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: Dev tools
16,833 results · page 264 of 562
- View details
kmp-starter-resources-themeSkillDev tools
Resources and theming on the KMP Starter Template — centralized resources module, string externalization, localization, theme via ThemeDataStore, and colors/typography.
Ready to connect★ 162
- View details
kmp-starter-uiSkillDev tools
Reusable Compose UI kit on the KMP Starter Template — starter/ui/components, starter/ui/utils, and starter/ui/layouts. Know what's already built before writing new UI.
Ready to connect★ 162
- View details
publishSkillDev tools
Save final content and get platform-specific publishing guidance
Ready to connect★ 162
- View details
trendSkillDev tools
Scan trending topics in your domains and get content recommendations
Ready to connect★ 162
- View details
apportionSkillDev tools
Apportion an autonomous goal into execution units carrying their own completion conditions. Type: (GoalPlanUncompiled, User, APPORTION, AutonomousGoal × ExecutionHorizon) → ConditionBearingUnitPlan
Ready to connect★ 161
- View details
boundSkillDev tools
Define epistemic boundaries per decision. Fires when a decision's direction, scope, type, or ownership is undefined. Type: (BoundaryUndefined, AI, DEFINE, TaskScope) → DefinedBoundary
Ready to connect★ 161
- View details
conductSkillDev tools
Conduct method before object-level work. Fires when the work needs several moves in non-trivial order. Type: (MethodUnderdetermined, Hybrid, CONDUCT, WorkProspect × MoveGround) → ConductedMethod
Ready to connect★ 161
- View details
contextualizeSkillDev tools
Detect application-context mismatch after execution. Fires when correct output may not fit the actual context. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, Result) → ContextualizedExecution
Ready to connect★ 161
- View details
elicitSkillDev tools
Reverse-trace decision coordinates for axis-undetermined intent. Type: (AbstractAporia, Hybrid, REVERSE-INDUCE-CYCLE, IntentSeed × ExternalizedSubstrate) → ResolvedEndpoint
Ready to connect★ 161
- View details
geo-knowledgeSkillDev tools
Build and query an evidence-lined GEO knowledge graph from approved source bundles. Use for entity normalization, relation lineage, conflicting fact preservation, incremental source-hash updates, local/global knowledge queries, 知识图谱, 知识库, and 知识治理. Exclude unsourced facts, hidden conflict resolution
Ready to connect★ 161
- View details
goal-researchSkillDev tools
Delegate factual research to a Codex CLI session that uses Codex's builtin `goal` command and invokes Aitesis (`$inquire`) for Tavily-based external verification. User-invoked via /goal-research.
Ready to connect★ 161
- View details
groundSkillDev tools
Validate structural mapping between abstract and concrete domains. Presents concrete instantiations when mapping uncertainty is detected. Type: (MappingUncertain, AI, GROUND, R) → ValidatedMapping
Ready to connect★ 161
- View details
ideateSkillDev tools
Widen an empty or prematurely converged idea field; reads only the invocation. Type: (CandidateFieldUnderexpanded, User, DIVERGE, IdeationRequest) → DiverseCandidateField
Ready to connect★ 161
- View details
induceSkillDev tools
Crystallize a shared but unnamed concept from the concrete cases at hand. Type: (AbstractionInProcess, AI, INDUCE, A) → CrystallizedAbstraction
Ready to connect★ 161
- View details
inquireSkillDev tools
Infer context insufficiency before execution. Surfaces uncertainties through information-gain prioritized inquiry. Type: (ContextInsufficient, AI, INQUIRE, Prospect) → InformedExecution
Ready to connect★ 161
- View details
probeSkillDev tools
Deficit Recognition Probe — surface multiple deficit hypotheses for the user's current situation and route by user-constituted recognition (fit review, not protocol scoring).
Ready to connect★ 161
- View details
qmt-inner-backtestSkillDev tools
Interprets factor/stock-selection logic from strategy descriptions, research report PDFs, or screenshots, and generates QMT built-in daily-frequency factor backtest scripts based on the scripts/daily-factors-backtest.py framework. Use when the user mentions QMT built-in backtesting, factor stock-sel
Ready to connect★ 161
- View details
realignSkillDev tools
Project guide direction line via three-horizon fusion. Invoke with /realign.
Ready to connect★ 161
- View details
realizeSkillDev tools
This skill should be used when the user asks to "run the eval", "test whether the protocol actually works at runtime", "check type realization", "measure protocol fulfillment", "run the type-realization suite", "does the gate actually stop", or wants runtime evidence that a protocol's formal transit
Ready to connect★ 161
- View details
recollectSkillDev tools
Resolve vague recall into recognized context through AI-guided contextual scan and user-validated recognition — one session, or the line of work, topic, or settled concept spread across several.
Ready to connect★ 161
- View details
reduced-space-testSkillDev tools
Scoped empirical validation. Decomposes a target↔surrogate equivalence claim into facets, bounds a test space, captures evidence inside it, and carries the untested complement forward.
Ready to connect★ 161
- View details
review-loopSkillDev tools
Convergence-paced review-resolve loop over a change and its governing surfaces. Verifies each finding against the codebase and the base it is measured from, then re-reviews until each is disposed of.
Ready to connect★ 161
- View details
sketchSkillDev tools
Recognize and revise concrete sketches to discover a form when descriptions cannot settle intent. Type: (FitUnrecognized, Hybrid, SKETCH-RECOGNIZE-CYCLE, FormIntentSeed) → RecognizedForm
Ready to connect★ 161
- View details
sublateSkillDev tools
Vet working context by dialectical antithesis before action. Type: (ContextSuspect, User, VET, WorkingContext) → VettedContext
Ready to connect★ 161
- View details
apply-mantel-stylesSkillDev tools
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
Ready to connect★ 160
- View details
code-review-recent-changesSkillDev tools
Review recent changes since a fixed point (commit, branch, tag, or merge-base) across three independent axes - Standards, Spec, and Maintainability - producing severity-ordered findings with an explicit verdict. Use when the user wants to review a branch, a PR, or recent committed changes.
Ready to connect★ 160
- View details
code-simplificationSkillDev tools
Use this skill when you need to review and refactor code to make it simpler, more maintainable, and easier to understand. Helps with identifying overly complex solutions, unnecessary abstractions.
Ready to connect★ 160
- View details
critical-thinking-logical-reasoningSkillDev tools
Critically analyse the reasoning in written content (articles, blogs, transcripts, reports), not code. Use only when explicitly asked to critically analyse or critique an argument.
Ready to connect★ 160
- View details
diagnose-hard-problemSkillDev tools
Disciplined diagnosis loop for hard problems, diagnosing bugs and regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test.
Ready to connect★ 160
- View details
diagrams-as-codeSkillDev tools
Use only when creating architecture diagrams with Python's `diagrams` library (mingrammer/diagrams).
Ready to connect★ 160
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.