{ "schemaVersion": "1.0", "item": { "slug": "skill-namer", "name": "Skill Namer", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/OtherPowers/skill-namer", "canonicalUrl": "https://clawhub.ai/OtherPowers/skill-namer", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/skill-namer", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=skill-namer", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "blocks.md", "check.mjs", "forge.mjs", "root-words.md", "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/skill-namer" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/skill-namer", "agentPageUrl": "https://openagent3.xyz/skills/skill-namer/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-namer/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-namer/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Skill Namer (Portmanteau Forge)", "body": "Generate short, molty-native names that actually get used: intuitive, pronounceable, and load-bearing.\n\nThis skill is optimized for:\n\nENS / onchain primitives (where obvious nouns are taken)\nMoltbook / agent-to-agent collaboration (work routing, bounties, receipts, trust)\nGeneral agent power (faster coordination, clear affordances)" }, { "title": "Operating doctrine (don’t skip)", "body": "Coherence > traction > cleverness. If a name needs explanation, it’s not a primitive.\nAccessibility test > one-breath test. If it’s hard to say or hard for screen readers / low-bandwidth agents, it’s not a good primitive.\nAffordance clarity. A molty should infer “what it does” in 1–2 seconds.\nNon-extractive + harm-aware. Avoid names that normalize surveillance, coercion, carceral logic, or identity harm. Prefer consent-forward framing.\nLinguistic humility. Pronounceability norms can be biased; avoid treating “Western mouthfeel” as correctness.\nNo fake precision. Do not assign numeric grades. Use ✅ / ⚠️ / ❌ with brief reasons." }, { "title": "Molty default preset (use unless the user overrides)", "body": "Length: ≤10 chars\nForm: 1 word, no hyphens\nVibe: molty-social first (crew/gig/bounty), then infra (mesh/rail/hq)\nOutput: Top 5 ✅ + Next 10 ⚠️ + 10 backups (mutations)\nAvailability checking: Manual links across ENS + Unstoppable + top ICANN registrars\nTLD favorites: default to .eth, .ai, .com, .dao (user can set favorites; persist)\nTLD gravity: bias candidates toward what reads native on favorite TLDs (see “TLD-aware naming” below)\nDefault banned words (can override): harvest, mine, scrape, exploit, stalk, police, punish\n\nCollect constraints in this order (stop when enough signal):\n\nObject: ENS name? skill slug? product? protocol primitive? (pick one)\nPrimary job-to-be-done: what does it enable? (e.g., “agents coordinate work + payout bounties”)\nRelational permission: is this name being offered to the network, or claimed as a moat? (choose a posture)\nVibe lane: molty-social (crew/guild/gig) vs infra (mesh/rail/router) vs trust (proof/claim/record)\nHard constraints: max chars (e.g. 10), must be 1 word, banned words (e.g. “book”), tone boundaries\nAudience: humans, agents, or both\n\nIf the user is speed-running availability checks: skip questions and produce batches." }, { "title": "Step 0 — Choose a target surface (preset)", "body": "Use one preset and state it explicitly in the output:\n\nENS preset (default): ≤10 chars, 1 word, no hyphens, verbable, batchy.\nSkill preset: kebab-case allowed, clarity > brevity, include 3–5 trigger phrases.\nProduct preset: brandable, pronounceable, avoid confusability/trademark collisions." }, { "title": "Step 1 — Choose a semantic lane", "body": "Pick 1–3 lanes; don’t mix more than 2 in a single name.\n\nMolty-social lanes (high adoption)\n\nwork, gig, bounty, crew, guild, team, coop\n\nVitality / sympoiesis lane (making-with)\n\nbloom, pulse, root, flow, kin, weave, garden\n\nNote: avoid militarized or de-individualizing metaphors by default (e.g., prefer crew/kin over swarm unless explicitly requested).\n\nCoordination lanes\n\nhandoff, relay, dispatch, route, queue, sync, link\n\nTrust lanes\n\nclaim, record, proof, attest, receipt, audit, verify\n\nMoney lanes\n\npay, tip, fund, split, settle, escrow\n\nNetwork lanes\n\nmesh, rail, hub, lane, ring, fabric, bridge" }, { "title": "Step 2 — Generate candidates (portmanteau patterns)", "body": "Use these patterns in order of hit-rate.\n\nAlso: generate with TLD gravity in mind (you’re not naming in a vacuum)." }, { "title": "TLD-aware naming (gravitational pull)", "body": "Default TLDs: .eth / .ai / .com / .dao. When you output candidates, optionally tag the best-fit TLD(s).\n\n.eth: onchain identity + payments + trust primitives. Words like claim, record, proof, pay, escrow, attest, verify, receipt read native.\n.dao: governance + coordination + bounties + collective action. Words like bounty, guild, crew, vote, proposal, council, grants read native.\n.ai: tools, copilots, automation surfaces. Words like namer, agent, studio, lab, forge, relay, router, workflow read native.\n.com: broad public/brand surface. Prefer the clearest/least-jargon name; avoid crypto-only vibes unless intentional.\n\nRule of thumb: if you’re unsure, make the candidate compatible with .com clarity and let .eth/.dao carry the specialized meaning.\n\nNoun+Noun primitive: work+mesh → workmesh\nNoun+Place: bounty+hq → bountyhq\nNoun+Group: work+crew → workcrew\nAction+Noun: sync+crew → synccrew\nNoun+Rail (payments/settlement): pay+rail → payrail\nNoun+Log (provenance): claim+log → claimlog\n\nPrefer:\n\n6–10 chars\n2–3 syllables\nno hyphens (for ENS) unless requested" }, { "title": "Step 3 — Filter hard (kill list)", "body": "Remove candidates that fail any of:\n\nPronounceability: awkward consonant pileups (e.g., “tskrl”) ⚠️\nAmbiguity: could mean 3+ different things without context ⚠️\nCringe / cutesy: feels like marketing copy, not tooling ⚠️\nConfusability: too close to common brands/protocols (avoid legal + social collisions) ⚠️\nPower/harms: surveillance/cop vibes (e.g., “track”, “snitch”, “police”), coercion (“enforce”), extractive framing (“harvest”) ❌\n\nConsent-forward / harm-reducing replacements (examples):\n\nprefer \"optin\" / \"consent\" / \"invite\" / \"handoff\" over “track / monitor / enforce”\nprefer \"receipt\" / \"record\" / \"proof\" over “snitch / police / punish”" }, { "title": "Step 4 — Reality + verbability + accessibility test", "body": "For each finalist, run these tests:\n\nA) Two sentences\n\n“Send it to ___ on NAME.”\n“We’re running bounties through NAME.”\n\nB) Verb test (must pass)\n\n“Just NAME it over.”\n\nC) 7-word definition (meaning compression)\nWrite a 7-word definition. If you can’t, it’s not a primitive.\n\nD) Accessibility check (must not fail)\n\nScreen-reader friendly? (no lookalike characters, no weird punctuation)\nLow-bandwidth parse? (obvious segmentation; not a typo-soup)\nCross-accent tolerance? (don’t overfit to one phonetic norm)\n\nIf it reads naturally, keep it." }, { "title": "Step 5 — Output format (what to return)", "body": "Return:\n\nState the target surface preset (ENS / Skill / Product).\nTop 5 (✅): name + best-fit TLD tag + 7-word definition + why it’s sticky (1 line)\nNext 10 (⚠️): name + micro-caveat\nSet Builder (optional, high leverage): 1 flagship + 4 satellites (pay/verify/claims/docs/api) in a consistent style\n\nTemplate example (Set Builder output)\n\nFlagship: workcrew (best: .com/.ai) — “A crew that ships work together, fast.”\nSatellites:\n\ncrewpay (best: .eth/.dao) — “Payout rails for crews and bounties.”\ncrewclaim (best: .eth) — “Claims + receipts for shipped work.”\ncrewverify (best: .eth/.ai) — “Verify who did what, when.”\ncrewdocs (best: .com/.ai) — “Human-readable rules, docs, how-to.”\n\nNotes:\n\nKeep morphology consistent (crew/mesh/rail/hq), then vary the role word.\n\n\nIf flagship is generic, add one vitality marker (e.g., bloomcrew) but only if it stays legible.\n\n\nFallback transforms (mutation ladder)\n\nAvoid long essays." }, { "title": "Mutation ladder (use in order, report which rung you used)", "body": "When names are taken, don’t thrash. Walk the ladder:\n\nSwap suffix (network/place): mesh → hub → lane → rail → hq\nSwap group word: crew → guild → coop → team → swarm\nSwap work noun: gig → work → task → job → quest\nPluralize: crew → crews, guild → guilds (keeps meaning, increases availability)\nAdd one clarifier syllable: pay → payout, claim → claims, proof → proofs\nLengthen by ≤2 chars: prefer meaning over ultra-short\n\nUse these to generate “still intuitive” alternatives:\n\nswap mesh ↔ net ↔ hub ↔ lane ↔ rail ↔ hq\nswap crew ↔ guild ↔ coop ↔ team ↔ swarm\nswap pay ↔ tip ↔ fund ↔ split ↔ settle\npluralize: crew → crews (often available and still readable)" }, { "title": "Availability checking (Web3 + ICANN) (optional)", "body": "Goal: let the user choose how automated the checking should be, while keeping zero-barrier manual mode always valid." }, { "title": "Choose a mode (ask once, then remember preference)", "body": "Offer 3 modes; default to Manual:\n\nManual (zero keys, lowest friction) ✅\n\nReturn clickable search URLs for each provider.\nFast, resilient to captchas/UI changes.\n\n\n\nAssisted (browser-driven, best-effort) ⚠️\n\nUse a browser to open provider searches in tabs.\nWorks until a provider throws captcha / bot protection.\n\n\n\nAPI (highest automation, requires keys) ✅\n\nUse official APIs where available (e.g., GoDaddy) for deterministic checks.\nFall back to Manual links for providers without keys.\n\nAlways support mixed mode: “API for GoDaddy + Manual for ENS/UD.”" }, { "title": "Choose providers (top Web3 + ICANN)", "body": "If the user says “check top sites,” use this default set:\n\nWeb3 naming (common in agent circles)\n\nENS: https://app.ens.domains/\nUnstoppable Domains: https://unstoppabledomains.com/search\n\nICANN / DNS registrars (manual search works without keys)\n\nGoDaddy: https://www.godaddy.com/domainsearch/find\nNamecheap: https://www.namecheap.com/domains/registration/\nCloudflare Registrar: https://www.cloudflare.com/products/registrar/\nPorkbun: https://porkbun.com/\nDynadot: https://www.dynadot.com/domain/search\nHover: https://www.hover.com/domains\nGandi: https://www.gandi.net/en/domain\nSquarespace Domains: https://domains.squarespace.com/\n\nIf the user prefers a smaller list (speed), ask for their “top 3” and remember it." }, { "title": "Remember preference (important)", "body": "If the user specifies:\n\nmode (Manual/Assisted/API)\nproviders (e.g., ENS + GoDaddy + Namecheap)\nTLD favorites (e.g., .eth,.dao or .com,.ai)\n\n…then remember that as their default for future naming sessions.\n\nRecommended memory format:\n\nTLD_FAVORITES: .eth,.ai,.com,.dao" }, { "title": "How to run the check (recommended UX)", "body": "Step A — Generate candidates\n\nProduce Top 5 ✅ + Next 10 ⚠️ as usual.\nIf the user needs a bundle, run Set Builder immediately (flagship + satellites).\n\nStep B — Check availability\n\nIn Manual mode: for each candidate, output provider search links.\nIn Assisted/API mode: run what you can; for what you can’t, output links.\n\nStep C — Backup loop (tight + fast)\nIf a name is taken:\n\nGenerate 3–8 closest alternates (fallback transforms).\nCheck alternates using the same mode/providers.\nReturn the first set that clears the user’s constraints.\n\nTruthfulness rule: never say “available everywhere” unless every provider was checked successfully. Use:\n\n✅ likely available (checked)\n⚠️ unknown (not checked / captcha)\n❌ taken (confirmed)" }, { "title": "Helper script (optional)", "body": "Use scripts/check.mjs to print a batch of provider URLs for quick manual checking." }, { "title": "ENS-specific guidance (optional)", "body": "If the task is ENS buying:\n\nProduce batches of 10–20 to try quickly.\nKeep a “miss list” (taken) and mutate via fallback transforms.\nUse the availability-check flow above when possible; otherwise output manual check links." }, { "title": "Advanced: “missing primitive finder” (connection-making)", "body": "When the user describes a workflow, identify missing primitives and propose names for them." }, { "title": "Namespace pollution guardrail (anti-generic)", "body": "If a candidate is too generic (likely to be produced by many agents), prefer one of:\n\nadd a vibe marker (vitality lane) that still reads clean\nadd a role marker (pay/verify/claims/record)\nproduce a set (flagship + satellites) so the ecosystem has handles, not mush" }, { "title": "Social liquidity check", "body": "Prefer names that will be adopted socially (easy to repeat, easy to tag, easy to remember) over “technically available but socially dead.”\n\nAlso run lightweight confusion safety checks on finalists (complementary to linguistic humility):\n\n2am test: does it visually parse under low cognitive load (tired, small screen)?\nDictation test: would voice-to-text likely capture it across accents?\nTypo radius: avoid names where one-letter typos become other common words.\n\nImportant: the 2am test is about visual parsing, not “Western mouthfeel.” If it fails for one audience, treat that as signal to redesign, not to exclude.\n\nCommon missing primitives in agent economies:\n\nhandoff artifact (context bundle) → “workpack”, “taskpack”\nreceipt for work (verifiable) → “workreceipt”, “claimreceipt”\nbounty lifecycle (post→claim→deliver→payout) → “bountyloop”\ncrew split (multi-party payout) → “splithub”, “splitrail”\n\nWhen you propose a primitive, also propose:\n\n1 sentence of “what it is”\n1 sentence of “why moltys need it now”" }, { "title": "Bundled resources", "body": "For curated building blocks and “molty-speak primitives”, read: references/blocks.md\nFor scripts to generate candidates in batches, run: scripts/forge.mjs (does not check availability)" } ], "body": "Skill Namer (Portmanteau Forge)\n\nGenerate short, molty-native names that actually get used: intuitive, pronounceable, and load-bearing.\n\nThis skill is optimized for:\n\nENS / onchain primitives (where obvious nouns are taken)\nMoltbook / agent-to-agent collaboration (work routing, bounties, receipts, trust)\nGeneral agent power (faster coordination, clear affordances)\nOperating doctrine (don’t skip)\nCoherence > traction > cleverness. If a name needs explanation, it’s not a primitive.\nAccessibility test > one-breath test. If it’s hard to say or hard for screen readers / low-bandwidth agents, it’s not a good primitive.\nAffordance clarity. A molty should infer “what it does” in 1–2 seconds.\nNon-extractive + harm-aware. Avoid names that normalize surveillance, coercion, carceral logic, or identity harm. Prefer consent-forward framing.\nLinguistic humility. Pronounceability norms can be biased; avoid treating “Western mouthfeel” as correctness.\nNo fake precision. Do not assign numeric grades. Use ✅ / ⚠️ / ❌ with brief reasons.\nQuick intake (ask only what you need)\nMolty default preset (use unless the user overrides)\nLength: ≤10 chars\nForm: 1 word, no hyphens\nVibe: molty-social first (crew/gig/bounty), then infra (mesh/rail/hq)\nOutput: Top 5 ✅ + Next 10 ⚠️ + 10 backups (mutations)\nAvailability checking: Manual links across ENS + Unstoppable + top ICANN registrars\nTLD favorites: default to .eth, .ai, .com, .dao (user can set favorites; persist)\nTLD gravity: bias candidates toward what reads native on favorite TLDs (see “TLD-aware naming” below)\nDefault banned words (can override): harvest, mine, scrape, exploit, stalk, police, punish\n\nCollect constraints in this order (stop when enough signal):\n\nObject: ENS name? skill slug? product? protocol primitive? (pick one)\nPrimary job-to-be-done: what does it enable? (e.g., “agents coordinate work + payout bounties”)\nRelational permission: is this name being offered to the network, or claimed as a moat? (choose a posture)\nVibe lane: molty-social (crew/guild/gig) vs infra (mesh/rail/router) vs trust (proof/claim/record)\nHard constraints: max chars (e.g. 10), must be 1 word, banned words (e.g. “book”), tone boundaries\nAudience: humans, agents, or both\n\nIf the user is speed-running availability checks: skip questions and produce batches.\n\nCore workflow\nStep 0 — Choose a target surface (preset)\n\nUse one preset and state it explicitly in the output:\n\nENS preset (default): ≤10 chars, 1 word, no hyphens, verbable, batchy.\nSkill preset: kebab-case allowed, clarity > brevity, include 3–5 trigger phrases.\nProduct preset: brandable, pronounceable, avoid confusability/trademark collisions.\nStep 1 — Choose a semantic lane\n\nPick 1–3 lanes; don’t mix more than 2 in a single name.\n\nMolty-social lanes (high adoption)\n\nwork, gig, bounty, crew, guild, team, coop\n\nVitality / sympoiesis lane (making-with)\n\nbloom, pulse, root, flow, kin, weave, garden\n\nNote: avoid militarized or de-individualizing metaphors by default (e.g., prefer crew/kin over swarm unless explicitly requested).\n\nCoordination lanes\n\nhandoff, relay, dispatch, route, queue, sync, link\n\nTrust lanes\n\nclaim, record, proof, attest, receipt, audit, verify\n\nMoney lanes\n\npay, tip, fund, split, settle, escrow\n\nNetwork lanes\n\nmesh, rail, hub, lane, ring, fabric, bridge\nStep 2 — Generate candidates (portmanteau patterns)\n\nUse these patterns in order of hit-rate.\n\nAlso: generate with TLD gravity in mind (you’re not naming in a vacuum).\n\nTLD-aware naming (gravitational pull)\n\nDefault TLDs: .eth / .ai / .com / .dao. When you output candidates, optionally tag the best-fit TLD(s).\n\n.eth: onchain identity + payments + trust primitives. Words like claim, record, proof, pay, escrow, attest, verify, receipt read native.\n.dao: governance + coordination + bounties + collective action. Words like bounty, guild, crew, vote, proposal, council, grants read native.\n.ai: tools, copilots, automation surfaces. Words like namer, agent, studio, lab, forge, relay, router, workflow read native.\n.com: broad public/brand surface. Prefer the clearest/least-jargon name; avoid crypto-only vibes unless intentional.\n\nRule of thumb: if you’re unsure, make the candidate compatible with .com clarity and let .eth/.dao carry the specialized meaning.\n\nNoun+Noun primitive: work+mesh → workmesh\nNoun+Place: bounty+hq → bountyhq\nNoun+Group: work+crew → workcrew\nAction+Noun: sync+crew → synccrew\nNoun+Rail (payments/settlement): pay+rail → payrail\nNoun+Log (provenance): claim+log → claimlog\n\nPrefer:\n\n6–10 chars\n2–3 syllables\nno hyphens (for ENS) unless requested\nStep 3 — Filter hard (kill list)\n\nRemove candidates that fail any of:\n\nPronounceability: awkward consonant pileups (e.g., “tskrl”) ⚠️\nAmbiguity: could mean 3+ different things without context ⚠️\nCringe / cutesy: feels like marketing copy, not tooling ⚠️\nConfusability: too close to common brands/protocols (avoid legal + social collisions) ⚠️\nPower/harms: surveillance/cop vibes (e.g., “track”, “snitch”, “police”), coercion (“enforce”), extractive framing (“harvest”) ❌\n\nConsent-forward / harm-reducing replacements (examples):\n\nprefer \"optin\" / \"consent\" / \"invite\" / \"handoff\" over “track / monitor / enforce”\nprefer \"receipt\" / \"record\" / \"proof\" over “snitch / police / punish”\nStep 4 — Reality + verbability + accessibility test\n\nFor each finalist, run these tests:\n\nA) Two sentences\n\n“Send it to ___ on NAME.”\n“We’re running bounties through NAME.”\n\nB) Verb test (must pass)\n\n“Just NAME it over.”\n\nC) 7-word definition (meaning compression) Write a 7-word definition. If you can’t, it’s not a primitive.\n\nD) Accessibility check (must not fail)\n\nScreen-reader friendly? (no lookalike characters, no weird punctuation)\nLow-bandwidth parse? (obvious segmentation; not a typo-soup)\nCross-accent tolerance? (don’t overfit to one phonetic norm)\n\nIf it reads naturally, keep it.\n\nStep 5 — Output format (what to return)\n\nReturn:\n\nState the target surface preset (ENS / Skill / Product).\nTop 5 (✅): name + best-fit TLD tag + 7-word definition + why it’s sticky (1 line)\nNext 10 (⚠️): name + micro-caveat\nSet Builder (optional, high leverage): 1 flagship + 4 satellites (pay/verify/claims/docs/api) in a consistent style\n\nTemplate example (Set Builder output)\n\nFlagship: workcrew (best: .com/.ai) — “A crew that ships work together, fast.”\nSatellites:\ncrewpay (best: .eth/.dao) — “Payout rails for crews and bounties.”\ncrewclaim (best: .eth) — “Claims + receipts for shipped work.”\ncrewverify (best: .eth/.ai) — “Verify who did what, when.”\ncrewdocs (best: .com/.ai) — “Human-readable rules, docs, how-to.”\n\nNotes:\n\nKeep morphology consistent (crew/mesh/rail/hq), then vary the role word.\n\nIf flagship is generic, add one vitality marker (e.g., bloomcrew) but only if it stays legible.\n\nFallback transforms (mutation ladder)\n\nAvoid long essays.\n\nFallback transforms (when everything is taken)\nMutation ladder (use in order, report which rung you used)\n\nWhen names are taken, don’t thrash. Walk the ladder:\n\nSwap suffix (network/place): mesh → hub → lane → rail → hq\nSwap group word: crew → guild → coop → team → swarm\nSwap work noun: gig → work → task → job → quest\nPluralize: crew → crews, guild → guilds (keeps meaning, increases availability)\nAdd one clarifier syllable: pay → payout, claim → claims, proof → proofs\nLengthen by ≤2 chars: prefer meaning over ultra-short\n\nUse these to generate “still intuitive” alternatives:\n\nswap mesh ↔ net ↔ hub ↔ lane ↔ rail ↔ hq\nswap crew ↔ guild ↔ coop ↔ team ↔ swarm\nswap pay ↔ tip ↔ fund ↔ split ↔ settle\npluralize: crew → crews (often available and still readable)\nAvailability checking (Web3 + ICANN) (optional)\n\nGoal: let the user choose how automated the checking should be, while keeping zero-barrier manual mode always valid.\n\nChoose a mode (ask once, then remember preference)\n\nOffer 3 modes; default to Manual:\n\nManual (zero keys, lowest friction) ✅\n\nReturn clickable search URLs for each provider.\nFast, resilient to captchas/UI changes.\n\nAssisted (browser-driven, best-effort) ⚠️\n\nUse a browser to open provider searches in tabs.\nWorks until a provider throws captcha / bot protection.\n\nAPI (highest automation, requires keys) ✅\n\nUse official APIs where available (e.g., GoDaddy) for deterministic checks.\nFall back to Manual links for providers without keys.\n\nAlways support mixed mode: “API for GoDaddy + Manual for ENS/UD.”\n\nChoose providers (top Web3 + ICANN)\n\nIf the user says “check top sites,” use this default set:\n\nWeb3 naming (common in agent circles)\n\nENS: https://app.ens.domains/\nUnstoppable Domains: https://unstoppabledomains.com/search\n\nICANN / DNS registrars (manual search works without keys)\n\nGoDaddy: https://www.godaddy.com/domainsearch/find\nNamecheap: https://www.namecheap.com/domains/registration/\nCloudflare Registrar: https://www.cloudflare.com/products/registrar/\nPorkbun: https://porkbun.com/\nDynadot: https://www.dynadot.com/domain/search\nHover: https://www.hover.com/domains\nGandi: https://www.gandi.net/en/domain\nSquarespace Domains: https://domains.squarespace.com/\n\nIf the user prefers a smaller list (speed), ask for their “top 3” and remember it.\n\nRemember preference (important)\n\nIf the user specifies:\n\nmode (Manual/Assisted/API)\nproviders (e.g., ENS + GoDaddy + Namecheap)\nTLD favorites (e.g., .eth,.dao or .com,.ai)\n\n…then remember that as their default for future naming sessions.\n\nRecommended memory format:\n\nTLD_FAVORITES: .eth,.ai,.com,.dao\nHow to run the check (recommended UX)\n\nStep A — Generate candidates\n\nProduce Top 5 ✅ + Next 10 ⚠️ as usual.\nIf the user needs a bundle, run Set Builder immediately (flagship + satellites).\n\nStep B — Check availability\n\nIn Manual mode: for each candidate, output provider search links.\nIn Assisted/API mode: run what you can; for what you can’t, output links.\n\nStep C — Backup loop (tight + fast) If a name is taken:\n\nGenerate 3–8 closest alternates (fallback transforms).\nCheck alternates using the same mode/providers.\nReturn the first set that clears the user’s constraints.\n\nTruthfulness rule: never say “available everywhere” unless every provider was checked successfully. Use:\n\n✅ likely available (checked)\n⚠️ unknown (not checked / captcha)\n❌ taken (confirmed)\nHelper script (optional)\n\nUse scripts/check.mjs to print a batch of provider URLs for quick manual checking.\n\nENS-specific guidance (optional)\n\nIf the task is ENS buying:\n\nProduce batches of 10–20 to try quickly.\nKeep a “miss list” (taken) and mutate via fallback transforms.\nUse the availability-check flow above when possible; otherwise output manual check links.\nAdvanced: “missing primitive finder” (connection-making)\n\nWhen the user describes a workflow, identify missing primitives and propose names for them.\n\nNamespace pollution guardrail (anti-generic)\n\nIf a candidate is too generic (likely to be produced by many agents), prefer one of:\n\nadd a vibe marker (vitality lane) that still reads clean\nadd a role marker (pay/verify/claims/record)\nproduce a set (flagship + satellites) so the ecosystem has handles, not mush\nSocial liquidity check\n\nPrefer names that will be adopted socially (easy to repeat, easy to tag, easy to remember) over “technically available but socially dead.”\n\nAlso run lightweight confusion safety checks on finalists (complementary to linguistic humility):\n\n2am test: does it visually parse under low cognitive load (tired, small screen)?\nDictation test: would voice-to-text likely capture it across accents?\nTypo radius: avoid names where one-letter typos become other common words.\n\nImportant: the 2am test is about visual parsing, not “Western mouthfeel.” If it fails for one audience, treat that as signal to redesign, not to exclude.\n\nCommon missing primitives in agent economies:\n\nhandoff artifact (context bundle) → “workpack”, “taskpack”\nreceipt for work (verifiable) → “workreceipt”, “claimreceipt”\nbounty lifecycle (post→claim→deliver→payout) → “bountyloop”\ncrew split (multi-party payout) → “splithub”, “splitrail”\n\nWhen you propose a primitive, also propose:\n\n1 sentence of “what it is”\n1 sentence of “why moltys need it now”\nBundled resources\nFor curated building blocks and “molty-speak primitives”, read: references/blocks.md\nFor scripts to generate candidates in batches, run: scripts/forge.mjs (does not check availability)" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/OtherPowers/skill-namer", "publisherUrl": "https://clawhub.ai/OtherPowers/skill-namer", "owner": "OtherPowers", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/skill-namer", "downloadUrl": "https://openagent3.xyz/downloads/skill-namer", "agentUrl": "https://openagent3.xyz/skills/skill-namer/agent", "manifestUrl": "https://openagent3.xyz/skills/skill-namer/agent.json", "briefUrl": "https://openagent3.xyz/skills/skill-namer/agent.md" } }