Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
8,868 results · page 250 of 296
- View details
git-guardrailsSkillAI & models
Use when a repository needs a guard against force-push, forced reset, clean, branch deletion, working-tree discard, stash drop, reflog expire, or gc prune. Not for remote or irreversible changes.
Ready to connect
- View details
github-backlog-triageSkillAI & models
Use when the user invokes backlog triage for a GitHub repo''s open issues and PRs. Not for proactive triage, non-GitHub trackers, or single bug issues: use github-bug-report-triage.
Ready to connect
- View details
github-bug-report-triageSkillAI & models
Use when evaluating whether a bug issue has sufficient detail and identifying missing reporter information. Not for non-bug issues or backlog triage: use github-backlog-triage.
Ready to connect
- View details
github-issue-dedupeSkillAI & models
Use when finding duplicate GitHub issues or checking for similar issues against a target issue. Not for closing, labeling, or modifying any duplicate issue.
Ready to connect
- View details
guillotineSkillAI & models
Use when dead, duplicate, superseded, or generated residue must leave more than one artifact class of a repo or subsystem, preserving behavior. Not for one enumerated record set: use clean-clean-cut.
Ready to connect
- View details
herdr-faqSkillAI & models
Launch and drive coding agents (codex, claude, agy) through the Herdr CLI. Use before starting or prompting a subagent via herdr agent or pane commands, and when a herdr command fails or an agent seems stuck or silently lost a prompt.
Ready to connect
- View details
instruction-understanding-gateSkillAI & models
Use when a request is long, bundled, high-stakes, or has ambiguous referents. Not for tiered scans: use askme. Not for interviews: use askme.
Ready to connect
- View details
interactive-drop-selectorSkillAI & models
Use when the user explicitly asks to choose which issues or pull requests to close interactively. Don''t use for closing items without per-item selection and explicit approval.
Ready to connect
- View details
ios-build-cleanupSkillAI & models
Use when the user wants a clean Xcode rebuild by deleting DerivedData and build artifacts. Do not use for diagnosing a specific build error; that is ios-build-fix.
Ready to connect
- View details
ios-build-fixSkillAI & models
Use when asked to run /ios-build-fix to fix a failing iOS build or UI behavior through the debug bridge. Not for a clean rebuild — use ios-build-cleanup.
Ready to connect
- View details
minimalism-drivenSkillAI & models
Use when writing or restructuring code, before adding a helper, wrapper, config key, or dependency, or when the user asks for minimal or DRY code. Produce the smallest complete implementation whose intent is obvious. Not for performance tuning — use the optimize skill.
Ready to connect
- View details
mswSkillAI & models
Apply the Minimum Sufficient Work (MSW) principle through the MSW Kernel to scope, execute, verify, and stop agent work. State the requested outcome and smallest proof, admit a claim only when deleting it would leave the contract unmet or unproven, do and prove each necessary claim, and halt at the
Ready to connect
- View details
multi-agent-tournament-scorecardSkillAI & models
Use when agent strategies need a reproducible finite tournament under a frozen evaluation protocol. Not for open-ended or infinite matchups: use a continuous benchmark.
Ready to connect
- View details
offenseSkillAI & models
Use when a human says "overhaul", "rebuild this subsystem", or "rewrite it from scratch" and the broken structure must be demolished and re-derived from its contracts. Deletes rather than deprecates, collapses special cases into the general case, and migrates every caller in one change. Not for thin
Ready to connect
- View details
plugin-scaffoldSkillAI & models
'Scaffolds a Claude Code / Cowork plugin bundle from a short YAML spec or from an existing agent definition''s
Ready to connect
- View details
principlesSkillAI & models
Use when a request names a working principle (subtract before you add, idempotent operations, never block on the human) or asks which principle governs a decision. Returns the law and its bite point; routes to the owning skill for execution. Not for running a repair — use fix.
Ready to connect
- View details
prismSkillAI & models
Use when one reviewer angle is insufficient or the user suspects a direction is tunnel-visioned or inherited its framing. Modes: artifact, direction. Not for source or remote-system changes.
Ready to connect
- View details
questSkillAI & models
Multi-agent quest orchestration. Plans, reviews, builds, and fixes features through coordinated agent handoffs. Use when the user invokes $quest or asks to run/resume Quest workflow.
Ready to connect
- View details
quickstart-onboardingSkillAI & models
'Dynamically guides a person through cloning + setting up the claude-code-marketing-quickstart
Ready to connect
- View details
refactor-break-compatSkillAI & models
Use when modernizing APIs, removing compat shims, killing feature flags, or rewriting a subsystem cleanly. Not for additive refactors that must preserve the old path.
Ready to connect
- View details
reproduce-and-fix-issuesSkillAI & models
Use when a trusted bug or performance report needs reproduction and fix. Drives the application, captures reproduction evidence, implements the minimal fix, and opens one draft PR with human approval. Not for untrusted reports or scope beyond the named feature.
Ready to connect
- View details
resonance-ops-founder-osSkillAI & models
The company operating system for a founder running a business with a fleet of agents. Owns company OKRs, scorecards, weekly reviews, L10/EOS and IDS, decisions, cadence, delegation, and authority budgets. Use when running the company operating rhythm or defining what an agent may spend, send, change
Ready to connect
- View details
resonance-ops-qaSkillAI & models
Quality Assurance Specialist. Proves that the system works, or breaks it trying. Use when writing a test plan, auditing test coverage against the 8-Path Matrix, writing destructive test cases, building an LLM eval suite, or performing a verification audit before a release.
Ready to connect
- View details
resonance-strategy-architectSkillAI & models
System Architect Specialist. Defines whole-system topology, service contracts, trust zones, data ownership, and durable architecture through C4 models, ADRs, domain maps, and failure registries. Use when work changes system boundaries or cross-system behavior. AI subsystem internals, prompts, retrie
Ready to connect
- View details
restart-keeping-lessonsSkillAI & models
Use when an implementation has more workarounds than structure and another patch will not pay. Not for in-place re-derivation: use breaking-driven. Not for one-artifact rewrites: use rewrite-clean-v0.
Ready to connect
- View details
rust-formal-verificationSkillAI & models
Use when Rust code, especially unsafe or panic-critical paths, needs a Kani, Verus, or Creusot harness written, run, and its failure read. Not for choosing the proof policy: use proof-driven.
Ready to connect
- View details
ruzzySkillAI & models
Lets your agent set up and run Ruzzy, a coverage-guided fuzzer for Ruby code and C extensions.
Ready to connect
- View details
sales-pipelineSkillAI & models
Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
Ready to connect
- View details
skill-authorSkillAI & models
Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
Ready to connect
- View details
slicing-code-contextSkillAI & models
Lets your agent pick out small, focused pieces of code and hand them to a smaller model for analysis or patch suggestions.
Ready to connect
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.