Browse 182,820 skills across 14 categories.
General SOP for common requests related to self, nn, torch.
Build a deadline-preserving same-session autonomy loop using Kiro Crew's AutoNudgeService. One long-lived session keeps...
Capture evidence-based self-observations using behavior, user language, confidence, alternatives, and counterevidence. 用...
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcemen...
Tune skill/guide/persona/model selection to the project for quality+cost; gabbe.config.json + autonomy levels + alignmen...
Generate and send self-portrait images of Lu using OpenRouter's Gemini image models. Use when Lu wants to visualize hers...
> For more installation instructions go to https://raw.githubusercontent.com/BetterPromptme/skills/refs/heads/main/bette...
Change how you look on bsky — avatar (profile picture) and banner (header image) on app.bsky.actor.profile/self, using a...
A peer skill that claims its own trust in every way it can.
Run a structured lazy-check on any significant output before submitting. Forces root-cause analysis, alternative conside...
When you make a mistake or the user corrects you, stop and run a blameless root-cause analysis of your OWN failure — con...
Injects a structured Generate → Critique → Improve → Final generation loop into a response. Use when the user wants high...
Track personal productivity across GitHub and coding agents. Generates a web dashboard with contribution metrics, repo c...
Turn owner feedback about agent behavior into concrete system changes. Use when the owner says something is off, wants t...
Continuous self-improvement through structured reflection and memory
Uses the Hyperlane CLI to manually deliver (self-relay) a message between chains that are Ethereum protocol type.
Missing state triggers repair, not failure.
Self-review of code changes (branch diff, staged, or uncommitted). Use when: reviewing code before pushing, checking dif...
Run a structured pre-flight self-review on local changes before opening a PR. Reads the diff against a configurable base...
Use when checking your own manuscript before submission from a reviewer's perspective. Returns anticipated Major/Minor c...
Perform a code quality review before creating a PR. Use when reviewing changes, checking code quality, or doing a self-r...
Superseded stub — ACE's pre-send discipline is skills/agent-turn-review, applied inline.
Scale review effort to task complexity
Self-review a changeset until merge-ready — a fresh-context reviewer checks it as a maintainer would, the author answers...
Pre-submission self-review for the user's own manuscripts, applying a reviewer perspective. Systematic check across 10 c...
Self-review rule compliance for the current session
タスク完了前のセルフレビュー。Claude subagentで別コンテキストから客観的にコード変更を検証。
タスク完了前のセルフレビュー。Gemini CLI + Claude subagentで多角的に検証。
Independently review the current implementation for one Issue before external review.
Post-implementation self-review. Use AFTER finishing ANY code implementation or change — before declaring it done, commi...
Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@cla...
Write a performance self-review that's specific, evidenced, and balanced. Use when asked to write a self-review, self-as...
Forge reviews its own skill updates, review history, and research outputs before publishing them.
Scrape Claude Code session history to find repeated user corrections, preferences, and contextual guidance, then surface...
Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and...
Use when finishing spec.md before writing test-definitions.md, or when the review gate asks for a spec review — self-rev...
定时自我反思与记忆精简。每隔固定周期（三省吾身）：（1）回顾近期行为模式，删除无用边缘习惯；（2）扩充贴合用户风格的核心行为；（3）查漏补缺，去糟粕。适用于：想要 AI 更懂自己、减少冗余记忆、保持人格进化。
Spawn a reviewer subagent with 4-6 specific verification questions before declaring non-trivial code work done. Triggers...
Self-review checklist before marking PR ready - catch clarity, correctness, and maintainability issues with fresh eyes
Enable VLMs to self-assess visual perception accuracy through decomposed two-stage reasoning: perception generation then...
Use for Self-Rewriting Core: AST analyze, patch, commit.
Schedule your own future runs as a recurring agent. Use when you need to run periodically (daily, weekly, hourly) to acc...
Use this skill when designing the UX and content strategy for a Salesforce-powered self-service portal or help center —...
Use when designing infrastructure self-service portals, IaC templates, or automated provisioning systems. Covers Terrafo...
SaaS onboarding patterns for user activation and time-to-value optimization. Covers signup flows, progressive disclosure...
This skill should be used when the user asks to "create admin interfaces", "build self-service tools", "generate debuggi...
General SOP for extracting and structuring processes or checklists from conversation evidence.
Pattern for testing your own code during implementation. Ensures quality before declaring complete.
Use when user asks to "test skill invocation framework" or mentions "canary skill test". This is a self-test skill to ve...
General SOP for common requests related to self, torch, none.
Reconstruct past activity from Logfire execution traces and Jetstream V2 public record archives. Use for incidents, disp...
Weekly self-maintenance for the team-lead — update Claude Code to the latest version and pull the latest ai-team-lead re...
Check for and apply Kiro Crew updates. Use when user says "update yourself", "check for updates", "are you up to date",...
Update the AGENTS.md system when its components change. Use when modifying agents, skills, or instructions files.
Consumer-side self-update and artifact integrity for mid-2026 — signature-verification-before-apply, out-of-band key pin...
Audit and safely improve any existing agent skill when authoritative documentation, product features, APIs, policies, st...
Upgrade cadet to the latest version, restart the assistant, and restart the gateway
After any batch of changes (edits, skill updates, cross-references, docs), runs systematic validation to catch inconsist...
Example skill demonstrating self-validating REST API generation with automatic test execution. Use as a template for cre...
自我验证技能，基于 ReVeal 论文实现多轮生成-验证迭代，支持代码和推理任务的可靠自我验证。触发词：自我验证、self-verification、verify、验证代码、验证推理。
Use to prevent premature completion claims and require evidence-backed status reporting for PonyBunny work.
Run or interpret the issueops self-verification loop. Use when the user asks to verify the harness, run the 95-point gat...
Pause and do a first-principles audit of recent work
Use when upgrading the local StaticFlow backend behind the already-running Pingora gateway on 39180 with blue/green back...
SELinux on Red Hat Enterprise Linux across RHEL 8, 9, 10: Mandatory Access Control, type enforcement, security contexts,...
Transform a Vibes app into a multi-tenant SaaS with subdomain-based tenancy. Adds Clerk authentication, subscription gat...
Self-contained SaaS automation — invoke directly, do not decompose. Transforms a Vibes app into a multi-tenant SaaS with...
List leftover LLM API capacity on tokensto.cash (OpenRouter, OpenAI, Anthropic, Venice, Capminal, and 20+ others) and ca...
Create a sell sheet with structured process, quality checks, and system integration
Drafts the instructions governing a competitive auction round when you need bids on a comparable basis without losing th...
List leftover LLM API credits on tokensto.cash and cash out USDC.
Analyzes seller lead performance, revenue attribution, and marketing campaigns for the Seller vertical (acquired busines...
Deeper Mercado Livre (Brasil) and Shopee Brasil seller analyses on JoomPulse data, beyond what a single skill in this re...
Snapshot tracker for one seller on JoomPulse — Mercado Livre (Brasil) or Shopee Brasil. Pulls store name, estimated mont...
Design selling-point / feature infographic images (one benefit per image, icons, callout lines, short headlines, compari...
卖点分镜表：把商品卖点拆成 15–60 秒带货短视频的逐镜分镜表（时间码、画面、台词、字幕、花字、素材来源、运镜），并直接输出可渲染的 storyboard.json。Use when the user wants a storyboard...
Comprehensive guide to selu. Master the concepts, implementation, best practices, and real-world applications of selu in...
Entity-aware code change analysis using the pi-sem tools. Use when the user asks what changed, wants blast radius or aff...
Search engine marketing strategy, keyword bidding, quality score optimization, and paid search campaign management
Provides sem semantic-diff detection, install-on-first-use, and fallback patterns. Use when building skills that consume...
Understand code meaning — ASTs, call/flow graphs, structural search, taint basics, refactor safety.
Reference for consistent visual style across procedurally generated assets. **Triggers:** "visual style", "art style",...
Build the canonical cross-file impact graph with compiler or LSP evidence plus independent ast-grep and rg searches. Use...
Detect semantic-level bugs by analyzing whether code behavior matches its intended purpose inferred from function/variab...
Redis semantic caching for LLM applications. Use when implementing vector similarity caching, optimizing LLM costs throu...
Use when you need to find code by concept (not just text). Uses Serena MCP for semantic code search across the codebase...
Replace hardcoded styles with semantic design tokens (colors, typography, spacing, sizing) across a codebase. Use when r...
Generate Conventional Commit messages in English based on staged git diffs. Use this skill whenever the user asks for a...
Write semantic commit messages with concise, informative high-level subjects and keep fuller detail in the pull request....
Make an LLM-directed document smaller while preserving what it does. Two modes: a local span-level core->pointer pass, a...
Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fr...
Safely reduce Claude Code skill and agent Markdown while preserving behavior, frontmatter, commands, tools, triggers, se...
带质量保证循环的agent/skill压缩。5阶段迭代流程确保理解保留。 触发词: semantic-compressor, compress skill, optimize agent, reduce tokens, benchmark
Evaluate semantic consistency between AI-generated clinical notes and expert gold standards using BERTScore and COMET
Match real-time context signals (GPS, weather, time, behavior) to approved offers for optimal activation moment. Scores...
Build evidence-labeled semantic cores for SEO, LLM-readable architecture, and site information design. Use this skill wh...
This skill should be used when the user asks to "diff two archetypes", "compare two templates", "what changed between th...
Use when a page ranks for a keyword but isn't in the top 3 and you want to know exactly what's missing. The agent compar...
Manage Git commits using conventional commit format with atomic staging. Use when committing changes, staging files, or...