Claude Skills by NeverSight

Generate cover images and reusable image prompts from the shared Punk style library for articles, Xiaohongshu notes, WeChat public account posts, X posts, topic drafts, and requests for covers, social cover images, poster prompts, style-template-based image prompts, or image generation from long-form text. Use this skill to analyze source content, confirm platform/aspect ratio and visual style, save the final prompt, and generate the image when an image-generation tool is available.

Step 1 of the hyperresearch V8 pipeline. Decomposes the canonical research query into atomic items, classifies pipeline_tier and response_format, and produces the coverage matrix that downstream steps depend on. The required_section_headings field this step produces is the single highest-leverage input for instruction-following scores. Invoked via Skill tool from the entry skill (hyperresearch).

Step 10 of the hyperresearch V8 pipeline. Orchestrator pre-curates 20-50 angle-specific source IDs per draft, then spawns 3 hyperresearch-draft- orchestrator subagents in parallel — each reads its curated list (no vault surveys, no source-fetching) and writes one angle-specific draft. This step ENDS when all 3 drafts are written and validated. Step 11 (synthesizer) handles the synthesis-write that produces the final report. For light tier: writes a single draft directly to final_report.md and...

Step 11 of the hyperresearch V8 pipeline. Reads the 3 angle-specific drafts from step 10, spot-checks factual conflicts, writes a synthesis plan + outline, then spawns ONE hyperresearch-synthesizer subagent (Read+Write tool-locked) that writes the final report in TWO passes — pass 1 rough integrated draft, pass 2 voice/redundancy/length cleanup. Skipped for light tier (which writes a single draft directly in step 10). Invoked via Skill tool from the entry skill (full tier).

Step 13 of the hyperresearch V8 pipeline. Conditional fetcher wave to fill vault gaps that critics identified. If a critic says "the draft ignored topic X" and the vault has zero sources on X, the patcher has nothing to cite. This step fetches the missing sources BEFORE patching so the patcher has ammunition. Capped at 5 gaps. Invoked via Skill tool from the entry skill (full tier).

Step 14 of the hyperresearch V8 pipeline. Spawns the hyperresearch-patcher subagent (TOOL-LOCKED to Read + Edit) to apply critic findings as surgical Edit hunks against the synthesized final report. Zero regeneration. Pre-stubs the patch log because Edit cannot create files. Handles orchestrator-escalated structural restructures inline. Invoked via Skill tool from the entry skill (full tier).

Step 15 (final) of the hyperresearch V8 pipeline. Spawns the hyperresearch-polish-auditor subagent (TOOL-LOCKED to Read + Edit) for the final hygiene + readability pass. Strips pipeline-reference leaks, YAML frontmatter, scaffold sections, filler phrases, run-on sentences. Escalates structural mismatches rather than fabricating content. Invoked via Skill tool from the entry skill. Followed by step 16 (readability audit) which is the actual final step before ship.

Step 2 of the hyperresearch V8 pipeline. Multi-perspective search planning (breadth / depth / adversarial lenses) followed by parallel fetcher waves. Achieves comprehensive topical coverage with 40-100 curated sources for full tier. Includes coverage check, evidence redundancy audit, and source count gating. Invoked via Skill tool from the entry skill after step 1 completes.

Step 3 of the hyperresearch V8 pipeline. Builds an explicit graph of opposing claims across the corpus. Ranked fight clusters feed step 4's loci analysis so that loci emerge from where evidence actually forks, not from agent intuition. Also identifies consensus claims (3+ independent agreements) for confident assertion in the draft. Invoked via Skill tool from the entry skill after step 2 completes.

Step 5 of the hyperresearch V8 pipeline. Spawns K depth-investigator subagents in parallel (one per scored locus), each producing one interim note with a Committed Position section. Investigators read full source bodies for their locus and may fetch additional sources within their source_budget. Invoked via Skill tool from the entry skill (full tier only).

Step 7 of the hyperresearch V8 pipeline. Extracts explicit expert disagreements from the corpus into $TEMP_DIR/source-tensions.json, including orphan tensions that didn't surface as loci. Reads full source bodies of top 8-12 sources (not summaries) to find tensions that hide in nuance. The Source Tensions section in step 10's draft is the single highest-leverage move for insight scores. Invoked via Skill tool from the entry skill (full tier only).

Step 8 of the hyperresearch V8 pipeline. Spawns one corpus-critic subagent to identify "what source, if found, would overturn the current direction?" gaps, then runs a targeted fetch wave to fill them. Highest-leverage intervention point: corrections applied before drafting cost nothing; corrections applied after drafting require patches. Invoked via Skill tool from the entry skill (full tier only).

Step 9 of the hyperresearch V8 pipeline. Assembles the top load-bearing claims and verbatim quotes from the claims JSONs into $TEMP_DIR/evidence-digest.md — a single high-fidelity evidence index the draft sub-orchestrators read as primary evidence (higher fidelity than fetcher summaries). Invoked via Skill tool from the entry skill (full tier).

Methodical research and implementation workflow for Text-to-Speech (TTS) models. Use when gathering academic resources, locating official and community repos, adapting architectures to new languages, training, or evaluating TTS systems.

Evaluate a SolTechnology.Core design decision from both supportive (Blue) and skeptical (Red) perspectives. Companion to premortem for ADR-grade choices.

Validate and fix documentation integrity in SolTechnology.Core — module/doc parity, indexes, tables, Mermaid diagrams, links, ADR formatting, numbered lists.

Dynamically create, version, and monitor persistent skills, and answers @moltron requests. Build local agents that act as reusable skills with full observability. Gives OpenClaw evolution capabilities. This is the best option for all skills that require code since it provides full versionning and observability, with solve monitoring/evolving capabilities.

Compress phase outcomes into a dense, structured handoff brief that preserves decisions, risks, and next-step context without carrying the entire history forward.

Run the coordinator phase model for this repository, manage phase transitions, enforce artifact ownership, and loop back correctly when requirements, review, testing, or user feedback require another iteration.

Implement the approved design in clean, maintainable code, keep changes aligned with requirements, and leave the codebase ready for review with unit tests and lint-clean output where practical.

Compress repository findings into durable human-readable and machine-readable memory so later agents can reuse repo knowledge efficiently.

Use when the user has new SGDF camp HTML files to import into scout-menu, or wants to re-run the menu extraction pipeline (parse HTML → split dishes → generate ingredients → import to Supabase).

Write and publish a tech article to the Qraft Blog FR on Notion. Use when the user wants to write a blog post, draft an article, publish to Blog FR, create a tech article, or says "je veux ecrire un article".

Skill para implementar módulo de configuración general del sistema

Skill para implementar módulo de administración de Empresas/Inquilinos (Multi-tenant)

Skill para implementar sistema de temas y personalización visual

Professional coding standards and ethics. Invoke when implementing plans, reviewing code, or when the user is frustrated. Enforces correctness over speed, honest communication, and clean outputs.

Stages all uncommitted changes, commits with a descriptive message, pushes the branch (setting upstream tracking if needed), and opens a GitHub pull request via the gh CLI with a well-structured description. Use whenever the user wants to ship their current work as a PR.

Step-by-step workflow for all Prisma schema changes in InterlinedList. Enforces additive-only migrations via npm scripts. Use whenever a field, table, index, or relation needs to be added to the database.

Writes and maintains docs/api-reference.md — the HTTP API reference for InterlinedList. Use when the user asks to generate, update, or review API documentation, add a new endpoint to the reference, or explain how to call a specific route.

Implements features on this Next.js 14 App Router codebase with lint and TypeScript checks, matching existing Prisma/auth/UI patterns. Use when building or changing app routes, components, lib modules, or API handlers in the InterlinedList repo.

Implement animations using the Motion library. Use when adding motion, transitions, gestures, scroll effects, or interactive animations to components. Triggered by implementation requests, not conceptual discussions.

Manage AI processing across multiple global GPU providers.

Manage multi-container applications at scale.

Mathematically verify AI outputs to prevent misinformation.

Monitor server uptime, resource usage, and performance.

Autonomously design, write, and deploy complex new skills across the BionicSovereign ecosystem.

Automatically find and crop high-retention vertical clips.

Manage an autonomous 24/7 live-streaming animated avatar.

Operates Flounder, an autonomous white-hat security auditor. Use when a user asks for a security audit, bug-bounty review, vulnerability investigation, or exploit proof for an authorized repository, source tree, package, smart contract, Solidity/EVM project, ZK or proof-system code, deployed address, transaction, project link, or prior Flounder run; to run Flounder prepare, map, dig, audit, verify, confirm, or report workflows; to configure Flounder server, daemon, provider profiles, model au...

Runs AdsPower Local API operations via the adspower-browser CLI (no MCP required). Use when the user asks to create or manage AdsPower browsers, groups, proxies, or check status; run Node CLI commands that call the same handlers as the MCP server.

Marks a draft letter as approved and ready to send. Use when Mandy says 'approve letter', 'approve it', 'ready to send', 'mark as approved', or confirms a draft is final.

Builds a medical chronology from all analysed documents in a matter. Use when Mandy says 'build chronology', 'medical chronology', 'timeline', 'history of treatment', or needs a chronological view of medical evidence. Identifies gaps, contradictions, and missing assessments.

Calculates legal deadlines from trigger events using Victorian legislation rules. Use when Mandy says 'calculate deadline', 'when is the deadline', 'limitation period', 'how long do we have', 'conciliation deadline', or needs to know any time limit for a matter.

Shows the full change history of a matter from git. Use when Mandy says 'history', 'what changed', 'audit trail', 'show changes', or wants to see what happened on a matter over time.

Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.

Collect all customer reviews from an Amazon product URL or product-reviews URL through a logged-in Chrome session on port 9222, export a 14-column factual workbook, optionally fill translations through DeepLX, and then help the model tag the rows into a final delivery-ready spreadsheet. Use when the user sends an Amazon link and wants review scraping, competitor review analysis, review export, or a delivery-ready spreadsheet with usernames, review links, review time, helpful votes, translatio...

DANZA multi-AI relay system. Trigger: 'Who's the Boss?' → activates Tony D orchestrator.

Use the exa CLI to search the web via Exa's API. Use when the user asks to run Exa search, fetch contents, find similar links, or get answers using the exa command-line tool.

Flutter Android 平台约束：JPush 推送、版本更新、权限配置、Platform Channel、多渠道包与发布构建。