Run and triage AI Atelie's Critical User Journey (CUJ) for every PR — the single end-to-end test that proves a user can open the app, create a project, drive the Claude Code agent, and see the canvas render. Before running, gate by inspecting the PR diff for changes that plausibly affect the journey (routes…
Run TypeScript scripts in sandboxed microVMs or Docker containers with AWS SDK access via IMDS. Use when investigating AWS resources, running read-only queries, or executing TypeScript automation that needs AWS credentials.
Current attested Codex, Claude Code, and Agent Skills extension contracts for skilltap. Use when designing, implementing, reviewing, or documenting harness adapters; plugin or marketplace manifests; native plugin lifecycle; skill directories or SKILL.md frontmatter; AGENTS.md/CLAUDE.md bridges; configuration scopes…
Protocol for working with the dejavu error-gate plugin. Use when a tool call is answered with a "[dejavu] REMINDER" or "[dejavu] BLOCKED" message, when the same tool call fails repeatedly, or when you discover the root cause of a gated failure. Covers how to react to reminders, what BLOCKED means, the dejavu:proceed…
Controls Obsidian vaults via the official CLI (1.12+). Reads, creates, appends to, and searches notes. Manages daily notes, tasks, tags, properties, templates, bookmarks, and plugins. Analyzes knowledge graph structure including backlinks, orphans, and unresolved links. Triggers on Obsidian, vault, notes, daily notes…
Use when the user wants to extract text from PDFs or images, manage OCR jobs, or work with output presets via the local Extracto OCR webapp. Talks HTTP to a running Extracto instance using the bundled extracto CLI.
Use when a bug, regression, race condition, or unexpected behavior has no proven root cause and you must confirm the cause with runtime evidence instead of guessing from source code.
Use when an agent needs live, structured search-engine data through SerpApi (web results, news, shopping, local, jobs, flights, scholar, images, video). Covers picking the right engine for the intent, choosing compact vs complete output, query operators, pagination, deduping and citing results, and when NOT to search.…
Tour is a local code-walkthrough CLI for AI agents. After finishing a task, the agent leaves line-anchored comments on a pinned git diff (a guided traversal) that a human steps through in a TUI or webapp. Activates when the user asks to "review this branch", "review this PR", "walk me through this diff", "leave…
Use Atet to create, generate, record, edit, and render visual media with a local CLI and coding agent. Trigger for AI image or video generation, screen, camera, microphone, or system-audio recording, non-destructive video editing, silence and filler-word removal, captions or subtitles, speaker framing, screen zooms…
★not rated 5▲
+1
changed 3d agoASkillSpector: pass125 tokens
originalMIT
Migrate Cloudflare Workers to Bun with runtime compatibility analysis. Use when converting Workers to Bun, migrating from Cloudflare bindings, or moving from edge to server deployment.
Use Wrench to give a bring-your-own coding agent bounded, local-first web capabilities: capture or scrape public and signed-in web pages into Markdown; archive authorized audio, video, and transcripts with verification; query encrypted cached email, contacts, inbox, and messaging views; resolve a live conversation…
Build or change a backend with stitchkit — the contract-first framework where one defineContract() becomes an HTTP API, MCP tools, AI-agent tools, a CLI and a typed client. Use this whenever working in a project that depends on stitchkit: defining or editing a contract, implementing handlers, exposing endpoints as MCP…
Persistent cross-session, cross-tool memory for this project via captain-memo. Use at the START of any non-trivial task to recall prior context, decisions, conventions, and past bugs/fixes, and whenever you'd ask "have we done / decided / hit this before?". Searches a shared local memory corpus (past session…
Use whenever the conversation involves the user's projects, systems, infrastructure, people, past decisions, or recurring problems — even when memory is not explicitly mentioned. Trigger on possessives and project references ("my project", "our server", "remember when we", "last time"), named systems and services in…
Use this skill whenever the user mentions "anywrite" by name, or mentions Anytype, asks to create/update/search/organize notes, tasks, or PKM objects in Anytype, or wants to upload files, manage properties/tags/types, or chat inside an Anytype space. Covers all 52 endpoints of the Anytype local API (spaces, objects…
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
Expertise in high-performance native codebase scanning and validation using Rust. Trigger this skill when asked to "scan the codebase natively", "run rust scanner", or "validate bxc core using rust".
Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.
Update libraries in a Bun project or monorepo with control over overrides, exact pins, 0.x versions, peer conflicts, supply-chain risk, and lockfile rebuild. Use when updating dependencies, bumping libraries, checking outdated packages, running bun audit, cleaning up overrides/resolutions, deduplicating the tree, or…
★not rated 2 17d agoB72 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: