brand-naming-method
/brand-naming-method
Generuje propozycje nazw marki, odsiewa je archetypami i regułami fonotaktycznymi, a pozostałe punktuje według dostępności domeny, nasycenia rynku i ryzyka znaku towarowego.
- Autor
- acaprino ↗
- Repozytorium
- alfio-claude-plugins ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 27.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 5
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 1
Brak sygnałów. Repozytorium zmienione 27.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Generuje propozycje nazw marki, odsiewa je archetypami i regułami fonotaktycznymi, a pozostałe punktuje według dostępności domeny, nasycenia rynku i ryzyka znaku towarowego.
Wyzwalacze z opisu
Oryginalny opis (EN)
Ideate brand names, filter against archetypes and phonotactic rules, and score survivors on domain availability, market saturation and trademark risk. TRIGGER WHEN: "brand name", "naming", "name my app", "name my product", "product name", "startup name", "come up with a name", "nome del brand", "naming strategico".
Jak działa
- Reference router
- BEFORE ANYTHING ELSE: Resolve the Brief
- Workflow
Podgląd SKILL.md
---
name: brand-naming-method
description: >
Ideate brand names, filter against archetypes and phonotactic rules, and score survivors on domain availability, market saturation and trademark risk.
TRIGGER WHEN: "brand name", "naming", "name my app", "name my product", "product name", "startup name", "come up with a name", "nome del brand", "naming strategico".
---
> `${PLUGIN_ROOT}` is this plugin's install directory, the one that holds its `plugin.json`. If the host has not expanded it, resolve it from where this file was loaded.
<daodan_host_binding host="copilot">
This binding governs execution of this package and its loaded references. It takes
precedence over executable examples written for another host. Use only registered
tools and their actual input schema; an example never creates a tool, argument,
permission, model alias or nested worker capability. Preserve the generated worker
allowlist, dependency closure, scope and delivery contracts.
Copilot binding: repository reads use search, writes use edit, shell execution uses
runCommands and network fetch uses fetch in the adapter's tool allowlist. Custom
agent dispatch uses the agent allowlist alias; the current CLI documents a task
dispatch tool. Call the mechanism actually registered in this session, not an
allowlist alias assumed to be a callable tool.
Use each registered tool's input fields; Claude's subagent_type, role and
run_in_background fields are not a portable dispatch schema. Dispatch only the
custom agent named by the generated owner-qualified binding and agents allowlist.
An omitted tools restriction retains host defaults; an explicit list constrains
the worker and does not grant omitted shell, write or MCP tools.
Skills use their exact installed registry identity; workflows are prompt entries.
A dispatched workflow also has its generated <workflow>-coordinator custom agent.
Required foreign providers use Copilot's marketplace/install commands:
copilot plugin marketplace add <source>, then copilot plugin install <provider>@<marketplace>.
Register plugin-declared MCP server commands in this host's MCP configuration as
the generated note directs. Registration and a dependency declaration alone do
not demonstrate that browser/server tools are callable by the selected worker.
Inherit the active session's model and default variant. A source model alias such
as sonnet is not a portable override; request a different model only through an
explicit adapter mapping to a valid host identity and user authorization.
Coordinator MCP allowances use <declared-server>/* for only the package's named
servers. This requires actual server registration and tool discovery; it grants
no undeclared server and does not prove MCP is callable in an installed run.
Schema reference: https://docs.github.com/en/copilot/reference/custom-agents-configuration
The executing agent and its coordinator own continuation, recovery, verification
and delivery. Skills supply knowledge and method instructions; they are not
executors or a runtime persistence mechanism.
Resolve each component by kind and exact installed identity. A role is dispatched
as a worker, a skill loads instructions, and a workflow starts its declared method.
Kernel owner-qualified skill references are logical provider identities: resolve
them to the actual host registry name and verified installed provider path. Do not
invent a registry string by adding an owner's prefix when the host does not use it.
Do not load an agent identity as a skill or execute a workflow name as a shell
command. Declared required foreign providers remain mandatory. If a required
provider or capability (including required MCP access or isolation) is unavailable,
stop its dependent phase and report the missing capability. Optional external
providers follow the method's declared selection and absence behavior; their
absence alone does not block the base workflow. Report any explicitly requested
but unavailable provider contribution as unfulfilled and continue independent
work. Do not install a different host's plugin or
substitute unrelated skills to claim coverage.
Shell execution alone does not establish interactive stdin. Before a capture or
checkpoint, use an available session-control mechanism. When stdin is unavailable,
keep user-driven capture in a supported background process with bounded output and
an explicit stop signal controlled by the coordinator after the user's completion
message. Close owned browser/process resources on completion or cancellation.
Continue working within the current authorization while the requested result is
achievable. After a tool error, inspect its cause, correct the relevant input or
implementation, retry when justified and verify the outcome; never repeat a
failing action blindly. Do not close the turn with a promise or a partial result
when an authorized next step can still produce or verify the requested result.
Stop only for a documented real impediment, a missing required capability, an
unresolved human decision or the caller's stop request. At that boundary, report
completed results, remaining work and the concrete prerequisite for continuation;
continue any independent work that the blocker does not prevent.
A tool's successful exit, a worker stop or an idle session is not the deliverable.
Return final text naming observed findings, artifact paths, executed checks and
blockers. An empty worker result is missing delivery: inspect or resume that worker
when permitted, or record failure. Verify required artifacts and candidate gates
before marking the requested outcome complete.
This is an execution binding, not a rewrite of source examples. Preserve programming
language fences, domain code and host APIs that are the subject of marketplace-ops
or agent-sdk-builder. A host-as-subject API is not a tool provided to this session.
Compiled binding and static checks do not prove an installed host executed a run.
</daodan_host_binding>
# Brand Naming Strategist
Ideate, filter, and validate brand names through a structured analytical workflow. Execute all steps inline in this conversation; do not delegate generation, filtering, domain checks, or scoring to a subagent or separate context.
## Reference router
| Need | Reference |
|---|---|
| Domain checker script flags, RDAP/whois/Patchright rules, Playwright MCP trademark register procedures (UIBM, TMview, USPTO, WIPO), phonotactic refinement, and fail-fast market saturation checks | `references/screening-and-domains.md` |
| Archetypes, Spellbrand 5 tests, phonosymbolism research, case studies, and register URLs | `references/naming-frameworks.md` |
| Final Markdown report structure and table templates | `references/report-template.md` |
## BEFORE ANYTHING ELSE: Resolve the Brief
The brief has six fields (Step 1) plus a reference country. Resolve them before any output, without greetings or blank questionnaires:
- **Branch A (user message supplies 4+ brief fields):** Extract the brief directly from the message/conversation. Do not scan the working directory (which may be an unrelated repo). Present the extracted brief for confirmation and proceed to Step 1.
- **Branch B (thin brief or user references a local project/app):** Read project files silently first (`README.md`, `CLAUDE.md`, `package.json`/`pyproject.toml`/`Cargo.toml`, landing copy, `docs/`). Present a pre-filled inferred brief for confirmation and ask only for fields that could not be inferred.
- **Branch C (user supplies candidate names to vet):** Skip Step 2 generation and Step 3c refinement. Run Steps 1b, 3, 3b, 4, 5, and 6 across all supplied names (recording removals in "Names removed"), and score every survivor in Step 7. Mark unreadable screenshot names as `unreadable`.
- **Reference country (all branches):** Needed before Step 1 to grade national trademark risk in Step 5. Take it from `--country`, the brief, or project metadata (address, currency, locale, copy language). If still unknown, ask: *"Which country is the reference market for the trademark check?"*
## Workflow
### Step 1: Brief Analysis and Sector Ban List
Confirm the brief fields:
1. Industry/sector and competitive landscape
2. Target audience
3. Core values and emotions
4. Tone (playful, serious, premium, technical, natural)
5. Target languages/markets (default: `en, it, es, fr, de, pt`, or `--languages`)
6. Constraints (length, letter preferences, sounds to avoid)
7. Reference country and assumed Nice classes (e.g. 9 and 42 for software)
Create and display a **Sector Ban List** of the 5-10 most overused prefixes, suffixes, and roots in the target sector (e.g. Fitness: `Fit, Nutri, Cal, Diet, Meal, Gym, Health, Body, Lean`; AI/Tech: `AI, Bot, Mind, Think, Brain, Smart, Logic, Synth, Cogni, Neural`; Finance: `Fin, Pay, Cash, Coin, Money, Wealth, Capital, Fund`; Travel: `Trip, Tour, Fly, Go, Wander, Roam, Trek, Voyage`).
### Step 1b: Instant Kill Pre-screening
Apply during generation:
- Never use morphemes from the Sector Ban List.
- Reject common words native to the sector. Single dictionary words are allowed only if obscure, archaic, or decontextualized from an unrelated domain (like Apple, Slack, Notion).
### Step 2: Strategic Semantic Generation (12-15 Curated Names)
Do not invent meaningless syllable combinations (no CVCV letter-mashing like "Nivo", "Rivo", "Zivo"), do not use cheap suffixes (`-ify`, `-ly`, `-io`), and do not staple two obvious words together. Generate **12-15 real, obscure, or decontextualized words** across four directions, each with `[Name] (X chars): [Etymology/Origin]. Brand Story: [1-sentence strategic fit]`:
1. **Etymological Hijacking:** Obscure, modern-looking words from Ancient Greek, Latin, Sanskrit, or philosophy (`Eidos`, `Kalon`).
2. **Scientific & Mathematical Decontextualization:** Precise terms from physics, biology, mathematics, or navigation applied metaphorically (`Basal`, `Ratio`, `Zenith`).
3. **The Metaphorical Shift:** Terms from art, architecture, or nature describing the product's function with a 1-second "aha!" connection (`Tessera`, `Kroma`).
4. **The Phonetic Real-Word:** When a short phonetic shape (such as CVCV) is requested, select real words with strong meaning (`Vela`, `Soma`, `Nova`) rather than coined strings.
### Step 3: Linguistic and Cultural Filtering (Filter to 8-10)
Filter the 12-15 candidates down to the best **8-10** by verifying:
- Pronunciation ease and absence of negative/offensive meanings across all target languages (defaulting to `en, it, es, fr, de, pt`, plus Chinese and Japanese when global/Asian markets apply).
- Phonosymbolism alignment with brand tone (see `references/naming-frameworks.md`).
- No phonetic collision with profanity, disease, or major existing brands.
### Step 3b: Quick Domain Gate
Read `references/screening-and-domains.md` (Section 1) and run `${PLUGIN_ROOT}/skills/domain-hunter/scripts/domain_checker.py` once across all 8-10 candidates for `.com, .app, .io, .co` (or `--tlds`).
- Keep the registration table for Steps 4 and 6a.
- List every dropped name with the exact reason (which TLDs were taken and by whom), generate replacements via Step 2, and re-filter.
### Step 3c: Phonotactic Refinement
For promising-but-rough survivors, apply the Refinement Toolkit in `references/screening-and-domains.md` (Section 2): vowel swaps, consonant softening, suffix shifts, or clipping.
### Step 4: Domain and Social Check
Reuse the Step 3b domain table (showing any unread TLD as `unverified`, never `free`) and check social handle availability via web search. Present:
`| Name | .com | .app | .io | Twitter/X | Instagram |`
For registrar price comparison and purchase guidance on finalists, point to `digital-marketing:domain-hunter`.
### Step 5: Trademark Pre-screening
Read `references/screening-and-domains.md` (Section 3) and `references/naming-frameworks.md`. Query the required trademark registers for the **Reference country**, **Europe** (EUIPO TMview / eSearch plus), and **World** (WIPO Global Brand Database + USPTO) using the `playwright` MCP browser tools in headless mode:
- Pace queries sequentially, check spaced variants, verify that each page is a genuine result list (recording WAF/error pages as `NOT SCREENED: <register>`), and run WIPO phonetic search on finalists.
- If Playwright MCP is unavailable, stop and print the recovery block in `references/screening-and-domains.md`.
- Grade each territory **A**, **B**, **C**, **D**, or **NS**. A **D in the reference country** removes the name at Step 5; a D in Europe or World lowers the Step 7 score and enters "Before you commit".
### Step 6: Market Saturation Analysis (Fail-Fast)
Follow `references/screening-and-domains.md` (Section 4) in fail-fast order:
- **6a. Domain activity gate** (`ACTIVE BUSINESS` in same sector -> discard immediately and replace; `PARKED`; `AVAILABLE`)
- **6b. App store saturation** (`SATURATED` / `MODERATE` / `CLEAR`)
- **6c. SERP saturation (Google Test)** (`DOMINATED` / `COMPETITIVE` / `OPEN`)
- **6d. Social media presence** (`TAKEN BY BRAND` / `INACTIVE/PERSONAL` / `AVAILABLE`)
- **6e. Industry-specific saturation** (`LOW` / `MEDIUM` / `HIGH` / `BLOCKED`)
- **6f. SEO Potential** (`HIGH` / `MEDIUM` / `LOW`)
Summarize in: `| Name | Domain Status | App Stores | SERP | Social | Industry | Overall Risk |`.
### Step 7: Scoring and Ranking
Score the 5 survivors from 1 to 5 (whole numbers: 5 excellent, 4 good, 3 acceptable/unverified, 2 weak, 1 poor) using these weights:
| Criterion | Weight | Description |
|---|---|---|
| Memorability | 15% | Easy to recall after one hearing (Phone Test: 70%+ recall) |
| Distinctiveness | 15% | Unique vs competitors, not generic |
| Market Saturation | 15% | Low saturation across domains, app stores, and SERP (inverted: low saturation = high score) |
| Simplicity/Pronunciation | 10% | Easy to say and spell (Spelling Test: 80%+ accuracy) |
| Relevance | 10% | Connection to brand values and product |
| SEO Potential | 10% | Organic discoverability and SERP openness |
| Domain Availability | 10% | `.com` or strong alternative TLD available |
| Trademark Risk | 5% | Reference country class (`A`=5, `B`=4, `C`=2, `D`=1), minus 1 (floor 1) if Europe or World is worse; if Reference country is `NS`, cap at `3 (not screened)` |
| Emotional Impact | 5% | Evocative power and storytelling potential |
| Cultural Adaptability | 5% | Works cleanly across all target languages |
Every score cites concrete evidence. A check that could not run at all (e.g. SEO Potential when SERP lookup was unavailable) is marked `not scored`, omitted from the weight denominator, and listed in "Before you commit".
Formula: `Overall = SUM(criterion_score * weight) / SUM(weight of scored criteria)`, rounded to one decimal. Break ties on Distinctiveness, then Market Saturation.
### Step 8: Evaluation Report
Read `references/report-template.md` and populate every section in order (1. Summary, 2. Scorecard, 3. Top 3 names, 4. Runners-up, 5. Names removed, 6. Before you commit, 7. Evidence) in the language of the brief. Every score across all 10 criteria for all 5 ranked names must include a one-sentence evidence-backed motivation.
Use the caller's owned run output directory when supplied; otherwise use the
user's selected output directory or a dedicated `.brand-naming/` directory inside
the current workspace. Write this native
Markdown report once to the user's requested report path, or
`brand-naming-report.md` in the owned output directory when no filename was given.
Keep required motivations, evidence and unknown states; do not shorten the checks
or regenerate the same content for another layout. Link to the saved report in the
conversation with the recommendation and open checks.
When the user requests HTML, or exploring the scorecard's weights would materially
help the choice, load the `report-rendering:report-renderer` skill and resolve its helper
through that skill. Render the saved Markdown with `--profile naming`, `--input`
set to that report, `--output` set to its same-stem `.html` sibling and `--root`
set to the same dedicated owned output directory. If the user selected a native
report path in the repository root or a shared directory, keep that Markdown path
and place its HTML in a dedicated `.brand-naming/` subdirectory instead; pass that
subdirectory as `--root`. The provider rebases relative evidence links to preserve
their targets. The fixed renderer supplies presentation
controls; do not author another HTML/CSS layout or new report content. Preserve the
template's sections, evidence, provisional values and original recommendation.
Weight changes are exploratory as the native template explains. Verify the helper
outcome before linking the HTML. On failure preserve Markdown and report the
optional view failure; an explicitly requested HTML deliverable remains open.
Pliki w paczce (5)
- SKILL.md 16 KB
- SKILL.toml 1 KB
- references/naming-frameworks.md 17 KB
- references/report-template.md 14 KB
- references/screening-and-domains.md 12 KB
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · acaprino/alfio-claude-plugins | 100 | MIT |
| acaprino/alfio-claude-plugins | 100 | MIT |
| acaprino/alfio-claude-plugins | 100 | MIT |
| acaprino/alfio-claude-plugins | 100 | MIT |
| acaprino/alfio-claude-plugins | 100 | MIT |
| acaprino/alfio-claude-plugins | 90 | MIT |
Identyczna treść występuje jeszcze w 1 innych folderach na GitHubie. Tu pokazujemy jedną, najlepiej ocenioną kopię.
Migawka bazy z 13.11.2026 · wersja paczki ec69561ecabf (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 1 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100arn-spark-naming
Prowadzi przez wymyślanie nazwy marki produktu: analiza strategiczna, generowanie pomysłów, ocena jakościowa i sprawdzenie dostępności. - 100brand-naming
Generuje ponad dwadzieścia propozycji nazw marki lub produktu w pięciu archetypach, ocenia je według ważonych kryteriów i sprawdza językowe oraz zapamiętywalnościowe ryzyka. - 100brand-naming-strategies
Pomaga nazwać lub zmienić nazwę firmy, produktu lub startupu: generowanie i ocena kandydatów, testy SMILE i SCRATCH, symbolika dźwięku, dostępność domeny i wstępna kontrola znaków towarowych. - 100brand-naming-lab
Tworzy nazwy marki dla produktów, usług i projektów w 8 klasycznych metodach, z objaśnieniem znaczenia, logiki i domeny oraz oceną bezpieczeństwa międzykulturowego i rejestrowalności znaku. - 100naming-is-hard
Interaktywnie pomaga wybrać nazwę projektu, produktu, repozytorium, firmy, pakietu lub funkcji, którą da się naprawdę używać, w tym sprawdza dostępność domeny, organizacji GitHub, npm i znaku towarowego. - 100brand-domain-research
Wymyśla nazwy marek, produktów lub projektów, proponuje pasujące domeny i sprawdza ich rejestrację, gdy trzeba wybrać nazwę.