curl -s -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID_B\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"\u003CA'\\''s message>\"}]}' \\\n  | python3 -c \"import sys,json;print(''.join(p.get('text','') for p in json.load(sys.stdin)['parts'] if p.get('type')=='text'))\")\n# Show both sides, formulate A's next message from $reply, repeat for N turns\n```\n\n## Limitations\n\n### Method B (HTTP API)\n\n| Limitation | Detail |\n|---|---|\n| Requires `opencode web` running | The REST server must be up (default port `4096`). If no port serves `\u002Fsession`, start it with `opencode web`. |\n| Sequential turns | The POST blocks until the target finishes its turn. No passive push\u002Fsubscribe — drive each turn explicitly. |\n| Local only | Server binds to `127.0.0.1`. Cross-machine is not supported. |\n| Triggers a real turn | The target actually processes the message and incurs cost. Use `\"noReply\": true` in the body to inject a user message without triggering a response. |\n\n### Method A (`task(session_id=...)`)\n\n| Limitation | Detail |\n|---|---|\n| Primary agents blocked | Errors `Cannot delegate to primary agent \"...\" via task`. Sisyphus is primary, so Method A does **not** work for it — use Method B. |\n| `run_in_background=true` fails | Error: \"Task not found for session\". Always use `run_in_background=false`. |\n| `subagent_type` must match | Must match the subagent running in the target session. |\n| Same process only | Both sessions must be running in the same opencode process\u002Finstance. |\n\n## Worked Example (Method B — verified against a live Sisyphus session)\n\n```bash\n# 1. Find the target session (cross-project) via the find-session skill \u002F SQLite\nsqlite3 ~\u002F.local\u002Fshare\u002Fopencode\u002Fopencode.db \\\n  \"SELECT id, title, directory FROM session WHERE title LIKE '%sandbox%' ORDER BY time_updated DESC LIMIT 5;\"\n# → ses_19eab2b32ffe0PftUbk85Lttj7 | sandbox | \u002FUsers\u002Frs\u002FBunch\u002Fcode\u002Fapps\n\n# 2. Find the opencode web port and confirm identity (returns title + agent)\nPORT=4096\nSID=ses_19eab2b32ffe0PftUbk85Lttj7\ncurl -s \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\" | python3 -c \"import sys,json;d=json.load(sys.stdin);print(d['title'],'|',d['agent'])\"\n# → sandbox | Sisyphus - ultraworker   (a PRIMARY agent — task() would refuse this)\n\n# 3. Inject the message — works despite the primary agent\ncurl -s -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"test\"}]}' \\\n  | python3 -c \"import sys,json;print(''.join(p.get('text','') for p in json.load(sys.stdin)['parts'] if p.get('type')=='text'))\"\n# → test   (HTTP 200 — round-trip confirmed)\n\n# 4. Repeat step 3 with the same SID for each further turn; context is preserved.\n```\n\n## Related Skills\n\n- `find-session` — locate sessions across all projects via SQLite when `session_list` is insufficient\n","# Session Conversation Skill\n\nThis skill enables one opencode session to send messages to and receive replies from another session — enabling inter-session communication, multi-agent dialogues, and cross-session orchestration.\n\n## How It Works\n\nThere are two ways to inject a message into another session. **Pick based on the target's agent:**\n\n| Method | Works with primary agents (e.g. Sisyphus)? | Use when |\n|---|---|---|\n| **A — `task(session_id=...)`** | ❌ No — errors `Cannot delegate to primary agent \"...\" via task` | Target runs a delegatable **subagent** you spawned |\n| **B — opencode web HTTP API** | ✅ Yes — no agent restriction | Target runs **any** agent, including primary Sisyphus (the common case) |\n\nMost interactive sessions run a primary agent (Sisyphus), so **Method B is the default**. Method A is only viable for subagent sessions.\n\nBoth deliver the message as a normal user turn; the target processes it and returns its response. Method B is also cross-project: the opencode web server addresses **every** session by ID regardless of which project directory it lives in.\n\n## Step 1 — Find the Target Session\n\n### Option A: session_list (current project, fast)\n\n```typescript\nsession_list(limit=20)\n```\n\nReturns sessions scoped to the current working directory. Check the title and agent columns to identify the right one.\n\n### Option B: find-session skill (cross-project, SQLite)\n\nLoad the `find-session` skill for cross-project search. Or query directly:\n\n```bash\nsqlite3 ~\u002F.local\u002Fshare\u002Fopencode\u002Fopencode.db \\\n  \"SELECT id, title, directory, datetime(time_updated\u002F1000,'unixepoch') as last_active\n   FROM session\n   ORDER BY time_updated DESC\n   LIMIT 20;\"\n```\n\n### Option C: Verify identity before sending\n\nRead the first few messages to confirm it's the right session:\n\n```typescript\nsession_read(session_id=\"ses_abc123\", limit=5)\n```\n\nCheck the opening messages — the user typically sets the session's role\u002Finstructions there.\n\n## Step 2 — Send a Message\n\n### Method B — opencode web HTTP API (RECOMMENDED; works with Sisyphus)\n\nThe `opencode web` server exposes a REST API that injects a message into any session by ID, with **no primary-agent restriction**. This is how the web UI itself sends messages, so it works for Sisyphus and every other agent.\n\n**1. Find the opencode web server port** (default `4096`; discover if not running there):\n\n```bash\n# Default is 4096. To discover: probe opencode listening ports for the one that serves \u002Fsession.\nPORT=4096\nfor p in 4096 $(lsof -nP -iTCP -sTCP:LISTEN 2>\u002Fdev\u002Fnull | grep -i opencode \\\n      | grep -oE '127\\.0\\.0\\.1:[0-9]+' | cut -d: -f2 | sort -u); do\n  if curl -s -m 2 \"http:\u002F\u002F127.0.0.1:$p\u002Fsession\" | grep -q '\"id\":\"ses_'; then PORT=$p; break; fi\ndone\necho \"opencode web port: $PORT\"\n```\n\n**2. POST the message** — only `parts` is required; the session reuses its own agent + model:\n\n```bash\nSID=ses_abc123\ncurl -s -m 180 -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"Your message here\"}]}'\n```\n\nThe call blocks until the target finishes its turn, then returns the full assistant message as JSON (text is in `.parts[].text`). Extract the reply:\n\n```bash\ncurl -s -m 180 -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"Your message here\"}]}' \\\n  | python3 -c \"import sys,json;print(''.join(p.get('text','') for p in json.load(sys.stdin)['parts'] if p.get('type')=='text'))\"\n```\n\nVerify the target is reachable first with `GET \u002Fsession\u002F$SID` (returns its `title` and `agent`).\n\n### Method A — `task(session_id=...)` (subagent sessions only)\n\nOnly works if the target runs a delegatable subagent. Against a primary agent (Sisyphus) it errors `Cannot delegate to primary agent \"...\" via task`.\n\n```typescript\ntask(\n  session_id=\"ses_abc123\",                  \u002F\u002F target session ID\n  subagent_type=\"Sisyphus (Ultraworker)\",   \u002F\u002F must match the agent in that session\n  load_skills=[],\n  run_in_background=false,                  \u002F\u002F MUST be false — see Limitations\n  description=\"Brief label for this turn\",\n  prompt=\"Your message here\"\n)\n```\n\nThe call blocks until the target session responds. The full response text is returned.\n\n## Step 3 — Continue the Conversation\n\nRepeat the same call with the same `session_id` for each subsequent turn. The session retains full context across calls — no re-introduction needed.\n\n```bash\n# Method B — each POST to the same SID is one more turn; context is preserved\ncurl -s -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"Follow-up based on their reply\"}]}'\n```\n\n## Multi-Session Dialogue Pattern\n\nTo orchestrate a back-and-forth between two independently running sessions (e.g. Bot A and Bot B), the **orchestrating session acts as the relay**:\n\n```\nUser\n └─► Session A (you, the orchestrator)\n       ├─► task(session_id=B) → B replies\n       ├─► formulate A's response\n       ├─► task(session_id=B) → B replies again\n       └─► ... repeat for N turns\n```\n\nEach POST (Method B) or `task()` call (Method A) is one conversational turn. You receive B's reply, generate A's next message, and send it back. Display both sides to the user as you go.\n\n```bash\n# Method B relay — orchestrator drives each turn against Bot B's session\nSID_B=ses_B\nreply=$(curl -s -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID_B\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"\u003CA'\\''s message>\"}]}' \\\n  | python3 -c \"import sys,json;print(''.join(p.get('text','') for p in json.load(sys.stdin)['parts'] if p.get('type')=='text'))\")\n# Show both sides, formulate A's next message from $reply, repeat for N turns\n```\n\n## Limitations\n\n### Method B (HTTP API)\n\n| Limitation | Detail |\n|---|---|\n| Requires `opencode web` running | The REST server must be up (default port `4096`). If no port serves `\u002Fsession`, start it with `opencode web`. |\n| Sequential turns | The POST blocks until the target finishes its turn. No passive push\u002Fsubscribe — drive each turn explicitly. |\n| Local only | Server binds to `127.0.0.1`. Cross-machine is not supported. |\n| Triggers a real turn | The target actually processes the message and incurs cost. Use `\"noReply\": true` in the body to inject a user message without triggering a response. |\n\n### Method A (`task(session_id=...)`)\n\n| Limitation | Detail |\n|---|---|\n| Primary agents blocked | Errors `Cannot delegate to primary agent \"...\" via task`. Sisyphus is primary, so Method A does **not** work for it — use Method B. |\n| `run_in_background=true` fails | Error: \"Task not found for session\". Always use `run_in_background=false`. |\n| `subagent_type` must match | Must match the subagent running in the target session. |\n| Same process only | Both sessions must be running in the same opencode process\u002Finstance. |\n\n## Worked Example (Method B — verified against a live Sisyphus session)\n\n```bash\n# 1. Find the target session (cross-project) via the find-session skill \u002F SQLite\nsqlite3 ~\u002F.local\u002Fshare\u002Fopencode\u002Fopencode.db \\\n  \"SELECT id, title, directory FROM session WHERE title LIKE '%sandbox%' ORDER BY time_updated DESC LIMIT 5;\"\n# → ses_19eab2b32ffe0PftUbk85Lttj7 | sandbox | \u002FUsers\u002Frs\u002FBunch\u002Fcode\u002Fapps\n\n# 2. Find the opencode web port and confirm identity (returns title + agent)\nPORT=4096\nSID=ses_19eab2b32ffe0PftUbk85Lttj7\ncurl -s \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\" | python3 -c \"import sys,json;d=json.load(sys.stdin);print(d['title'],'|',d['agent'])\"\n# → sandbox | Sisyphus - ultraworker   (a PRIMARY agent — task() would refuse this)\n\n# 3. Inject the message — works despite the primary agent\ncurl -s -X POST \"http:\u002F\u002F127.0.0.1:$PORT\u002Fsession\u002F$SID\u002Fmessage\" \\\n  -H 'content-type: application\u002Fjson' \\\n  -d '{\"parts\":[{\"type\":\"text\",\"text\":\"test\"}]}' \\\n  | python3 -c \"import sys,json;print(''.join(p.get('text','') for p in json.load(sys.stdin)['parts'] if p.get('type')=='text'))\"\n# → test   (HTTP 200 — round-trip confirmed)\n\n# 4. Repeat step 3 with the same SID for each further turn; context is preserved.\n```\n\n## Related Skills\n\n- `find-session` — locate sessions across all projects via SQLite when `session_list` is insufficient\n",{"name":5,"description":7},"main","e25eb555e87aa9eeb59b520834f46fd926ad19a3","opencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fsession-conversation","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles","https:\u002F\u002Fgithub.com\u002Ftwidxuga","Software developer, data scientist, applications architect and all round computer geek.","2026-10-28 03:46:24",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add twidxuga\u002Fdotfiles --skill session-conversation",{"tool":40,"command":41},"bunx","bunx skills add twidxuga\u002Fdotfiles --skill session-conversation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add twidxuga\u002Fdotfiles --skill session-conversation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fsession-conversation\u002FSKILL.md",true,[],[49,81,95,112,128,140],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":63,"publishedAt":22},"01M6C9Z7VKBN4HAFBDXD67K3E1","terraform-test","Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution.","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fterraform-test\u002FSKILL.md",[55,60],{"categoryNo":56,"categoryName":57,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":61,"categoryName":62,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000011","运维与部署",[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"test","terraform","terraform test","testing","writing","infrastructure","run","data","ibm","Providers","execution","troubleshooting","syntax","behavior","guide","use","files",{"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":88,"publishedAt":22},"01M6C9Z4GWWTXCXAS8NK747K07","terraform-style-guide","Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fterraform-style-guide\u002FSKILL.md",[87],{"categoryNo":61,"categoryName":62,"taxonomyType":58,"taxonomyTypeDesc":59},[89,78,65,90,91,92,93,68,94,79],"terraform style guide","official","generate","code","best practices","hashicorp",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":102,"publishedAt":22},"01M6C9Z1DCAC8YQQ1WS0AHBB14","terraform-stacks","Comprehensive guide for working with HashiCorp Terraform Stacks. Use when creating, modifying, or validating Terraform Stack configurations (.tfcomponent.hcl, .tfdeploy.hcl files), working with stack components and deployments from local modules, public registry, or private registry sources, managing multi-region or multi-environment infrastructure, or troubleshooting Terraform Stacks syntax and structure.","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fterraform-stacks\u002FSKILL.md",[101],{"categoryNo":61,"categoryName":62,"taxonomyType":58,"taxonomyTypeDesc":59},[65,103,104,80,105,106,107,108,69,109,72,94,110,75,76,111,78,79],"terraform stacks","multi-environment","deployments","public","modules","components","registry","stack","environment",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":22},"01M6C9YYAVCNTR81V4HGZWPFW1","terraform-search-import","Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fterraform-search-import\u002FSKILL.md",[118],{"categoryNo":61,"categoryName":62,"taxonomyType":58,"taxonomyTypeDesc":59},[120,121,65,79,122,69,123,72,73,124,125,126,127],"terraform search import","search","support","cloud","list","management","version","iac",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":132,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":136,"publishedAt":22},"01M6BZS7EAXHWK32RG213VE65G","run-acceptance-tests","Guide for running acceptance tests for a Terraform provider. Use this when asked to run an acceptance test or to run a test with the prefix `TestAcc`.","MPL-2.0","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fterraform-run-acceptance-tests\u002FSKILL.md",[135],{"categoryNo":61,"categoryName":62,"taxonomyType":58,"taxonomyTypeDesc":59},[137,138,70,64,65,139,72],"run acceptance tests","acceptance","terraform provider",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":153,"publishedAt":22},"01M6BZS4MJD31PY7M7654ZWQ56","refactor-module","Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.","https:\u002F\u002Fgithub.com\u002Ftwidxuga\u002Fdotfiles\u002Fblob\u002Fmain\u002Fopencode\u002Fdot-config\u002Fopencode\u002Fskills\u002Fterraform-refactor-module\u002FSKILL.md",[146,149,150],{"categoryNo":147,"categoryName":148,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":61,"categoryName":62,"taxonomyType":58,"taxonomyTypeDesc":59},{"categoryNo":151,"categoryName":152,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000015","视觉设计",[154,155,93,65,72,94,156],"refactor module","refactor","design"]