Loading...
Loading...
Found 1,658 Skills
Run existing ShinkaEvolve tasks with the `shinka_run` CLI from a task directory (`evaluate.py` + `initial.<ext>`). Use when an agent needs to launch async evolution runs quickly with required `--results_dir`, generation count, and strict namespaced keyword overrides.
Two-way sync between a local paper directory and an Overleaf project via the Overleaf Git bridge (Premium feature). Lets you keep ARIS audit/edit workflows on the local copy while collaborators edit in the Overleaf web UI. Token never touches the agent — user does the one-time auth via macOS Keychain. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to bridge their ARIS paper directory with an Overleaf project.
Phase 2 of the issue process — Read the issue report + read the code, identify the true root cause and assess repair risks, and finally provide users with 2-3 repair solution options for them to decide. **Do NOT start modifying code in this phase** — present the conclusions to the user after analysis, and only proceed to Phase 3 after the user confirms the solution. Prerequisite: cs-issue-report has been completed. Trigger scenarios: The user says "Analyze this bug", "Find the root cause", "Locate the issue", and {slug}-report.md already exists in the issue directory.
Unified LLM torch-profiler triage skill for `sglang`, `vllm`, and `TensorRT-LLM`. Use it to inspect an existing `trace.json(.gz)` or profile directory, or to drive live profiling against a running server and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.
Convert .NET projects and solutions (.sln, .slnx) to NuGet Central Package Management (CPM) using Directory.Packages.props. USE FOR: converting to CPM, centralizing or aligning NuGet package versions across multiple projects, inlining MSBuild version properties from Directory.Build.props into Directory.Packages.props, resolving version conflicts or mismatches across a solution or repository, updating or bumping or syncing package versions across projects. Also activate when packages are out of sync, drifting, or inconsistent -- even without the user mentioning CPM. Provides baseline build capture, version conflict resolution, build validation with binlog comparison, and a structured post-conversion report. DO NOT USE FOR: packages.config projects (must migrate to PackageReference first) or repositories that already have CPM fully enabled.
Append-only task record convention for Loom. Use when reading or writing per-task records under `.agents/tasks/<task-id>/`, when another skill needs to log a lifecycle milestone (saved, decision, readiness, blocker, done), when the user asks about an existing task's status or progress, or when checking task records for drift via the linter. Do NOT trigger for creating new tasks (that is `task-brief`'s job), for general docs/planning unrelated to a task directory, or for historical questions about the retired `task-state-management` system.
Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.
Use when creating a new Phoenix project, adding Phoenix to an umbrella, configuring assets with Bun, setting up devenv.nix for a Phoenix project, configuring Ecto with PostgreSQL Unix sockets, or adding end-to-end tests.
Patterns for DeFi market analysis, screening, and comparison using DefiLlama MCP tools. Covers valuation ratios (P/S, P/F), growth screening with pct_change columns, multi-metric protocol comparison, category comparison, and cross-entity analysis. Use when users ask to compare protocols, screen for undervalued projects, analyze growth trends, or do sector analysis.
This skill should be used when the user asks to "write a pipeline", "add caching", "make this build faster", "show test failures in the build page", "add annotations", "only run tests when code changes", "set up dynamic pipelines", "add retry", "parallel steps", "matrix build", "add plugins", or "work with artifacts in pipeline YAML". Also use when the user mentions .buildkite/ directory, pipeline.yml, buildkite-agent pipeline upload, step types (command, wait, block, trigger, group, input), if_changed, notify, concurrency, or asks about Buildkite CI configuration.
Skill for optimizing article style to remove AI flavor. Used to identify and rewrite issues such as AI traces, template tone, material-like style, translationese, empty buzzwords, excessive golden sentences, overuse of em dashes, bullet stacking, and random bolding in articles, official account drafts, self-media drafts, oral broadcast scripts, speech scripts, course scripts, and product copy; activated when users say phrases like "remove AI flavor", "eliminate AI traces", "not written by AI", "more human-written", "more natural", "less robotic", "remove template feel", "polish to official account final draft". Not applicable for fact-checking, zero-based topic planning, converting papers to official account articles, pure title generation, or pursuing AI detector pass rates.
Execute Claude Code commands in the telegram_agent project directory. Use when the user wants to work on the telegram agent itself, fix bugs, add features, or modify the bot code. This is a COMMAND HANDLER, not a script executor.