Loading...
Loading...
Found 2,779 Skills
Autonomous project gardening by a coordinated team of agents. Spawns a team of gardeners that each run the `garden` skill in parallel, coordinating via a shared task list to avoid duplicate work. Use when the user wants to tend multiple small issues in one pass. Invoke with /gardeners.
Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.
Cultural adaptation for translated content. Run AFTER blog-translate completes. Adjusts brand examples, CTAs, legal references, and formality for the target market (German, French, Japanese, Spanish, etc.). Deep cultural adaptation of translated blog posts. Goes beyond translation to swap brand examples, adapt CTAs, substitute legal references, localize statistic sources where possible, and adjust formality (Sie/du, tu/vous, formal/informal). Built-in profiles for DACH, Francophone, Hispanic, and Japanese markets, plus a custom-locale template. Makes content feel locally authored, not translated. Use when user says "localize blog", "blog localize", "cultural adaptation", "adapt for Germany", "adapt for France", "lokalisieren", "localiser", "adaptar".
arthrod's coding philosophy and dispatcher. Universal red-green TDD, stacked PRs, test-always, evidence-before-claims. Routes to conejo-code (active coding), conejo-frontend (strict UI), conejo-merge (calm PR/merge). Use when starting any coding work or deciding how to approach a task.
Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_grounding pipeline. Triggers include 'image grounding', 'phrase grounding', 'ground captions', 'auto-label image grounding', 'image_grounding'.
亚马逊店铺 Listing 与刊登相关定义/限制（与 linkfox-amazon-store-auth / linkfox-amazon-store-report 同系列），经 LinkFox /spApi/developerProxy 调用 SP-API：Listings Items（get/search/patch/put/delete）、Listings Restrictions（getListingsRestrictions）、Product Type Definitions（searchDefinitionsProductTypes、getDefinitionsProductType）。当用户提到获取或删除 Listing、刊登限制、ASIN 能否卖、product type 定义、JSON Schema 刊登属性、searchDefinitionsProductTypes、getDefinitionsProductType、getListingsRestrictions、Listings Restrictions、亚马逊刊登列表 时触发。
Verify journals, prepare submission documents, check disclosures, and organize reviewer responses and revision evidence. Use when the user asks for "preparing for submission", "journal selection", "responding to reviewer comments", or requests the rw-journal-submission workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Design and execute reproducible systematic reviews, scoping reviews, and other evidence synthesis processes. Use when the user asks for "conduct a systematic review", "how to conduct a scoping review", "design a screening process", or requests the rw-review-methods workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Use when building AI agent storage workflows on Tigris — forks for isolated dataset copies, workspaces for per-agent buckets with TTL, checkpoints for snapshot/restore, and coordination for event-driven pipelines via bucket webhooks. Triggers on "@tigrisdata/agent-kit", "agent storage", "agent workspace", "agent fork", "isolated agent environment", "checkpoint and restore", "bucket webhook", "multi-agent pipeline"
Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks & open questions, and decisions/FAQ when they earn a tab) — published with the built-in Artifact tool to a default-private claude.ai page the user can share with teammates. Use when a piece of work spans several workstreams and you want a shareable overview kept current. Each artifact is backed by a small per-project config in the plugin data dir, so refreshing it re-gathers live state, redeploys the same URL, and reports only the delta. For software projects whose workstreams are PRs, also read swe.md (the X.Y PR-numbering convention; pulling PR state with gh/git; a per-PR detail block). Needs the built-in Artifact tool (claude.ai login). Not for single-PR changes or public docs.
Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits.
Interrogates a user's decision, plan, pitch, positioning, target market, pricing, or still-forming idea with sharp, unsparing questions — extended when useful to hostile or even unfair framings — until the plan sharpens into defensible decisions, or the user concludes it isn't a good idea after all. Acts as the constructive devil's advocate that the user cannot be for themselves. Load when the user wants to stress-test, attack, pressure-test, find holes in, or play devil's advocate against something they're attached to; when they ask to be "grilled," "beat up," or told "why I'm wrong"; when they suspect their plan contains wishful thinking, fluffy language, or an unnamed elephant in the room; or when they need to convert vague aspirations into real strategic decisions (with consequences accepted). Do NOT load for ordinary code review, prose editing, or general feedback requests without an adversarial frame.