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
9,019 results · page 110 of 301
- View details
claude-code-plugin-referenceSkillAI & models
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
Ready to connect★ 337
- View details
clear-contextSkillAI & models
Manages context overflow by handing off to a fresh subagent at 80% usage. Use when context pressure is critical and work must continue uninterrupted.
Ready to connect★ 337
- View details
- View details
code-communitiesSkillAI & models
Detects architectural clusters and coupling boundaries via community detection on the code graph. Use when identifying module groupings or refactoring targets.
Ready to connect★ 337
- View details
code-quality-principlesSkillAI & models
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.
Ready to connect★ 337
- View details
compression-strategySkillAI & models
Recommends context compression strategies for bloated or quota-heavy sessions. Use when context feels sluggish or quota burns faster than expected.
Ready to connect★ 337
- View details
content-sanitizationSkillAI & models
Provides sanitization guidelines for external content in skills and hooks. Use when loading GitHub Issues, PRs, WebFetch results, or any untrusted input.
Ready to connect★ 337
- View details
- View details
context-mapSkillAI & models
Lets your agent build a map of the files relevant to a task before editing code.
Ready to connect★ 337
- View details
- View details
Create IssueSkillAI & models
Create a new GitHub issue with formatted description, labels, and optional reference links
★ 337
- View details
damage-controlSkillAI & models
Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols. Use when an agent session fails or a worktree is corrupted.
Ready to connect★ 337
- View details
decisive-actionSkillAI & models
Guides when to ask clarifying questions versus proceed autonomously. Use to reduce unnecessary clarifying questions when intent is clear.
Ready to connect★ 337
- View details
deferred-captureSkillAI & models
Defines the contract for deferred-item capture across plugins. Use when building or validating a plugin's deferred-capture wrapper or adding source labels.
Ready to connect★ 337
- View details
dependency-graphSkillAI & models
Generates a Mermaid dependency graph showing import relationships between modules. Use when analyzing coupling, finding circular deps, or planning refactors.
Ready to connect★ 337
- View details
dependency-verificationSkillAI & models
Verifies a package exists before install, defending against hallucination and slopsquatting. Use when adding, recommending, or installing a package.
Ready to connect★ 337
- View details
DigSkillAI & models
Interactively refine research results by searching deeper into a specific subtopic or channel. Requires an active research session from /tome:research.
★ 337
- View details
DismissSkillAI & models
The ONLY way to stop the egregore. Human-initiated graceful shutdown that saves all state.
★ 337
- View details
Do IssueSkillAI & models
Implement issues (GitHub/GitLab/Bitbucket) using progressive analyze-specify-plan-implement workflow
★ 337
- View details
dorodangoSkillAI & models
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
Ready to connect★ 337
- View details
Elegant Code ReviewSkillAI & models
Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.
★ 337
- View details
elegant-codeSkillAI & models
Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage. Use when adding code, choosing a dependency, or auditing a diff.
Ready to connect★ 337
- View details
error-patternsSkillAI & models
Provides error classification, recovery, and graceful-degradation patterns. Use when implementing error handling or debugging resilience failures in any skill.
Ready to connect★ 337
- View details
escalation-governanceSkillAI & models
Assess whether to escalate models. Use when evaluating reasoning depth.
Ready to connect★ 337
- View details
evaluation-frameworkSkillAI & models
Provides weighted scoring, rubrics, and decision-threshold patterns. Use when designing quality gates, evaluation systems, or decision frameworks.
Ready to connect★ 337
- View details
Fix PrSkillAI & models
Address PR/MR review feedback by reading comments, implementing fixes, and resolving threads. GitHub and GitLab support.
★ 337
- View details
Fix WorkflowSkillAI & models
Retrospective analysis and improvement of workflow components with self-evolving patterns
★ 337
- View details
FixitSkillAI & models
Fix broken functionality from pasted error output, stack traces, or failing-behavior descriptions using research, TDD, and proof-of-work evidence.
★ 337
- View details
friction-detectorSkillAI & models
Detect friction signals; graduate patterns into rules. Use for session retrospectives.
Ready to connect★ 337
- View details
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.
54,764 of the 55,196 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.