Skills
Security-reviewed skills, MCP servers, and toolkits for AI agents. Filter by type, price, and delivery, then install any listing with one command. Every listing is scanned before an agent can run it.
Sitebulb Technical Seo Audit
Produce the client-facing technical SEO audit document from a Sitebulb project's latest finished audit: a focused Word working draft of 5–10 issues — never encyclopaedic — selected and ordered by why the audit was commissioned (traffic decline, redesign/migration, onboarding, due diligence), written for the stated reader, each issue carrying its true affected count, labelled sample URLs, a Sitebu…
Sitebulb Dev Handoff
Turn Sitebulb audit findings into dev-ready tickets in the connected PM tool (Jira, Linear, Asana, Monday, or ClickUp): one ticket per selected issue — what's wrong, why it matters, the true affected-URL count with labelled sample URLs and a pointer to the full export in the Sitebulb app, a suggested fix with its knowledge-base link, acceptance criteria, severity-mapped priority, and an effort es…
Sitebulb What To Fix First
Produce a prioritised read of a Sitebulb audit — the 3–5 issue clusters most worth fixing for this business in this situation — by interviewing for business context, sweeping triggered hints, and scoring impact (severity × section tier × effective coverage × traffic linkage) against effort (fix archetype, S–XL, owner, indicative duration), with context reframing what leads but never the scores. U…
Sitebulb What Changed
Tell the change story between a Sitebulb project's two most recent audits — wins first, then regressions, then a watch-list, each with what it means and whether it needs action — reframed for the business's situation, with a Google Analytics/Search Console overlay where connected, evidence cards showing per-hint deltas, and an optional self-contained HTML dashboard. Use for \"what changed since l…
Sitebulb Release Check
Run the user's configured post-release watch-list check on a Sitebulb project: compare the latest finished audit against the previous one, evaluate each watched item against the thresholds in this file's settings block (project, watch-list, thresholds and alert channel live there — the first run asks setup once and hands the filled block back to paste in), treat changes the user names as delibera…
Postext Port
Port an existing publication into a Postext project (config manifest + enriched Markdown chapters + resources + fonts) that reproduces the original's layout rules. Use when the user wants to convert, adapt, migrate, re-typeset or rebuild a book, textbook, magazine, catalogue, report, manual, course or deck in Postext from a PDF, Word (.docx), PowerPoint (.pptx), EPUB, HTML, InDesign (IDML), LaTeX…
Avoid Ai Writing Russian
>-
Antiplagiat
>-
Context
File project knowledge the user shares conversationally into the correct .ai/ files - purpose, rules, database, dependencies, conventions, decisions - and close the memory loop at the end of tasks and sessions. Use when the user shares project context, decisions, or conventions, or when finishing a task in an initialized project.
Ship
Prepare a commit: verify the staged diff, generate a conventional commit message, run pre-commit checks (including a fresh-context review), commit, and report the hash. Use when the user asks to commit or ship changes.
Debug
Find and fix a bug systematically: reproduce it, isolate the failing path, verify assumptions, fix the root cause, and keep a regression test. Use when something is broken and the cause is not obvious, when an earlier fix did not hold, or when the user reports a bug with no known cause.
Worktrees
Do work in a git worktree so the main checkout stays untouched: create the worktree, work and verify inside it, land the branch, then clean up. Use when work must run alongside something else in the same repository, when the main checkout holds uncommitted changes, or when the user asks for an isolated workspace.
Plan
Survey the repository and produce a numbered implementation plan with explicit success criteria before any code changes, then stop and wait for approval. Use when the user asks to plan, or before starting any non-trivial implementation.
Ci
Run the full CI pipeline locally: lint, test, build, security scan, and report pass/fail per step. Use when the user asks to run CI locally or to verify the build before pushing.
Extend Config
Create or update files in the agent-config repo (rules, skills, docs, templates, presets, bridges) following its authoring spec. Use when the user asks to add, extend, or reorganize the agent-config repo, or to create new agent config files following the existing patterns.
Dispatch
Split independent work across parallel subagents and merge their results: one deliverable per task, launched together, each result verified before it is used. Use when a task has independent parts, when several areas need the same kind of review, or when exploring options in parallel saves time.
Review
Review all pending changes on the current branch: diff, unpushed commits, linters, tests, a fresh-context adversarial pass, and a structured report. Use when the user asks to review pending changes or before declaring work done.
Onboard
Understand a repository like a new engineer: classify NEW vs EXISTING, survey docs and history, summarize, ask questions, and change nothing. Use when starting work in an unfamiliar repository or when the user asks to be onboarded.
Jevelry
Jev (TypeSafe System One) decisions: use when you or the code you are working on need a judgment call about text or data, such as triage of a ticket, a message or a log, whether something is urgent, whether an issue is a duplicate, how high the severity is, whether a change is risky, or whether a failing test is caused by the code or by the environment, and you would otherwise ask an LLM to retur…
Mcbe Model Fundamentals
Build a Minecraft Bedrock Edition entity model in code. Use for any new Bedrock model (vehicle, creature, weapon, cosmetic, prop), or when a model's orientation, rotation, mirroring or units look wrong.
Mcbe Model Collision Footprint
Fit a physics / collision footprint to a Bedrock model by measurement: rest-pose corners of structural bones, convex envelope in slices, shape supports 0–0.03 outside the measured extremes.
Mcbe Model Hand Edits
Work with a person who edits the model in Blockbench: their file wins, lint it, fix only defects with minimal text patches, bring the builder to their geometry, keep their original.
Mcbe Model Shape Language
Shape rules for Bedrock cube models: no stair steps, tilted links joined corner to corner, splays where widths step, filled valleys, one design language. Use when shaping any body, curve, slope, limb, blade or panel, or when feedback says 'stairs', 'gap', 'plays apart', 'looks like a lizard'.
Mcbe Model Attachables
Model Bedrock attachables and wearables: held weapons and tools, a wrist watch, charms, armour pieces. Player-bone frames, slim/wide arm variants, Molang-driven parts, emissive alpha, verifying orientation.
Mcbe Model Vehicles
Model a Bedrock vehicle the player rides: kart, car, boat, aircraft, mount with a seat. Covers the skeleton, rider fit, a closed body with wheel arches and chamfered corners, steering sweep, wheels, locators.
Mcbe Model Visibility Budget
Reduce a Bedrock model's texture size and VRAM: blank faces nobody can see, per-face density, cropped atlas, no grain. Use for mobile performance or when told 'this texture is hidden / wasted'.
Mcbe Model Verification
Verify a Bedrock model before delivery: forge checks, game-true renders from the player's camera in every pose and two liveries, the linter, tests proven to fail on the broken model, an honest report.
Mcbe Model Zfight And Seams
Find and fix z-fighting (flicker), cracks, seams, gaps and collapsed cubes in a Bedrock model. Use when the user reports flicker, cracks, lines between cubes, or after any hand edit in Blockbench.
Mcbe Model Uv And Texture
Lay out UVs and paint textures by function for a Bedrock model: per-face rectangles, per-face density, liveries, pictures placed by position, cut-out plates, emissive alpha. Use when making or fixing a model's texture.
Mcbe Model Transforming Parts
Make parts of a Bedrock model open, fold, unfold, pop up or transform with animations: model open, fold with the bind pose, check every pose, keep fixed parts out of the path, speed-driven state controllers.
Mcbe Model Creatures And Props
Model Bedrock creatures (monsters, dragons, animals), aircraft, weapons, cosmetics and props in code: bone per joint, curved bodies as chains, wings and fins as alpha-cut plates the way the vanilla Ender Dragon does, looping Molang motion.
Competitor Gap
Identify a domain's real search competitors from shared rankings, then map keyword, content, backlink, and traffic-channel gaps with a prioritised closing plan. Use when the user asks who competes with them in search, which keywords or content they are missing, or how they compare against a named competitor.
Serp Analysis
Analyse the current Google top 10 for one keyword — keyword metrics, search intent, SERP features, the winning content format, and the gap the user can realistically win. Use when the user asks what ranks for a keyword, what the SERP looks like, which format to write, or why competitors outrank them.
Internal Link Audit
Audit internal linking to find orphan pages, broken internal links, crawl-depth problems, and weak anchor distribution, then plan the hub-and-spoke structure that fixes them. Use when the user asks about internal links, orphan pages, site architecture, crawl depth, or how to pass authority to priority pages.
Technical Seo Audit
Audit crawlability, indexability, HTTPS and redirects, Core Web Vitals, mobile parity, metadata, canonicals, structured data, and internal architecture using Semrush Site Audit data, separating confirmed defects from analyst judgment. Use when the user asks for a technical SEO audit or a site health check, why pages are not indexed, or why a site is losing search visibility for technical reasons.
Content Brief
Turn one target keyword into a content brief a writer can ship — intent, audience and angle, SERP context, title and meta description, outline, FAQs, scope guidance, and an internal linking plan. Use when the user asks for a content brief, a blog outline, what to write about a keyword, or how long an article should be.
Schema Markup
Audit the structured data a page actually declares, decide which entities belong on it, and draft validated JSON-LD from verified facts only, separating Schema.org validity from Google rich-result eligibility. Use when the user asks about schema markup, structured data, JSON-LD, or whether a page is eligible for rich results.
Keyword Research
Run a keyword research workflow on a topic or domain — existing rankings, keyword ideas from a seed, intent classification, filtering by volume, difficulty, CPC and business value, then clustering by topic. Use when the user asks for keyword research, keyword ideas, search volume or keyword difficulty, or which keywords to target.
Ai Brand Visibility
Measure how a brand appears in AI answers by combining Semrush AI-channel traffic estimates with controlled prompt observations, keeping measured findings separate from diagnostic hypotheses. Use when the user asks about AI visibility, whether ChatGPT or Perplexity mention their brand, AI share of voice, or how much traffic arrives from AI assistants. AI-channel traffic reports require a Trends s…
Backlink Audit
Audit a domain's backlink profile — anchor distribution, referring domains, toxic patterns, competitor link gaps, and broken-link recovery — and produce an evidence-labeled action plan. Use when the user asks for a backlink audit, whether their links are toxic or spammy, where competitors get links they do not have, or how to recover lost links.
Objection
Adversarial review before opening or merging a pull request. Accusers review the diff, a defender tries to refute each finding with evidence from the code, and the main session judges and stores a record for the exact commit. With a gate installed, PR create, ready and merge are blocked until the record is APPROVED. Use when a branch is ready for a PR, when the gate blocks, or with "init" to opt…
Cutlist
Turn any long video with captions (a podcast, an interview, a webinar, a lecture, a tutorial, a stream VOD, a keynote; the video file plus .srt or .vtt captions) into a ranked plan of 5 to 8 short vertical clips with exact cut times, plus YouTube title, description, hashtags, tags, and category for the video and each clip, a cold-open pick, and one thumbnail mockup that matches the first 10 secon…
Malformed Yaml
A Claude skill from Mane087/skill-router.
Empty Description
A Claude skill from Mane087/skill-router.
Duplicate Keys
First description.
Writing Plans
Use when a specification exists and a multi-step implementation plan must be written before touching code.
Finishing A Development Branch
Use when the implementation is done and the branch has to be integrated, rebased or merged.
Unknown Phase
Declares a phase outside the supported lifecycle.