Laravel Specialist
Jeffallan/claude-skills
Builds Laravel 10+ applications with Eloquent models, Sanctum authentication, Horizon queues, API resources and Livewire components, tested with Pest or PHPUnit.
[RU: интеграция mutagen.ru — частотность Яндекс, конкуренция, SERP-отчёты] Mutagen.ru REST API — RU SEO tool: точная частотность Yandex Wordstat, уровень конкуренции (strong), биды Директа, async…
$ npx skills add VKirill/claude-lane-stack --skill mutagen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VKirill/claude-lane-stack mutagen --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lane-stack/skills/seo-tools/mutagen .claude/skills/mutagen && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mutagen" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagen into .claude/skills/mutagen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mutagen", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagenType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VKirill/claude-lane-stack --skill mutagen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VKirill/claude-lane-stack mutagen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/lane-stack/skills/seo-tools/mutagen .agents/skills/mutagen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mutagen" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagen into .agents/skills/mutagen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mutagen", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VKirill/claude-lane-stack --skill mutagen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VKirill/claude-lane-stack mutagen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/lane-stack/skills/seo-tools/mutagen .cursor/skills/mutagen && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mutagen" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagen into .cursor/skills/mutagen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mutagen", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VKirill/claude-lane-stack.git --path plugins/lane-stack/skills/seo-tools/mutagen--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VKirill/claude-lane-stack --skill mutagen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VKirill/claude-lane-stack mutagen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/lane-stack/skills/seo-tools/mutagen .gemini/skills/mutagen && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mutagen" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagen into .gemini/skills/mutagen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mutagen", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VKirill/claude-lane-stack mutagenInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VKirill/claude-lane-stack --skill mutagen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/lane-stack/skills/seo-tools/mutagen .github/skills/mutagen && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mutagen" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagen into .github/skills/mutagen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mutagen", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VKirill/claude-lane-stack --skill mutagen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VKirill/claude-lane-stack mutagen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/lane-stack/skills/seo-tools/mutagen .opencode/skills/mutagen && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mutagen" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/seo-tools/mutagen into .opencode/skills/mutagen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mutagen", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
mutagen[RU: интеграция mutagen.ru — частотность Яндекс, конкуренция, SERP-отчёты] Mutagen.ru REST API — RU SEO tool: точная частотность Yandex Wordstat, уровень конкуренции (strong), биды Директа, async…
Mutagen is an agent skill from VKirill/claude-lane-stack. [RU: интеграция mutagen.ru — частотность Яндекс, конкуренция, SERP-отчёты] Mutagen.ru REST API — RU SEO tool: точная частотность Yandex Wordstat, уровень конкуренции (strong), биды Директа, async checkkey polling, parser.mass batch jobs, serp.report mega-tool with 22+ report types. Use when: mutagen, mutagen.ru, мутаген, api.mutagen.ru, точная частотность, частотность яндекс вордстат, конкуренция директа, mutagen.checkkey, mutagen.parser.mass, mutagen.serp.report, mutagen.balance, clasterid, wordstatqso…
Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including reference files (for example `CHANGELOG.md`, `references/REFERENCE.md` and `references/batch-strategy.md`).
It sits in Backend & APIs, covering Background jobs and REST APIs. It works with Ahrefs. The repository describes itself as: Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 45fa19e. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
mutagen.ruapi.mutagen.ruFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
MUTAGEN_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Mutagen loads about 5.2k tokens when it runs, and up to ~41k if it reads all its reference files. Until then it costs about 224 tokens; SKILL.md has 2,029 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from VKirill/claude-lane-stack at commit 45fa19e, republished under its MIT licence (© VKirill). 2,029 words, ~5,194 tokens.
.claude/skills/mutagen/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.<!-- versions:start -->
Primary pins:
docs-only (stable JSON REST, no version path)3.14.x24.x (Active LTS)Source of truth: STACK_VERSIONS.md — verified 2026-08-24
<!-- versions:end -->
Loaded automatically when its description matches the active task. Read only the section you need, then follow the link to the relevant reference file for full detail.
mutagen.parser.mass.new (wordstat_qso для "[!фраза]")strong) ключевых фраз через async mutagen.check_key.new + mutagen.check_key.get pollingdirect.spec / direct.first / direct.garant) для оценки стоимости трафикаwordstat_key (до 2000 ключей, 10 страниц) или wordstat_key_50 (первые 200 с первой страницы)mutagen.serp.report — конкуренты домена, упавшие/поднявшиеся фразы, хвосты, страницы домена, дополняющие фразыclaster_id — mutagen.progects() + mutagen.progect.keywords(progect_id) для кластеризации семантического ядраwordstat-api (cascade marker)key-collector (cascade marker)httpx, nodejs, python)Mutagen.ru is one of the dominant Russian SEO SaaS providers, used by SEO specialists, agencies, and content teams to collect Yandex semantic cores. Its core differentiator: cheap pay-per-call access to Wordstat exact-frequency variants (wordstat_qso = "[!фраза]"), proprietary competition metric (strong, scale ~1-25+), and a mega-tool serp.report covering 22+ report types — keyword info, organic positions, PPC bids, domain competitors, page-level analysis, lost/new/rising/falling keywords, и т.д.
This skill is high-stakes because every paid method debits the merchant balance per call, and incorrect polling/batching patterns burn money:
check_key.new creates a paid async task; calling it twice on the same keyword without persisting task_id doubles the spend.parser.mass.new charges per keyword in the batch — not deduplicating means paying for duplicates.serp.report with wrong region returns RU-wide data instead of city-specific, leading to wasted budget when re-running.created → processed → completed | rejected | error) requires correct polling with exponential backoff — naive tight loops waste rate limits and create runaway poll storms.The skill owns provider-domain knowledge — method shapes, parser-type semantics, region codes, filter/sort/count semantics, polling lifecycle, billing safety. HTTP plumbing belongs to the runtime skill (httpx, nodejs).
If you are working inside the mcp-mutagen MCP server, the raw Mutagen async API is already wrapped for you. Two tools are available:
mutagen_api — generic gateway to the full Mutagen API: SERP reports (serp.report with all 23 report types), balance, projects, and keyword analytics. Handles async polling automatically. See references/cookbook.md for ready-to-run recipes.mutagen_competition — convenience tool for batch keyword competition checks (check_key), with deduplication and 30-day caching built in.Use mutagen_competition for batch competition scoring; use mutagen_api for everything else.
mutagen_competition({
phrases: string[], // required — one or more Russian search phrases
poll_timeout_sec?: number, // optional — max seconds to wait for results (default: 60)
force_refresh?: boolean, // optional — bypass 30-day result cache (default: false)
})For each phrase: strong (competition score 1-25), wordstat (Wordstat frequency), direct.spec / direct.first / direct.garant (Yandex Direct bid estimates in RUB).
check_key.new for each phrase, persists task_id internally.check_key.get with exponential backoff until completed or timeout.force_refresh: true to re-query and overwrite the cache.~0.30 RUB per phrase. Results are cached 30 days, so repeating the same phrase within the TTL costs nothing. Before calling with a large list, verify your Mutagen balance — use mutagen.balance() directly (curl or a one-off script) or check your account dashboard at https://mutagen.ru/?api_config. A negative balance causes all tasks to be rejected.
mutagen_competition({phrases: ["ремонт квартир москва", "купить машину"]})Returns an array of two result objects, one per phrase, with strong, wordstat, and direct fields.
Use the raw check_key.new + check_key.get pattern (documented below) when you need: custom polling timeouts, streaming partial results, or integration outside the mcp-mutagen runtime.
Single endpoint pattern: http://api.mutagen.ru/json/{api_key}/{method}/?{params}. API key in the URL path (obtain at https://mutagen.ru/?api_config). UTF-8 required for all requests and source files. GET hard-limit 128KB — anything above MUST use POST with JSON-encoded params in body. Response envelope shape varies by method; status field carries lifecycle for async calls.
Full reference: references/setup.md
Account: mutagen.balance (баланс). Projects/Избранное: mutagen.progects, mutagen.progect.keywords (with claster_id for кластеризация). Async competition: mutagen.check_key.new + mutagen.check_key.get. Parser: mutagen.parser.get (single) + mutagen.parser.mass.new/mass.list/mass.id (batch). SERP mega-tool: mutagen.serp.report (22+ report types × 9 regions × 17 filter types).
Full reference: references/methods.md
check_key pattern (state machine)State flow: created → processed → completed | rejected | error. Poll check_key.get(task_id) with exponential backoff starting at 2-3 s capped at 30 s, max 60 attempts. While not completed, response mirrors check_key.new: {task_id, status}. On completed: returns key, strong (конкуренция), wordstat, tails, direct.{spec,first,garant} (ставки в Директе), vital, vital_site (тематический сайт). CRITICAL: persist task_id so retries on transient errors don't double-spend. rejected is terminal — re-submitting blindly re-charges.
Full reference: references/check-key-async-pattern.md
Nine parser types map to Wordstat modifier semantics: wordstat_n (broad, no quotes), wordstat_q ("" phrase match), wordstat_qs (!"" exact form), wordstat_no ([] order-locked), wordstat_qo ("[]"), wordstat_qso ("[!]" — точная частотность, эталон для SEO), wordstat_key (левая колонка Вордстата, до 2000 ключей, 10 страниц + правая колонка/ассоциации), wordstat_key_50 (первые 200 с первой страницы), direct (биды Директа со shows/bid1/bid2/bid3/all_positions). Picking the wrong variant gives wrong frequency and wastes budget.
Full reference: references/parser-types.md
mutagen.serp.report is a single endpoint switching on the report parameter. Keyword reports (require keyword / keywords CSV ≤1000): report_keyword_info, report_keyword_tailings (хвосты), report_keyword_variations, report_keyword_expansion (дополняющие фразы), report_keyword_positions_organic, report_keyword_positions_ppc. Domain reports: report_keywords_organic + _up/_down/_new/_lost (поднявшиеся/упавшие/новые/потерянные), report_keywords_ppc, report_keywords_ppc_history, report_domain_pages, report_domain_subdomains, report_domain_competitors, report_domain_competitors_ppc, report_domain_advert, report_domain_advert_active, report_domain_info. Page reports: report_page_info, report_page_competitors, report_page_recommended_keywords.
Full reference: references/serp-report.md
17 filter types: gr (>), gr_or_eq (>=), less (<), less_or_eq (<=), eq (=), not_eq (!=), range (min+max numeric), in/not_in (CSV list up to 1024), like/not_like (substring), like_any/not_like_any (CSV up to 1024), like_start/like_finish (prefix/suffix), is (boolean). Combine with "or":1 marker to start an OR-block (default AND). Sort: "column" asc or "-column" desc, one column per request. count: 1 returns only {"count": N} — use for cheap row-count probes before paginating.
Full reference: references/filtering.md
For serp.report: nine region values — yandex_ru (global, keyword-only reports), yandex_msk, yandex_spb, yandex_minsk, yandex_nsk, yandex_ekb, yandex_rostov, yandex_kazan, yandex_nn. For parser methods: region_id="0" = no region (default); numeric region codes accepted as comma-separated list, - prefix excludes (e.g. "255,-17"). Mismatch between intended region and actual call returns useless data — region-specific frequency differs by orders of magnitude.
Full reference: references/regions.md
Mutagen is pay-per-call. mutagen.balance() returns current rubles. Documentation does NOT publish per-call costs in the API page — verify current tarification at https://mutagen.ru/?p=price. Pattern: always call mutagen.balance() before any paid batch and gate operation on balance >= expected_cost * 2. Track expected cost client-side (count of keys × known per-call rate from your account dashboard).
Full reference: references/pricing-and-balance.md
parser.mass over loopsparser.mass.new accepts keys_list (array or CSV) with a name tag for tracking; returns {id, status}. Poll parser.mass.id(mass_id) until status: "finish". Always deduplicate keys_list before submit (case-fold + trim Cyrillic) — duplicates are charged. Single-shot parser.get is for one-off probes only; never loop over parser.get — use parser.mass.new for ≥2 keys.
Full reference: references/batch-strategy.md
claster_idmutagen.progects() lists user projects ({progect_id, name}). mutagen.progect.keywords(progect_id) returns [{keyword, claster_id}] — the cluster id is the link to the кластеризация tool on the site (/?p=clasterization). Use projects for ops tracking, not pipeline state.
Full reference: references/projects-and-clustering.md
httpx.AsyncClient with tenacity exp-backoff retry on transient errors, pydantic envelope schemas, env var MUTAGEN_API_KEY, polling helper for check_key/parser.mass, dedup helper for keys_list, balance pre-check.
Full reference: references/integration-python.md
fetch / axios with retry, TypeScript types per method, env-based key, polling pattern via setTimeout exp-backoff, batch dedup.
Full reference: references/integration-node.md
mutagen.balance() BEFORE any paid batch (check_key.new, parser.mass.new, serp.report); gates execution on balance ≥ expected_cost × 2task_id (check_key) and mass_id (parser.mass) to durable storage BEFORE the first poll — recovery after crash must not re-submit and re-chargecheck_key.get / parser.mass.id with exponential backoff starting 2-3 s, cap 30 s, max 60 attempts — never tight-loopsparser.mass.new for ≥2 keys instead of a parser.get loop — batching reduces per-call overheadkeys_list (case-fold + strip Cyrillic whitespace) BEFORE submit — duplicates are chargedregion explicitly on serp.report; never relies on defaults — region mismatch silently returns wrong datacount: 1 on serp.report to probe row count before paginating with limit — cheap probe over expensive full fetchkeys_list or long filter chainsapi_key from MUTAGEN_API_KEY env var; scrubs from access logs (key is in URL path)rejected and error statuses as terminal — never auto-resubmits without explicit handlingapi_key in source, commit history, or client bundles — it grants full balance-spending powercheck_key.new or parser.mass.new without a prior mutagen.balance() check and known per-call costcheck_key.new on the same keyword twice without checking persistent task_id first — double-chargescheck_key.get / parser.mass.id — use exp backoff (2-3 s → 30 s cap, max 60 attempts)rejected / error — terminal states, requires manual triageyandex_ru is global keyword-only, city codes give regional SERP / frequencyapi_key is in the URL path and ends up in nginx access logs / APMstatus, presence of task_id / id / data) before reading domain fields90%-filter applied — mainstream 2026 choices used in RU SEO pipelines.
httpx — Python async HTTP client (primary runtime for SEO scripting)python — Python 3.14 (parent runtime for SEO scripting)nodejs — Node 24 (alternative runtime)pydantic — validate Mutagen envelopes (status field, completed-vs-pending response shapes)pytest — test polling logic, dedup, balance gating against fixturesproxy6 — RU SaaS skill (high-stakes pattern reference; pay-per-call, polling)cloudpayments — RU payment SaaS (high-stakes pattern reference)yookassa — RU payment SaaS (high-stakes pattern reference)redis — Redis 8 (task_id / mass_id cache, idempotency dedup)postgresql — PostgreSQL 18 (semantic core storage, batch state, claster_id mapping)bullmq — BullMQ 5 (background poller for check_key / parser.mass)karpathy-guidelinesDomain-specific references (Pattern 2) — load only what's relevant:
| Topic | File |
|---|---|
| Index, decision map, when-to-use which doc | references/REFERENCE.md |
| API key handling, base URL, UTF-8, GET vs POST 128KB limit, dashboard | references/setup.md |
| Every method — signature, params, response shape, examples | references/methods.md |
check_key async lifecycle — state machine, polling, idempotency, rejected handling | references/check-key-async-pattern.md |
| Parser types — wordstat_n/q/qs/no/qo/qso/key/key_50/direct, semantics, response shapes | references/parser-types.md |
| All 22+ serp.report types, when to use which, response shape, key columns | references/serp-report.md |
| All 17 filter_types, OR-blocks, sort syntax, count=1 row count | references/filtering.md |
| Regions — yandex_ru/msk/spb/minsk/nsk/ekb/rostov/kazan/nn + parser region_id codes | references/regions.md |
| Pricing model, balance pre-check pattern, daily quota safety | references/pricing-and-balance.md |
| Batch strategy — parser.mass over parser.get, dedup, batch size, polling | references/batch-strategy.md |
| Projects (Избранное) — mutagen.progects, progect.keywords, claster_id, кластеризация | references/projects-and-clustering.md |
| Python integration — httpx, tenacity, pydantic, asyncio, polling helper | references/integration-python.md |
| Node.js / TS integration — fetch / axios, types, retry, polling | references/integration-node.md |
| Recommended defaults — SSOT: timeouts, polling backoff, batch size, balance threshold | references/recommended-defaults.md |
| Wrong vs Right — paired anti-patterns: key leakage, polling without backoff, missing balance check, duplicate keys, region mismatch | references/wrong-vs-right.md |
| Troubleshooting — symptom-indexed: balance 0, stuck on processed, rejected loops, 128KB rejection, encoding, attribution | references/troubleshooting.md |
| Eval cases — routing tests (positive RU/EN + negative + edge) | references/eval-cases.md |
| Cookbook — mutagen_api recipes: free-tier methods, Top-4 SERP reports, all 23 report types table, async polling, pitfalls | references/cookbook.md |
How to use: open the topic file relevant to the current task. New integration → setup.md + integration-python.md or integration-node.md. Async work → check_key-async-pattern.md + batch-strategy.md. SERP analysis → serp-report.md + filtering.md. Tuning → recommended-defaults.md. Audit existing code → wrong-vs-right.md.
© VKirill, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 19 other files (references) in plugins/lane-stack/skills/seo-tools/mutagen of VKirill/claude-lane-stack.
Open the folder on GitHubat commit 45fa19e
Mutagen next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mutagen this skillVKirill/claude-lane-stack | 122 | — | ~5.2k | Automated safety check: Pass | MIT | |
| Laravel SpecialistJeffallan/claude-skills | 12k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Polylith Base CreationDavidVujic/python-polylith | 553 | — | ~757 | Automated safety check: Pass | MIT | |
| Frappe App Devfrappe/skills | 147 | — | ~943 | Automated safety check: Pass | None | |
| Function Devbutterbase-ai/butterbase-skills | 534 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Sap Btp Job Schedulingsecondsky/sap-skills | 462 | — | ~3.6k | Automated safety check: Pass | GPL-3.0 |
Jeffallan/claude-skills
Builds Laravel 10+ applications with Eloquent models, Sanctum authentication, Horizon queues, API resources and Livewire components, tested with Pest or PHPUnit.
DavidVujic/python-polylith
Create a Polylith base with poly create base — the entry point of a deployable application (HTTP API, CLI, message-queue consumer, AWS Lambda handler, GCP Cloud Function, scheduled job).
frappe/skills
Builds full-stack Frappe Framework applications end-to-end. An agent skill from frappe/skills.
butterbase-ai/butterbase-skills
A skill your agent uses when developing, deploying, or debugging Butterbase serverless functions, or when the user needs to add backend logic like webhooks, scheduled jobs, or custom API endpoints
secondsky/sap-skills
This skill provides comprehensive guidance for SAP BTP Job Scheduling Service development, configuration, and operations.
forcedotcom/sf-skills
Primary Apex authoring skill for class generation, refactoring, and review.
VKirill/claude-lane-stack
Lane-stack design + brand intelligence (vendored ui-ux-pro-max).
VKirill/claude-lane-stack
Owner-facing architect for a new app or service. An agent skill from VKirill/claude-lane-stack.
VKirill/claude-lane-stack
Live browser QA + Playwright-compatible replay. An agent skill from VKirill/claude-lane-stack.
VKirill/claude-lane-stack
Карта файлов копирайта в .agents/copy/: шаблоны, статусы, цепочка audience→headlines→ux.
VKirill/claude-lane-stack
Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast.
VKirill/claude-lane-stack
Keep living docs/ honest after code changes. An agent skill from VKirill/claude-lane-stack.
Works with
Categories
[RU: интеграция mutagen.ru — частотность Яндекс, конкуренция, SERP-отчёты] Mutagen.ru REST API — RU SEO tool: точная частотность Yandex Wordstat, уровень конкуренции (strong), биды Директа, async…. Mutagen is an agent skill from VKirill/claude-lane-stack.report mega-tool with 22+ report types.
Mutagen fits situations like: Точная частотность; Частотность яндекс вордстат; Конкуренция директа; mutagen.checkkey.
Run `npx skills add VKirill/claude-lane-stack --skill mutagen -a claude-code`. Or copy the skill folder (plugins/lane-stack/skills/seo-tools/mutagen in VKirill/claude-lane-stack) into .claude/skills/mutagen in your project. Claude Code loads it when a task matches its description.
Run `npx skills add VKirill/claude-lane-stack --skill mutagen -a codex`. Or copy the skill folder (plugins/lane-stack/skills/seo-tools/mutagen in VKirill/claude-lane-stack) into .agents/skills/mutagen in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VKirill/claude-lane-stack --skill mutagen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mutagen, .gemini/skills/mutagen, .github/skills/mutagen and .opencode/skills/mutagen in your project.
Going by SKILL.md and its folder, Mutagen needs credentials named MUTAGEN_API_KEY. Our summary lists: Python 3; Node.js.
SKILL.md names 2 domains. In commands or code: mutagen.ru and api.mutagen.ru; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Mutagen is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 36k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Mutagen: Laravel Specialist (Jeffallan/claude-skills, 12k stars), Polylith Base Creation (DavidVujic/python-polylith, 553 stars), Frappe App Dev (frappe/skills, 147 stars) and Function Dev (butterbase-ai/butterbase-skills, 534 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
VKirill (a GitHub user) maintains it in VKirill/claude-lane-stack, which has 122 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 9, 2026.
Source: VKirill/claude-lane-stack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.