The catalog
610,677 rows, by stacks then stars
chrisallenlane/claude-swe-workflows/skills/think-diagnose Skill
18★ repoAbductive reasoning about causes. Takes a phenomenon, separates observations from interpretations, then spawns diagnosticians applying different reasoning lenses (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical) in isolation. Orchestrator evaluates candidate causes for fit-against-evidence, calibrates confidence honestly, and reports leading candidate(s) with distinguishing evidence needed. Produces feedback only — no code, no tickets, no artifacts.
The same file is in 2 other repositories
chrisallenlane/claude-swe-workflows/skills/think-premortem Skill
18★ repoProspective failure imagination for a plan, decision, or running system. Operates in two modes — **plan mode** (a plan has not yet been committed to; imagine its catastrophic failure broadly) and **scenario mode** (a specific catastrophic scenario is posed against an existing system; investigate causes against the actual code and architecture). Spawns parallel pre-mortemers in isolation across three categories of lens: standard failure classes (technical, operational, estimation, scope, adoption, dependency, team, incentive, detection, reversibility, adversarial), 0-3 ad-hoc target-specific lenses the orchestrator names when warranted, and a first-principles lens that always runs to catch what the prescribed taxonomy misses. Synthesizes into a prioritized risk register with early-warning signals. Produces feedback only — no code, no tickets, no artifacts.
chrisallenlane/claude-swe-workflows/skills/think-reflect Skill
18★ repoRetrospective learning from a completed experience. Takes a project, incident, decision that played out, or time period; gathers ground truth (observations) separately from recollections; spawns reflectors applying different lenses (what-worked-vs-got-lucky, what-didn't, what-surprised, system-rewards-vs-intent, decisions-that-aged, what-to-tell-past-self, patterns-that-recur) in isolation; synthesizes into updated mental models as first-class output. Produces feedback only — no code, no tickets, no artifacts.
The same file is in 2 other repositories
chrisallenlane/claude-swe-workflows/skills/think-reframe Skill
18★ repoProblem redefinition before problem solving. Takes a stated problem, extracts its premises, then spawns reframers applying different lenses (problem-vs-symptom, scope-shift, stakeholder-shift, level-of-abstraction, time-horizon, inversion, category-shift, constraints-shift) in isolation, and synthesizes the alternatives into a report with an orchestrator recommendation. Produces feedback only — no code, no tickets, no artifacts.
The same file is in 2 other repositories
chrisallenlane/claude-swe-workflows/skills/think-scrutinize Skill
18★ repoGood-faith adversarial scrutiny of an idea or plan. Spawns critical skeptics across relevant lenses, pairs them with an advocate defending the idea, and synthesizes the exchange into a report. Produces feedback only — no code, no tickets, no artifacts.
The same file is in 2 other repositories
chrisallenlane/claude-swe-workflows/skills/tidy-docs Skill
18★ repoMechanical documentation hygiene. Spawns a doc-maintainer agent to audit all project documentation and fix correctness, completeness, freshness, and consistency issues autonomously within its authority. Surfaces anything requiring user judgment for approval.
The same file is in 3 other repositories
chrisallenlane/claude-swe-workflows/skills/tidy-git Skill
18★ repoMechanical git repo hygiene. Prunes stale remote-tracking refs, deletes merged local branches (with confirmation), and reports stashes, untracked files, and unpushed work. Never touches remote state. Safe by default — destructive operations require explicit operator approval.
The same file is in 2 other repositories
Benkapner/claude-code-basecamp/skills/python-conventions Skill
18★ repoTeam-specific Python conventions — credential management with dotenv, API client rules, LLM response parsing, TDD workflow, and testing patterns for data pipelines.
The same file is in 2 other repositories
Benkapner/claude-code-basecamp/skills/refactoring-patterns Skill
18★ repoMeasurement-driven code refactoring — profile before changing, measure after, keep only if metrics improve. Covers complexity reduction, extraction patterns, and bulk refactoring for mechanical changes across many files.
The same file is in 2 other repositories
Benkapner/claude-code-basecamp/skills/security-check Skill
18★ repoScan Python projects for credential leaks, secrets in code, insecure patterns, LLM API key exposure, PII leakage to external AI services, and .env/.gitignore misconfigurations. Focused on data science pipelines handling API keys, tokens, and LLM integrations.
The same file is in 2 other repositories
Benkapner/claude-code-basecamp/skills/update-docs Skill
18★ repoUse when implementing features, fixing bugs, or refactoring code that may invalidate existing docs. Detects stale documentation by matching the code diff against in-repo doc files and applies targeted updates. Relevant when code changes rename, remove, or add APIs, fields, config keys, or CLI flags. Also applies when the user says "update docs", "check docs", or "are the docs stale", or when reviewing a branch for documentation accuracy.
The same file is in 2 other repositories
Benkapner/claude-code-basecamp/skills/verification-loop Skill
18★ repoUnified verification engine for Python data science projects. Covers environment checks, type checking, linting, tests, security scans, code review with DS anti-patterns, and notebook checks. Commands (/verify, /quality-gate) invoke different subsets of this skill.
The same file is in 2 other repositories
wei18/apple-dev-skills/apple-dev-skills/skills/app-store-review-rejections Skill
18★ repoUse when preparing an App Store submission, diagnosing an App Review rejection / Resolution Center message, or hardening a free game/app with ads + Remove-Ads IAP + CloudKit + Game Center against the rejection classes it realistically hits. Covers guideline 1.3 / 2.1 / 2.3 / 2.5.x / 3.1.1 / 4.0 / 4.3 / 5.1.1 / 5.1.2, the ATT-vs-AdMob trap, privacy-label parity, and a pre-submit checklist.
wei18/apple-dev-skills/apple-dev-skills/skills/apple-platform-targets Skill
18★ repoDefault minimum deployment targets for Apple-platform Swift Apps and how to deviate up or down. Default is iOS 18 / macOS 15 with Xcode 16+ (first toolchain to formally support Swift 6 language mode). Invoke when starting a new Apple-platform project, writing Package.swift `platforms:` list, deciding whether to adopt Liquid Glass / latest-OS-only APIs, or when asked "what should the minimum iOS / macOS version be?".
wei18/apple-dev-skills/apple-dev-skills/skills/apple-public-repo-security Skill
18★ repoSecurity baseline for public iOS / macOS repos — secret classification (CloudKit PEM, ASC API key, APNs key, signing cert, provisioning profiles), `.gitignore` baseline, three lines of defence (mise gitleaks + lefthook pre-commit · Xcode Cloud `ci_post_clone.sh` · GitHub Secret Scanning), rotate-first leak SOP (`git filter-repo`, fork persistence), Apple upstream telemetry disclosure (MetricKit / Game Center / sysdiagnose). Invoke when a repo goes public, an existing repo open-sources, a secret enters the build pipeline, or asked "how to prevent secret leaks in a public repo". Repo-hygiene baseline; for ship-in-binary identifiers (AdMob ID via xcconfig `$()`) see build-time-secret-injection.
wei18/apple-dev-skills/apple-dev-skills/skills/apple-three-piece-analytics Skill
18★ repoDefault analytics stack for solo / small Apple-platform Apps — App Store Connect Analytics + MetricKit + Game Center (for games), no third-party tracking SDK by default, PrivacyInfo.xcprivacy mandatory. Invoke when starting a new project, deciding analytics SDK (vs Firebase / TelemetryDeck / Amplitude), writing PrivacyInfo, or when asked "should I integrate Firebase / Mixpanel / TelemetryDeck".
wei18/apple-dev-skills/apple-dev-skills/skills/asc-api-automation Skill
18★ repoReusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
wei18/apple-dev-skills/apple-dev-skills/skills/build-time-secret-injection Skill
18★ repoUse when introducing an AdMob production ID (`GADApplicationIdentifier` / `GADBannerUnitID`), ASC API `.p8` key, or any "ships in binary but must stay out of public-repo PR diffs" identifier into an Apple build. Codifies the xcconfig + Info.plist `$()` substitution + `Bundle.main` read pattern, paired with `secrets/.env` for CLI tooling; multi-app `CI_PRODUCT` dispatch + built-bundle smoke-test. Build-time injection mechanism, not the repo-hygiene baseline; for secret-leak prevention (gitleaks, lefthook, GitHub Secret Scanning) see apple-public-repo-security.
Cloudkit schema source of truth
wei18/apple-dev-skills/apple-dev-skills/skills/cloudkit-schema-source-of-truth Skill
18★ repoUse when a CloudKit-backed app's persistence layer adds or edits a record type, field, or index and the schema needs to reach a container, or when asked "how do I push CloudKit schema to Production", "why can't cktool deploy to prod", or "why is a field silently missing in Production". Covers one committed `.ckdb` per app as the schema source of truth, `xcrun cktool` export/validate/deploy against Development (management token from an env file, passed positionally since cktool rejects piped stdin, purged after use), Production promotion as an irreversible Console-button-only gate `cktool` cannot reach, Production fields/indexes being add-only, and Just-In-Time schema existing only in Development — a field the code writes that Production was never seeded with fails silently.
wei18/apple-dev-skills/apple-dev-skills/skills/host-driven-xcuitest-e2e Skill
18★ repoReusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
Interactive simulator ux audit
wei18/apple-dev-skills/apple-dev-skills/skills/interactive-simulator-ux-audit Skill
18★ repoUse when auditing an iOS/iPadOS app's live behavior in the Simulator — navigation, modals, back-stack, completion flows, safe-area/Dynamic-Island clipping, offline or signed-out states — bugs a fixed-size snapshot render structurally cannot show. Covers installing `idb` without Homebrew (direct GitHub release + an exec wrapper that preserves rpath), the describe-all → tap → screenshot drive loop, device-point vs screenshot-pixel coordinate spaces, and the "stale build" / "worktree launch crash" false-negative traps. Use when asked to "test the UI", "find UX problems", "drive the simulator", or verify an interactive flow end-to-end.
wei18/apple-dev-skills/apple-dev-skills/skills/ios-accessibility-engineering Skill
18★ repoConcrete VoiceOver / Dynamic Type / touch-target / Reduce Motion implementation guide for SwiftUI and UIKit. Invoke when building or auditing any user-facing iOS/macOS UI, when asked "make this accessible", or before an App Review submission a11y pass.
wei18/apple-dev-skills/apple-dev-skills/skills/ios-design-mockup Skill
18★ repoReusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
wei18/apple-dev-skills/apple-dev-skills/skills/ios-performance-engineering Skill
18★ repoMeasure and fix iOS/macOS performance — Instruments (Time Profiler, Allocations, SwiftUI instrument, Hangs), os_signpost, MetricKit field telemetry, XCTMetric baselines, launch-time optimisation, memory footprint, binary size. Invoke when diagnosing slowness/hitches/high memory, setting up CI perf baselines, wiring MetricKit, or asking "why is my app slow / using too much memory / large".
wei18/apple-dev-skills/apple-dev-skills/skills/mise-tool-management Skill
18★ repoUse mise (mise.jdx.dev) to manage binary CLI / build tools (swiftlint, swiftformat, xcbeautify, gitleaks, lefthook, etc.) on both dev machines and CI, sharing a single `.mise.toml` for version parity. Invoke when starting a new project, choosing a tool version manager (vs asdf / Homebrew / manual), writing `.mise.toml`, or when asked "how do I manage swiftlint / xcbeautify versions".
wei18/apple-dev-skills/apple-dev-skills/skills/monetization-sdk-integration Skill
18★ repoInvoke when adding, upgrading, or auditing any third-party monetization SDK (AdMob, UMP, StoreKit wrappers, RevenueCat, ironSource, etc.). Also invoke when reviewing PR diffs that touch your monetization target's ad-bridge sources, or when anyone proposes `import GoogleMobileAds` outside the existing live-bridge file.
wei18/apple-dev-skills/apple-dev-skills/skills/oslog-logger-defaults Skill
18★ repoDefault logging stack for Apple-platform Swift Apps — Apple's built-in `os.Logger` (no third-party), subsystem = bundle ID, category = module name, all string interpolation defaults to `.private` with explicit `.public` opt-in. Invoke when starting a new project, choosing a logging library, writing the first Logger declaration, deciding privacy interpolation, or when asked "OSLog vs SwiftLog vs CocoaLumberjack, which one".
wei18/apple-dev-skills/apple-dev-skills/skills/swift-dependency-injection Skill
18★ repoTestable seam design via protocol injection, SwiftUI environment, and task-local overrides; Swift 6 Sendable rules for dependencies; mentions pointfreeco/swift-dependencies and Factory as library options. Invoke when designing a new service seam, asking "how do I inject CloudKit/network/clock", setting up a composition root, or making code testable.
wei18/apple-dev-skills/apple-dev-skills/skills/swift-testing-baseline Skill
18★ repoDefault testing stack for new Apple-platform Swift projects — swift-testing (no XCTest), pointfreeco/swift-snapshot-testing, protocol-injected fakes for CloudKit / Game Center / network, snapshot images committed to git, CI Xcode version locked to local. Invoke when starting a new project, writing the first test target, choosing a snapshot framework, deciding CloudKit / GameKit test strategy, or when asked "which test framework".
wei18/apple-dev-skills/apple-dev-skills/skills/swift6-concurrency Skill
18★ repoDefault to Swift 6 language mode with complete concurrency checking from the first line of code; treat all in-house types as needing Sendable; isolate third-party deps that lag with @preconcurrency. Invoke when starting a new Swift Apple-platform project, writing Package.swift, picking the Swift language mode in Xcode build settings, or when asked "should I turn on strict concurrency?".
wei18/apple-dev-skills/apple-dev-skills/skills/swiftpm-modularization Skill
18★ repoDefault modularization shape for Apple-platform Swift Apps — single Swift Package, multi-target, thin App target, DI composition root, restricted Apple framework imports, one test target per production target. Invoke when starting a new project, writing Package.swift, deciding how to split modules, planning portability (e.g. Swift on Android), or when asked "single package or multi-package, how should I split modules".
wei18/apple-dev-skills/apple-dev-skills/skills/swiftui-interaction-footguns Skill
18★ repoReusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
Swiftui navigation architecture
wei18/apple-dev-skills/apple-dev-skills/skills/swiftui-navigation-architecture Skill
18★ repoDefault navigation shape for SwiftUI Apps (iOS 18 / macOS 15, Swift 6) — value-based `NavigationStack(path:)` over a typed `Route` enum, one `@Observable @MainActor` Router in `.environment`, `navigationDestination(for:)` at the stack root (never in a lazy container), per-transition presentation semantics (push / sheet / `fullScreenCover` / popover / alert / root-swap) incl. macOS behavior (no native `fullScreenCover` → push fallback, pop-to-landing), `item:`-driven modal optionals, `.onOpenURL` deep-link funnel, `NavigationSplitView`, per-tab paths, `Codable` restoration. Invoke when wiring an App's navigation, choosing sheet vs cover vs push, adding deep links / restoration, migrating off `NavigationView`, or asked "router / coordinator in SwiftUI". Bugs → swiftui-interaction-footguns.
wei18/apple-dev-skills/apple-dev-skills/skills/telemetry-facade-pattern Skill
18★ repoSingle `Telemetry` SwiftPM target with a fan-out facade — callers say "what happened" (`telemetry.observe(event)`), facade dispatches to multiple sinks (OSLog / NoOp tracking / MetricKit / Game Center). Invoke when starting a new project that will log + track, deciding logger / tracker coupling, designing telemetry interfaces, or when asked "should Logger and Tracking be one thing".
wei18/apple-dev-skills/apple-dev-skills/skills/xcode-cloud-single-track-ci Skill
18★ repoDefault CI strategy for solo / small-team Apple-platform projects — Xcode Cloud single-track only (defer GitHub Actions until real pain appears), 4 workflow types (PR / Main / Release / Periodic), pre-merge main on PR CI, Xcode version locked to local. Invoke when setting up CI on a new project, deciding GitHub Actions vs Xcode Cloud, writing ci_scripts/, or when asked "how should CI be set up, do I need dual-track".
wei18/apple-dev-skills/collaboration-skills/skills/agent-impl-notes-log Skill
18★ repoMaintain a running `meetings/{date}_{topic}.impl-notes.md` *during* subagent task execution to capture in-flight design decisions, intentional deviations from spec, considered alternatives, and open questions for Leader/User. Distinct from the post-hoc phase meeting log; this file is updated incrementally as decisions are made. Invoke at the start of any non-trivial subagent dispatch, when ambiguity is encountered mid-task, or when about to deviate from spec.
wei18/apple-dev-skills/collaboration-skills/skills/backlog-routing-by-topic Skill
18★ repoRoute mid-discussion stray ideas to the matching file's §Backlog section by topic — product → design.md; tooling → foundations.md; implementation step → plan.md; collaboration → methodology.md; unclassifiable → today's meeting log §Open questions. Invoke when a stray idea pops up during focused work, when reviewing a meeting log for parking lot items, or when asked "where does this idea go".
wei18/apple-dev-skills/collaboration-skills/skills/claude-skill-plugin-packaging Skill
18★ repoHow to distribute Claude Code skills for reuse across repos and how to install them — as a plugin via a marketplace, a pinned git-submodule with committed project-scope settings, or globally. Covers the depth-1 discovery rule (why a bare folder/submodule of skills is NOT found), the `settings.json` schema, aggregating other skill repos, and the gotchas. Invoke when sharing skills across projects, wiring a skill plugin into a repo, choosing flat-skills vs plugin, or asked "why aren't my submodule'd skills showing up / how do I install project skills".
wei18/apple-dev-skills/collaboration-skills/skills/github-contribution-workflow Skill
18★ repoAuthor GitHub contributions with the gh CLI — open/merge PRs, open issues, create/edit files on GitHub, set repo secrets, configure contribution-flow repo settings. Use when running `gh pr create` / `gh pr merge` / `gh pr checks` / `gh issue create` / `gh secret set` / `gh api`, checking CI before merge, or bumping a submodule pin. Covers Conventional branch/PR-title conventions, Co-Authored-By trailer + 🤖 footer, squash+delete merge, CLEAN-before-merge, `gh secret set` without --body, `git update-index` submodule bumps, the --no-verify rule. Does NOT cover pure local git, diff-vs-commit verification (→ pr-diff-verification), security repo settings (→ apple-public-repo-security), worktree conflicts (→ subagent-conflict-detection), plugin distribution (→ claude-skill-plugin-packaging).
Leader developer handoff contract
wei18/apple-dev-skills/collaboration-skills/skills/leader-developer-handoff-contract Skill
18★ repoWhen the main agent dispatches a sub-agent, the prompt MUST include 5 elements — (1) task scope with verifiable target, (2) files / docs the sub-agent should read, (3) explicit skill list to invoke, (4) expected return format (diff / markdown section / decision text), (5) verification criteria. Invoke when about to dispatch a sub-agent (Developer / Designer / Code Reviewer), writing the dispatch prompt, or when asked "what should the sub-agent prompt include".
wei18/apple-dev-skills/collaboration-skills/skills/methodology-pattern-extractor Skill
18★ repoRead accumulated meeting logs and session JSONL files, extract collaboration patterns that have repeated ≥ 3 times, and append them to `docs/methodology.md` §Patterns. Each entry captures trigger / action / outcome / next-time adjustment. Invoke when the user asks "update methodology", "extract patterns from this session", "consolidate recurring collaboration patterns", or after every 5+ meeting logs accumulate.
wei18/apple-dev-skills/collaboration-skills/skills/pr-diff-verification Skill
18★ repoUse before pushing a branch or opening a PR to verify `git show --stat HEAD` matches what the commit message claims. Prevents the "commit log wrote but code didn't make it" class of accidents where the commit message describes changes that aren't in the diff (e.g. amend overwrote the previous commit's content, force-push lost commits, worktree wipe lost staged work). Invoke whenever Leader is about to `git push` a feature branch OR open a PR.
wei18/apple-dev-skills/collaboration-skills/skills/session-to-meeting-log Skill
18★ repoRead a Claude Code session JSONL log and produce a clean timeline-style meeting log at `meetings/{YYYY-MM-DD}_{topic}.md`. Invoke when the user asks "turn this session into a meeting log", "archive today's discussion", "extract a meeting record from jsonl", or when wrapping up a working session before context window rolls.
wei18/apple-dev-skills/collaboration-skills/skills/skill-authoring-patterns Skill
18★ repoReusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos
wei18/apple-dev-skills/collaboration-skills/skills/spec-phase-orchestration Skill
18★ repoThe pre-implementation document pipeline — 5 files + `meetings/` directory (README.md + docs/design.md + docs/foundations.md + docs/plan.md + docs/methodology.md + meetings/), section-by-section approval (§What before §How), prerequisite checklist with Unconfirmed / Resolved gates, "no implementation code before design.md and plan.md approved" rule. Invoke when starting a new project that needs spec-first development, deciding doc structure, or when asked "which documents go in the spec phase".
wei18/apple-dev-skills/collaboration-skills/skills/subagent-conflict-detection Skill
18★ repoUse before dispatching a subagent (especially `isolation:"worktree"`) to avoid three dispatch hazards — file-scope overlap with an in-flight subagent, a stale dispatch base, and collisions with another live agent/session editing the same checkout or git-submodule path. Invoke when about to call the Agent tool with `isolation:"worktree"`; when another subagent is running; right after a merge or branch switch (verify the dispatch base first); or when another Claude session is editing a shared repo/submodule path.
wei18/apple-dev-skills/collaboration-skills/skills/subagent-review-cycles Skill
18★ repoThe Leader / Developer / Code-Reviewer triad pattern — Leader dispatches Developer for proposal → Code Reviewer for adversarial review (with WebSearch, no CLI) → Leader accepts/rejects with specific reasons → iterate up to `limit(N)` rounds. Round-1 cosmetic-grade fixes get inline-applied by Leader instead of consuming a round. Invoke when planning multi-round review on a document, dispatching a Code Reviewer subagent, or when asked "how many review rounds / what skills should the Code Reviewer carry".
daftAI2026/daftAI-skills/skills/daftai-image-to-svg Skill
no license18★ repoConverts transparent or solid-background single-color PNG files and SVG files containing one embedded or local PNG into verified path-only SVG output. Removes pure-color backgrounds automatically. Uses Potrace threshold and parameter scans with alpha error metrics to preserve detailed logos, stamps, engravings, and line art. Use when the user asks to convert images to SVG, vectorize PNG, convert bitmap to true SVG, remove embedded raster data from SVG, 图片转矢量, PNG 转 SVG, 真矢量, or 位图描摹.
daftAI2026/daftAI-skills/skills/daftai-subtitle-translator Skill
no license18★ repoTranslate subtitle files (SRT/VTT) between languages. Auto-detect source language, batch translate with count validation, optional bilingual merge output. Use when user asks to "translate subtitles", "翻译字幕", "subtitle translation", or needs subtitles converted to another language.
daftAI2026/daftAI-skills/skills/daftai-url-to-markdown Skill
no license18★ repoFetch any URL and convert to markdown using Chrome CDP, with automatic image downloading. Supports auto-capture and wait-for-user modes. Downloads article images to local directory and rewrites image references to relative paths. Use when user wants to save a webpage as markdown with images. Keywords: url to markdown, save webpage, download article, 网页转markdown
daftAI2026/daftAI-skills/skills/daftai-video-subtitler Skill
no license18★ repoBurn subtitles into local video files. Supports SRT/VTT/ASS formats, auto-detect subtitles and language, bilingual subtitle merging and translation. Use when user needs to hardcode subtitles into video. Keywords: 字幕烧录、burn subtitles、本地视频、hardcode subtitles
mahmoud20138/Tradecraft/plugins/tradecraft/skills/ai-agent-builder Skill
18★ repoExpert guide for building AI-powered coding agents that produce professional-quality output. Trigger whenever the user asks to build an AI agent, coding assistant, automation pipeline, tool-using LLM system, or says "agent", "agentic", "tool use", "function calling", "LLM pipeline", "AI workflow", "coding bot", or "autonomous AI". Covers agent architecture, tool design, skill loading, prompt engineering, context management, evaluation loops, and multi-step orchestration using the Claude API or any LLM API.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/ai-signal-aggregator Skill
18★ repoML-powered signal aggregation across ALL strategy skills — combines signals from every strategy using weighted voting, random forest meta-learner, and confidence calibration. THE MASTER SIGNAL COMBINER. Use for "combine all signals", "aggregate strategies", "meta strategy", "AI signal", "ensemble signal", "which signal to follow", "best signal now", "combine everything", "master signal", "AI recommendation", or any request to synthesize signals from multiple skills. This is the intelligence layer ABOVE trading-brain.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/ai-trading-crew Skill
18★ repoAI Trading Crew — 50-agent AutoGen system for US stock analysis. 8 specialized teams (Technical, Fundamental, Macro, Sentiment, Quant, Risk, Execution, Strategy) reporting to a Head Coach supervisor. Risk team has veto power. Devil's Advocate agent f
mahmoud20138/Tradecraft/plugins/tradecraft/skills/alternative-data-integrator Skill
18★ repoAlternative data sources for trading signals — Google Trends, web traffic, search volume, shipping/supply chain data, satellite imagery proxies, and economic nowcasting. Use this skill whenever the user asks about "alternative data", "Google Trends trading", "search trends", "web traffic signals", "nowcasting", "satellite data trading", "shipping index", "Baltic Dry", "unusual data sources", "non-traditional indicators", "big data trading signals", or any request to incorporate non-standard data into trading decisions. Works with trading-data-science for feature engineering and trading-brain for signal integration.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/analyze-gold Skill
18★ repoPre-configured combination command for gold (XAUUSD) analysis. Runs the full pair-analyze pipeline tuned for gold's volatility profile, session behavior, and dollar sensitivity. USE FOR - analyze gold, analyze XAUUSD, gold setup, trade gold, gold analysis, XAUUSD plan.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/analyze-us30 Skill
18★ repoPre-configured combination command for US30 (Dow Jones Industrial Average CFD) analysis. Runs the full pair-analyze pipeline tuned for US30's session-driven flow, earnings sensitivity, and Fed-rate reactivity. USE FOR - analyze US30, analyze Dow, analyze Dow Jones, US30 setup, trade US30, DJ30 plan.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/analyze Skill
18★ repoInstant full trading analysis — just type a symbol. Auto-detects asset class, timeframe, and runs the complete 18-phase master workflow. Use for ANY ticker/symbol like "EURUSD", "AAPL", "BTCUSD", "XAUUSD", "SPY", "NQ", "ES". This is THE one-command entry point.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/asian-session-scalper Skill
18★ repoTokyo session low-volatility scalping setups — range-bound strategies for the quietest session. Use for "Asian scalp", "Tokyo session trade", "Asian range", "night scalping", "low vol scalp", "Asian session strategy", or any Tokyo-session-specific trading. Works with session-profiler.
mahmoud20138/Tradecraft/plugins/tradecraft/skills/autohedge-swarm Skill
18★ repoAutoHedge — enterprise-grade autonomous hedge fund using swarm agent architecture. Sequential pipeline: Director → Quant → Risk Manager → Execution agents. Risk-first design: position sizing before any trade execution. Currently supports Solana; Coin