Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 961 files from 2 125 authors, of which 68 678 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says "I do not know this area", "give me the map", "zoom out", "orient me".
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation.
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 8 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".
Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying "commit", "git commit", "save my changes", or ready to commit after making changes.
Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `<wiki>/derived/surveys/<slug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a "survey", "literature review", "lit review", or "deep dive" on a technical topic.
Drive a change through a red-green-refactor loop - failing test first, minimal code to pass, then clean up. Use when implementing a feature or fixing a bug where correctness matters and a test can pin the behavior. Says "TDD", "test first", "red green refactor", "write the test first".
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, plus a shadow FTS5 index so any session can recall it. Use when the user says "start a wiki", "add to wiki", "compile a page", "wiki on X", or wants a long-lived knowledge base on a topic, paper, product, person, project, or codebase.
Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says "what does the wiki say about X", "ask wiki", "search wikis", or before drafting a new wiki page (to avoid duplication).
Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or convergence. Use when the user says "research <topic>", "grow the <slug> wiki", "auto-research", or wants a knowledge base that builds itself overnight.
Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.
End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
Apply clear-writing standards to any prose the agent produces - READMEs, docs, UI copy, error messages, commit and PR text, release notes. Use when writing or editing documentation, interface copy, or any text a human will read. Says "write the README", "improve this copy", "draft the docs", "word this error".
Fetch the latest financial signals and transmission-chain analyses from DeepEar Lite. Use when the user needs immediate insights into financial market trends, stock performance factors, and reasoning from the DeepEar Lite dashboard.
Create visualize finance logic diagrams (e.g., Draw.io XML) to explain complex finance transmission chains or finance logic flows.
Fetch hot finance news, unified trends, and prediction financial market data. Use when the user needs real-time financial news, trend reports from multiple finance sources (Weibo, Zhihu, WallstreetCN, etc.), or Polymarket finance market prediction data.
Market prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments.
Plan, write, and edit professional financial reports; generate finance chart configurations. Use when condensing finance analysis into a structured output.
Perform finance web searches and local context searches. Use when the user needs general finance info from the web (Jina/DDG/Baidu) or needs to retrieve finance information from a local document store (RAG).
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.
Track finance investment signal evolution and update logic based on new finance market information. Use when monitoring finance signals and determining if they are strengthened, weakened, or falsified.
Search A-Share/HK/US finance stock tickers and retrieve finance stock price history. Use when user asks about finance stock codes, recent price changes, or specific company finance stock info.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Security audit of a codebase — web apps, APIs, services, CLI tools, libraries, daemons, and more. Use when asked to find security bugs, do a security review, audit for vulnerabilities, or pen-test the code. Focuses on exploitable issues with real impact, not theoretical concerns or industry-standard behavior.
Generate correct pg_durable SQL code for durable function workflows. USE WHEN: writing pg_durable DSL, creating durable functions, using df.start(), composing ~> |=> & | ?> !> @> operators, building ETL pipelines, loops, parallel joins, race conditions, conditional branching, HTTP requests, signals, cron scheduling, or variable substitution in pg_durable. DO NOT USE FOR: general PostgreSQL queries unrelated to pg_durable, Rust extension development, or duroxide internals.
Creates event-driven email listeners that monitor for specific conditions (like urgent emails from boss, newsletters to archive, package tracking) and execute custom actions. Use when user wants to be notified about emails, automatically handle certain emails, or set up email automation workflows.
Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when user wants reusable actions for their specific workflows (send payment reminder to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources).
Transforms research findings into executive-ready briefings. Automatically activated when user mentions 'executive', 'briefing', 'C-suite', 'board', 'leadership', or 'presentation'.
|
| Use when the user wants to see, inspect, cancel, or prune background agents fired during prior chain runs. Read/manage `.hyperflow/background/registry.json` and the per-agent output buffers at `.hyperflow/background/<id>.md`. Standalone — never auto-invoked.
| Use when the user wants to view, search, add, edit, prune, archive, or clear hyperflow memory entries. CRUD interface for `.hyperflow/memory/` — never modifies source code, only memory files.
| Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the designer specialist, and reviews for taste + accessibility. Standalone — ends with a handoff gate into the chain.
| Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to parallel agents with per-task model selection. Use when capturing chat to Notion, running the To-Do queue, suggesting, approving, or discussing tasks, or coordinating multi-task batches. Trigger with "/agency-os" subcommands or "run the queue").
| Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules carry over. Lossy (no slash commands, no actual skill dispatch) but useful.
| Use when ready to ship — runs pre-push gates (lint, typecheck, build, tests, security sweep), commits, releases, and pushes. Standalone, never auto-invoked. Push always requires explicit confirmation.
| Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy.
| Use when managing a two-session handoff — inspecting, picking up, or reviewing a committed handoff package produced by a session=two scope run. The operator interface over the cross-environment handoff lifecycle (plan in one session, build in another, review back in the first).
|
| Use when the user wants to manually flush a deferred-commit queue from a prior or interrupted chain. Reads .hyperflow/commits-queue/manifest.json, fast-forwards the staging branch onto the user's branch, deletes staging, clears the queue. Recovery interface when a chain crashed before its Step 4 auto-flush ran.
| Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the standard chain with a PR exit.
| Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain.
|
| Use when the user wants a one-screen view of current hyperflow project state — version, profile freshness, memory count, and live progress on every in-flight task. Read-only; never modifies state, never dispatches workers.
| Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request doesn't need, then STOPS at a build-location gate (build here, hand off to another session, or just keep the plan). Plan never implements.
| Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix.
|
|
Hacker News post crafter — given a product, feature, or story produces a ready-to-post HN submission (title ≤80 chars, no marketing), honest body text with technical depth, no outbound links, predicted reception analysis, and comment-response templates for likely pushback. Use when asked to "write an HN post", "craft a Show HN", "prepare our Hacker News launch", or "help me post on HN".
Developer relations playbook builder — produces a DevRel program design covering community platform, contributor program tiers, ambassador criteria, event strategy, and success metrics. Use when asked to "build a DevRel program", "design our developer community", "create a contributor program", "start a developer advocacy program", or "how do we grow our dev community".
Claude Skills — questions
Answers built from the skills we actually parsed.