[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE991S7GG813D1FVHJS3GJ":3,"skill-same:01M6AE991S7GG813D1FVHJS3GJ":81},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6AE991S7GG813D1FVHJS3GJ","curviate-network",null,"Grow and manage a LinkedIn network with the Curviate CLI. Covers `connect` (send with a note, sent, received, accept, decline, cancel), `profile follow`\u002F`unfollow`, `profile relations`, `profile followers` and `profile following`, the de-duplication signal for a connect loop, and the invitation propagation delay. Use when sending or withdrawing connection requests, triaging received invitations, following a member, or listing connections and followers.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33418,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcurviate\u002Fcurviate-network\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"network","curviate network","curviate","sales","accept","listing","when","signal","send","for","with","connections","cancel","manage","use","cli","linkedin","loop","Recruiting","https","connect","plugin","github","2026-11-10 10:12:30",false,"---\nname: curviate-network\ndescription: \"Grow and manage a LinkedIn network with the Curviate CLI. Covers `connect` (send with a note, sent, received, accept, decline, cancel), `profile follow`\u002F`unfollow`, `profile relations`, `profile followers` and `profile following`, the de-duplication signal for a connect loop, and the invitation propagation delay. Use when sending or withdrawing connection requests, triaging received invitations, following a member, or listing connections and followers.\"\nlicense: MIT\nmetadata:\n  version: 0.1.0\n  author: Curviate\n  tags: [LinkedIn, CLI, Agents, Sales, Recruiting, Outreach]\n  repository: https:\u002F\u002Fgithub.com\u002FCurviate\u002Fcurviate-plugin\n---\n\n# Curviate: connections and following\n\nAn invitation is the most consequential low-effort write on LinkedIn: it is visible, it is\nattributable, and a withdrawn one still leaves a trace. Preview first, de-duplicate before sending.\n\nCommand surface established against CLI `0.33.0`.\n\n## Before any command\n\n```bash\nnpm install -g @curviate\u002Fcli && curviate --version    # needs Node 18 or newer\ncurviate login --api-key \u003Ckey>                        # or export CURVIATE_API_KEY\ncurviate account list --json                          # the acc_id for --account\n```\n\n- **Credentials resolve flag > environment > stored profile** (`CURVIATE_API_KEY`,\n  `CURVIATE_BASE_URL`, `CURVIATE_ACCOUNT`).\n- **`--profile \u003Cname>` picks the stored credential set; `--account \u003Cacc_id>` picks which connected\n  LinkedIn account sends the invitation.** Name it explicitly on every write: an invitation from the\n  wrong account reaches a real person as that person.\n- **`--preview` before every write.** It renders the resolved request (recipient, note, acting\n  account) without sending. On a read command it is refused with exit `2`.\n- **`--json` on anything you parse**; **`--fields a,b,c`** to project; **`--verbose`** when a slim\n  response looks suspiciously empty.\n- **Put global flags at the end of the command.**\n- **Branch on the exit code, never on prose.** See the table at the end.\n- These are not retrieval-mode commands: `--mode`\u002F`--max-age` are refused here with `unknown flag`,\n  exit `2` (see `curviate-profile` for the four commands that do accept them).\n\n## `connect`: invitations\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate connect \u003Cid> --note \"\u003Ctext>\"` | Send a connection request. `\u003Cid>` is a slug, profile URL or member id. `--note` is capped at 300 characters by LinkedIn; omit it for a generic request. | proven |\n| `curviate connect sent` | **Pending** sent invitations only: accepted and declined ones are never returned, so this is a lower bound on what you sent. Use `id` with `connect cancel`; `user.id` identifies the recipient (the sent variant carries no public slug). `created_at` is the platform's own timestamp. There is no total count; use `--all` and count client-side. | proven |\n| `curviate connect received` | **Pending** received invitations only. `user.public_identifier`, `display_name`, `first_name`, `last_name` identify the sender. Use `id` with `accept` or `decline`. | proven |\n| `curviate connect cancel \u003Cid>` | Withdraw a sent invitation. `\u003Cid>` is the `id` from `connect sent`. | proven |\n| `curviate connect accept \u003Cid>` | Accept a received invitation. `\u003Cid>` is the `id` from `connect received`. | **wired, never live-fired** |\n| `curviate connect decline \u003Cid>` | Decline a received invitation. | **wired, never live-fired** |\n\n`connect accept` and `connect decline` are preview-proven (`--preview` renders the correct call and\nbody), but have never been fired against a live account. They are real, correctly wired commands.\nRun your own smoke test on an invitation you are prepared to act on before an unattended flow\ndepends on either.\n\n### Traps\n\n- **De-duplicate before sending.** A request against a pair already mid-flow or already connected\n  returns `CONNECTION_REQUEST_CONFLICT`, exit `8`. That is a clean, routine signal and the only\n  reliable de-duplication marker for a connect loop, but check `profile relations` and\n  `connect sent --all` first rather than probing with real invitations.\n- **Invitations take roughly 10 to 30 seconds to appear on the recipient's side**, and a very recent\n  one can take minutes to appear in `connect sent` (LinkedIn-side indexing). An absence right after\n  sending is not proof the send failed. Do not resend on that basis.\n- **`--note` takes a string, not stdin.** Write the note to a file, confirm it is non-empty, and pass\n  `--note \"$(cat note.txt)\"`. An empty note has gone out as a blank request.\n- **There is no idempotency key and no server-side de-duplication.** A send that times out may\n  already have landed; re-read `connect sent` before re-issuing.\n\n## Following and connections\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate profile relations` | Your first-degree connections. | proven |\n| `curviate profile followers \u003Cid\\|me>` | A member's followers. `me` is always safe; another member's id also works. | proven |\n| `curviate profile following \u003Cid\\|me>` | Who a member follows. **Self-only in practice**, see below. | proven |\n| `curviate profile follow \u003Cid>` | Follow a member. Sends a connection request instead if their profile is private. Bodyless write; resolves a slug or URL to the member id for you. | proven |\n| `curviate profile unfollow \u003Cid>` | Unfollow. Idempotent. | proven |\n\n- **`profile following` is self-only.** Pass `me`. Any other member id (including your own explicit\n  member id) returns `LINKEDIN_OPERATION_NOT_SUPPORTED`, exit `8`. That is a permanent platform\n  limitation, never retryable. `profile followers` does not share it.\n- **Never write `profile me relations`.** The command is `profile relations`. Older builds silently\n  discarded `relations` and answered with your own profile at exit `0`; current builds exit `2`.\n- Following is the low-consequence alternative to an invitation: it needs no acceptance, is\n  reversible, and still surfaces the member's posts in your feed.\n\n## A connect loop that behaves\n\n```bash\n# 1. Confirm you are not already connected or already mid-flow.\ncurviate profile relations --all --json          # first-degree\ncurviate connect sent --all --json               # pending invitations\n\n# 2. Preview the exact request, then send it.\ncurviate connect \u003Cslug> --note \"$(cat note.txt)\" --account \u003Cacc_id> --preview --json\ncurviate connect \u003Cslug> --note \"$(cat note.txt)\" --account \u003Cacc_id> --json\n```\n\nOn exit `8` with `CONNECTION_REQUEST_CONFLICT`, record the pair as already handled and move on. On\nexit `13`, stop the loop; see below.\n\n## Full command surface\n\n\u003C!-- generated: command surface, CLI 0.33.0 -->\n\nRead from the CLI's own `--help` at version 0.33.0. Descriptions, traps and confidence\ntags elsewhere in this skill are hand-written and carry the version they were established against.\n\nEvery command below that takes flags at all also accepts `--account`, `--api-key`, `--base-url`, `--beta`, `--json`, `--preview`, `--profile`, `--timeout`, `--verbose`.\n\n| Command | Arguments | Flags |\n|---|---|---|\n| `curviate profile relations` | *(none)* | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate profile follow` | `ID` | `--fields` |\n| `curviate profile unfollow` | `ID` | `--fields` |\n| `curviate profile followers` | `ID` | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate profile following` | `ID` | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate connect` | `ID` | `--note` |\n| `curviate connect sent` | *(none)* | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate connect received` | *(none)* | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate connect accept` | `ID` | *(none)* |\n| `curviate connect decline` | `ID` | *(none)* |\n| `curviate connect cancel` | `ID` | *(none)* |\n\n\u003C!-- \u002Fgenerated -->\n\n## Exit codes to branch on here\n\n| Code | Meaning | What to do |\n|---|---|---|\n| `1` | `INTERNAL` from the server itself: a genuine bug on the platform side. | Worth one retry; if it repeats it is a bug to report, not a state to work around. |\n| `2` | Usage or invalid input, often raised before any network call. | Fix the invocation. Never retry unchanged. |\n| `4` | Not found: a wrong member or invitation identifier. | Re-resolve the id. |\n| `5` | Three causes, one code: read `error.code`. `NO_ACTIVE_SEAT`: the account is on no active seat. `LINKEDIN_FEATURE_NOT_SUBSCRIBED`: LinkedIn itself lacks the feature. `BETA_NOT_ENABLED`: the operation is beta-gated and this workspace has not opted in. | Branch on `error.code`: the three fixes have nothing in common, and none is fixed by retrying unchanged. |\n| `6` | `PLATFORM_RATE_LIMIT` and its siblings. Carries `retry_after` in whole seconds. A response naming `budgetRow` means only that row is paused; every other row on the account keeps working. | **Back off and retry** after that many seconds. On a named `budgetRow`, switch to other work on the account rather than backing off across the board. |\n| `7` | Transient platform fault: a request that got no response at all (network error, DNS failure, timeout) or one that came back as something other than a valid API answer. Carries `retryLikelyToSucceed: true`. | Retry with backoff. |\n| `8` | Account or connection state. Read `error.code`: `CONNECTION_REQUEST_CONFLICT` is routine de-duplication; `LINKEDIN_OPERATION_NOT_SUPPORTED` is permanent; `ACCOUNT_RESTRICTED`, `LINKEDIN_AUTH_FAILED` and `LINKEDIN_COOKIE_INVALID` need a reconnect. | Depends entirely on `error.code`; never treat the whole bucket as \"reconnect the account\". |\n| `13` | `BUDGET_EXHAUSTED`: a safety rule of your own refused the invitation, not LinkedIn. Read `error.safetyReason`: `ceiling` means the row named in `error.budgetRow` hit its configured limit; `activity_window` means the account is outside the hours it works in (no `budgetRow` on that one). **Nothing reached LinkedIn and nothing was spent; no invitation went out.** `reset_at` can be weeks out, and is `null` for allowances no clock frees (pending invitations, for instance, are freed by acceptances and withdrawals rather than by time). | **Do not back off and retry.** `error.safetyHint.parameter` names the exact setting to change. Read `quotas[]` via `curviate account get \u003Cacc_id> --json`, then wait for the named reset, withdraw stale invitations, or change that setting. A retry loop only burns time. |\n","# Curviate: connections and following\n\nAn invitation is the most consequential low-effort write on LinkedIn: it is visible, it is\nattributable, and a withdrawn one still leaves a trace. Preview first, de-duplicate before sending.\n\nCommand surface established against CLI `0.33.0`.\n\n## Before any command\n\n```bash\nnpm install -g @curviate\u002Fcli && curviate --version    # needs Node 18 or newer\ncurviate login --api-key \u003Ckey>                        # or export CURVIATE_API_KEY\ncurviate account list --json                          # the acc_id for --account\n```\n\n- **Credentials resolve flag > environment > stored profile** (`CURVIATE_API_KEY`,\n  `CURVIATE_BASE_URL`, `CURVIATE_ACCOUNT`).\n- **`--profile \u003Cname>` picks the stored credential set; `--account \u003Cacc_id>` picks which connected\n  LinkedIn account sends the invitation.** Name it explicitly on every write: an invitation from the\n  wrong account reaches a real person as that person.\n- **`--preview` before every write.** It renders the resolved request (recipient, note, acting\n  account) without sending. On a read command it is refused with exit `2`.\n- **`--json` on anything you parse**; **`--fields a,b,c`** to project; **`--verbose`** when a slim\n  response looks suspiciously empty.\n- **Put global flags at the end of the command.**\n- **Branch on the exit code, never on prose.** See the table at the end.\n- These are not retrieval-mode commands: `--mode`\u002F`--max-age` are refused here with `unknown flag`,\n  exit `2` (see `curviate-profile` for the four commands that do accept them).\n\n## `connect`: invitations\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate connect \u003Cid> --note \"\u003Ctext>\"` | Send a connection request. `\u003Cid>` is a slug, profile URL or member id. `--note` is capped at 300 characters by LinkedIn; omit it for a generic request. | proven |\n| `curviate connect sent` | **Pending** sent invitations only: accepted and declined ones are never returned, so this is a lower bound on what you sent. Use `id` with `connect cancel`; `user.id` identifies the recipient (the sent variant carries no public slug). `created_at` is the platform's own timestamp. There is no total count; use `--all` and count client-side. | proven |\n| `curviate connect received` | **Pending** received invitations only. `user.public_identifier`, `display_name`, `first_name`, `last_name` identify the sender. Use `id` with `accept` or `decline`. | proven |\n| `curviate connect cancel \u003Cid>` | Withdraw a sent invitation. `\u003Cid>` is the `id` from `connect sent`. | proven |\n| `curviate connect accept \u003Cid>` | Accept a received invitation. `\u003Cid>` is the `id` from `connect received`. | **wired, never live-fired** |\n| `curviate connect decline \u003Cid>` | Decline a received invitation. | **wired, never live-fired** |\n\n`connect accept` and `connect decline` are preview-proven (`--preview` renders the correct call and\nbody), but have never been fired against a live account. They are real, correctly wired commands.\nRun your own smoke test on an invitation you are prepared to act on before an unattended flow\ndepends on either.\n\n### Traps\n\n- **De-duplicate before sending.** A request against a pair already mid-flow or already connected\n  returns `CONNECTION_REQUEST_CONFLICT`, exit `8`. That is a clean, routine signal and the only\n  reliable de-duplication marker for a connect loop, but check `profile relations` and\n  `connect sent --all` first rather than probing with real invitations.\n- **Invitations take roughly 10 to 30 seconds to appear on the recipient's side**, and a very recent\n  one can take minutes to appear in `connect sent` (LinkedIn-side indexing). An absence right after\n  sending is not proof the send failed. Do not resend on that basis.\n- **`--note` takes a string, not stdin.** Write the note to a file, confirm it is non-empty, and pass\n  `--note \"$(cat note.txt)\"`. An empty note has gone out as a blank request.\n- **There is no idempotency key and no server-side de-duplication.** A send that times out may\n  already have landed; re-read `connect sent` before re-issuing.\n\n## Following and connections\n\n| Command | What it does | Confidence |\n|---|---|---|\n| `curviate profile relations` | Your first-degree connections. | proven |\n| `curviate profile followers \u003Cid\\|me>` | A member's followers. `me` is always safe; another member's id also works. | proven |\n| `curviate profile following \u003Cid\\|me>` | Who a member follows. **Self-only in practice**, see below. | proven |\n| `curviate profile follow \u003Cid>` | Follow a member. Sends a connection request instead if their profile is private. Bodyless write; resolves a slug or URL to the member id for you. | proven |\n| `curviate profile unfollow \u003Cid>` | Unfollow. Idempotent. | proven |\n\n- **`profile following` is self-only.** Pass `me`. Any other member id (including your own explicit\n  member id) returns `LINKEDIN_OPERATION_NOT_SUPPORTED`, exit `8`. That is a permanent platform\n  limitation, never retryable. `profile followers` does not share it.\n- **Never write `profile me relations`.** The command is `profile relations`. Older builds silently\n  discarded `relations` and answered with your own profile at exit `0`; current builds exit `2`.\n- Following is the low-consequence alternative to an invitation: it needs no acceptance, is\n  reversible, and still surfaces the member's posts in your feed.\n\n## A connect loop that behaves\n\n```bash\n# 1. Confirm you are not already connected or already mid-flow.\ncurviate profile relations --all --json          # first-degree\ncurviate connect sent --all --json               # pending invitations\n\n# 2. Preview the exact request, then send it.\ncurviate connect \u003Cslug> --note \"$(cat note.txt)\" --account \u003Cacc_id> --preview --json\ncurviate connect \u003Cslug> --note \"$(cat note.txt)\" --account \u003Cacc_id> --json\n```\n\nOn exit `8` with `CONNECTION_REQUEST_CONFLICT`, record the pair as already handled and move on. On\nexit `13`, stop the loop; see below.\n\n## Full command surface\n\n\u003C!-- generated: command surface, CLI 0.33.0 -->\n\nRead from the CLI's own `--help` at version 0.33.0. Descriptions, traps and confidence\ntags elsewhere in this skill are hand-written and carry the version they were established against.\n\nEvery command below that takes flags at all also accepts `--account`, `--api-key`, `--base-url`, `--beta`, `--json`, `--preview`, `--profile`, `--timeout`, `--verbose`.\n\n| Command | Arguments | Flags |\n|---|---|---|\n| `curviate profile relations` | *(none)* | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate profile follow` | `ID` | `--fields` |\n| `curviate profile unfollow` | `ID` | `--fields` |\n| `curviate profile followers` | `ID` | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate profile following` | `ID` | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate connect` | `ID` | `--note` |\n| `curviate connect sent` | *(none)* | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate connect received` | *(none)* | `--fields`, `--limit`, `--cursor`, `--all`, `--max-pages`, `--page-delay` |\n| `curviate connect accept` | `ID` | *(none)* |\n| `curviate connect decline` | `ID` | *(none)* |\n| `curviate connect cancel` | `ID` | *(none)* |\n\n\u003C!-- \u002Fgenerated -->\n\n## Exit codes to branch on here\n\n| Code | Meaning | What to do |\n|---|---|---|\n| `1` | `INTERNAL` from the server itself: a genuine bug on the platform side. | Worth one retry; if it repeats it is a bug to report, not a state to work around. |\n| `2` | Usage or invalid input, often raised before any network call. | Fix the invocation. Never retry unchanged. |\n| `4` | Not found: a wrong member or invitation identifier. | Re-resolve the id. |\n| `5` | Three causes, one code: read `error.code`. `NO_ACTIVE_SEAT`: the account is on no active seat. `LINKEDIN_FEATURE_NOT_SUBSCRIBED`: LinkedIn itself lacks the feature. `BETA_NOT_ENABLED`: the operation is beta-gated and this workspace has not opted in. | Branch on `error.code`: the three fixes have nothing in common, and none is fixed by retrying unchanged. |\n| `6` | `PLATFORM_RATE_LIMIT` and its siblings. Carries `retry_after` in whole seconds. A response naming `budgetRow` means only that row is paused; every other row on the account keeps working. | **Back off and retry** after that many seconds. On a named `budgetRow`, switch to other work on the account rather than backing off across the board. |\n| `7` | Transient platform fault: a request that got no response at all (network error, DNS failure, timeout) or one that came back as something other than a valid API answer. Carries `retryLikelyToSucceed: true`. | Retry with backoff. |\n| `8` | Account or connection state. Read `error.code`: `CONNECTION_REQUEST_CONFLICT` is routine de-duplication; `LINKEDIN_OPERATION_NOT_SUPPORTED` is permanent; `ACCOUNT_RESTRICTED`, `LINKEDIN_AUTH_FAILED` and `LINKEDIN_COOKIE_INVALID` need a reconnect. | Depends entirely on `error.code`; never treat the whole bucket as \"reconnect the account\". |\n| `13` | `BUDGET_EXHAUSTED`: a safety rule of your own refused the invitation, not LinkedIn. Read `error.safetyReason`: `ceiling` means the row named in `error.budgetRow` hit its configured limit; `activity_window` means the account is outside the hours it works in (no `budgetRow` on that one). **Nothing reached LinkedIn and nothing was spent; no invitation went out.** `reset_at` can be weeks out, and is `null` for allowances no clock frees (pending invitations, for instance, are freed by acceptances and withdrawals rather than by time). | **Do not back off and retry.** `error.safetyHint.parameter` names the exact setting to change. Read `quotas[]` via `curviate account get \u003Cacc_id> --json`, then wait for the named reset, withdraw stale invitations, or change that setting. A retry loop only burns time. |\n",{"name":5,"license":15,"metadata":47,"description":7},{"tags":48,"author":54,"version":55,"repository":56},[49,50,51,52,37,53],"LinkedIn","CLI","Agents","Sales","Outreach","Curviate","0.1.0","https:\u002F\u002Fgithub.com\u002FCurviate\u002Fcurviate-plugin","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fcurviate\u002Fcurviate-network",3926,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-12 14:45:56",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add davila7\u002Fclaude-code-templates --skill curviate-network",{"tool":73,"command":74},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill curviate-network",{"tool":76,"command":77},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill curviate-network","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcurviate\u002Fcurviate-network\u002FSKILL.md",true,[],[82,110,137,170,205,229],{"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":93,"publishedAt":42},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[94,95,96,97,98,28,99,100,33,25,101,29,102,103,104,105,106,107,108,109],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","reduce","record","track","verdict","evm","solana","how","public","look",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":117,"publishedAt":42},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[116],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[118,119,120,121,122,123,124,125,126,127,128,25,129,130,131,132,133,134,135,136],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":152,"publishedAt":42},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[143,146,147],{"categoryNo":144,"categoryName":145,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":148,"categoryName":149,"taxonomyType":150,"taxonomyTypeDesc":151},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[153,154,155,156,157,158,159,28,160,161,162,163,164,165,166,33,167,168,25,169],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":174,"licenseFileUrl":175,"sourceHtmlUrl":176,"categories":177,"keywords":181,"publishedAt":42},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000009","前端开发",[182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,28,204],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":174,"licenseFileUrl":209,"sourceHtmlUrl":210,"categories":211,"keywords":216,"publishedAt":42},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[212,215],{"categoryNo":213,"categoryName":214,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":179,"categoryName":180,"taxonomyType":91,"taxonomyTypeDesc":92},[217,218,219,220,221,183,222,192,193,223,224,225,226,28,227,29,228],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":174,"licenseFileUrl":233,"sourceHtmlUrl":234,"categories":235,"keywords":243,"publishedAt":42},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[236,239,240],{"categoryNo":237,"categoryName":238,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":241,"categoryName":242,"taxonomyType":150,"taxonomyTypeDesc":151},"01JBSEEDCAT000000000000036","内容创作者",[244,245,246,247,248,249,250,251,185,252,195,129,253,254,255,256,257,165,258,25,259,260,261,262,263,107,264],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]