Loading...
Loading...
Found 6,275 Skills
When the user says phrases like "update the index", "add this to the index", "added a new file", "added a new book/note/document", "need to update the material library index", the **Incremental Maintenance Mode** of this skill should be used. When the user says phrases like "index health check", "index体检", "check the index", "sync the index", "fill in missing index entries", the **Health Check Mode** of this skill should be used to scan all libraries ↔ INDEX to find missing/invalid entries and batch fill them in. Applicable to all libraries with INDEX.md: Reading Notes Library, Core Concepts Library, Viral Script Library, 04-Methodology Precipitation, and any newly created libraries in the future. The value of an index depends on content accuracy—you must fully read the original text before writing; inferring based on file names or impressions will render the index useless for reference. Even if the user only says "I added a file" or "put this in", as long as it involves the index, this skill should be triggered. Do NOT trigger for: Only viewing the index (directly Read), deepening topics (use li-topic), generating scripts (use li-writer). Use when the user adds new content to any indexed library, OR runs a global index health-check to find missing/stale entries.
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", or wants context on a specific location in the codebase.
DataWorks metadata Skill for Alibaba Cloud — browse Data Map metadata and perform non-destructive writes via Aliyun CLI. READ scope: list/get catalogs, databases, tables, columns, partitions; query data lineage (upstream/downstream impact); list/get datasets & versions; list/get metadata collections (Category/Album) and entities inside them; preview dataset version content. WRITE scope (non-destructive only): update table & column business metadata; register lineage relationships; create/update datasets and versions; create/update metadata collections and add entities to them. This Skill exposes NO delete or remove APIs — every `delete-*` and `remove-*` operation is intentionally out of scope. For deletions, use the DataWorks console. Triggers: "dataworks metadata", "data map", "data lineage", "meta collection", "dataset", "catalog", "table info", "column info", "partition", "impact analysis", "register lineage", "create dataset", "update business metadata".
Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.
Improve a skill using a test-fix-retest loop. Runs static checks, proposes targeted fixes, rewrites the skill, re-tests, and keeps or reverts based on score change.
Use when you need to implement acceptance tests from a Gherkin .feature file for Quarkus applications — including @acceptance scenarios, @QuarkusTest, BaseAcceptanceTest with QuarkusTestResourceLifecycleManager for Testcontainers and WireMock, REST Assured for full HTTP pipeline testing, WireMock JSON mapping files (classpath:wiremock/mappings/), *AT suffix naming, and Maven Surefire/Failsafe three-tier split. Requires the .feature file in context. This should trigger for requests such as Implement Quarkus acceptance tests from a Gherkin feature file; Set up BaseAcceptanceTest with Testcontainers and WireMock for Quarkus; Create WireMock JSON mapping files for external HTTP stubs in Quarkus acceptance tests; Configure Maven *AT naming convention and Failsafe plugin for Quarkus acceptance tests. Part of cursor-rules-java project
Apiiro CLI commands for querying the Guardian AI agent: ask security questions, get analysis and insights about a repository, and manage repository detection. Use this skill whenever the user wants AI-powered security analysis, security posture review, or wants to ask questions about their codebase's security. Also trigger when they need deep analysis of authentication flows, attack surfaces, or want an AI to explain security concepts. Even without mentioning "apiiro" or "guardian", trigger when the user asks things like "is this code secure?", "what's the attack surface here?", or "explain this vulnerability". For dedicated STRIDE threat modeling of a design or feature spec, use the apiiro-threat-model skill instead. For fixing a known risk, use apiiro-fix.
Load data into MotherDuck from local files, object storage, HTTPS, dataframes, or external databases. Use when choosing a MotherDuck-specific ingestion path, especially CTAS and INSERT...SELECT, bulk loading, secrets, and Postgres-endpoint versus DuckDB-client tradeoffs.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing academic-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
Claude + Obsidian knowledge companion. Sets up a persistent wiki vault, scaffolds structure from a one-sentence description, and routes to specialized sub-skills. Use for setup, scaffolding, cross-project referencing, and hot cache management. Triggers on: "set up wiki", "scaffold vault", "create knowledge base", "/wiki", "wiki setup", "obsidian vault", "knowledge base", "second brain setup", "running notetaker", "persistent memory", "llm wiki".
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.