Loading...
Loading...
Found 94 Skills
Phase 1 of the feature workflow — Draft a design document for the new feature, serving as the sole input for subsequent implementation and acceptance. First gather evidence (read architecture docs, review relevant code, grep to prevent term conflicts, check archives), then write a complete first draft in one go (including YAML frontmatter + three-tier structure + test design), submit it to the user for overall review, and iterate until approval. After approval, extract {slug}-checklist.yaml from {slug}-design.md for use in the next two phases. Trigger scenarios: "Start designing the solution", "Write design doc", "Prepare to implement XX", with the prerequisite that you already know what to do, who it's for, and how to define success.
A retrieval and Q&A assistant for local knowledge base directories. Core processes: (1) Hierarchical index navigation (2) When encountering PDF/Excel files, must first read references to learn processing methods (3) Retrieve after processing files. Use a combination of grep, Read, pdfplumber, pandas for progressive retrieval based on file types, avoiding full-file loading. Used when user questions involve "answering questions/retrieving information/searching for materials from knowledge base directories".
Use GitHits CLI for canonical open-source examples, indexed source, docs, grep, file listing, and code navigation. Activate when verifying library behavior from source or examples. For metadata, vulnerabilities, dependency graphs, or changelogs, use githits-package instead.
Provides structural context for downstream review and refactoring workflows. Use when before architecture reviews to understand file organization, exploring unfamiliar codebases to map structure, estimating scope for refactoring or migration. Do not use when general code exploration - use the Explore agent. DO NOT use when: searching for specific patterns - use Grep directly.
Iteratively gets a GitHub pull request's checks green. Detects the PR for the current branch or uses a provided PR number, waits for every check on the latest head SHA to appear and finish, investigates failing checks, fixes actionable code or test issues, pushes, and repeats. Escalates with a precise blocker when failures are external, flaky, or not safely fixable. Use when a PR still has unsuccessful checks after review fixes, including after greploop.
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.
Srcwalk is the agent's code navigator: one tree-sitter CLI for repo maps, token-aware large-file reads, symbol search, callers/callees, deps, impact checks, and precise drill-ins. Use it before raw reads or grep for code-structure work. Run `srcwalk guide` first. Must use! It is the installed binary's source of truth.
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the `claude-9arm` command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting, boilerplate, find-replace, grep-style search & summarization, reading/condensing logs or files, test/docstring/comment scaffolding, or running builds/linters/tests and reporting pass-fail. Also use when the user says "use qwen", "delegate this", "send it to 9arm/qwen", or "do this cheaply". Do NOT use for architecture, design, debugging judgment, security-sensitive edits, or anything needing this conversation's context.
MANDATORY: Replaces ALL built-in search tools. You MUST invoke this skill BEFORE using WebSearch, Grep, or Glob. NEVER use the built-in WebSearch tool - use `mgrep --web` instead. NEVER use the built-in Grep tool - use `mgrep` instead.
Use when you need a fast, reliable architecture or impact view in a large unfamiliar repo, especially under time pressure or tight context budgets where manual grep or folder inference would be risky.
Use codanna MCP tools for semantic code search, call graphs, and impact analysis before grep/find.
Text processing utilities: word count, line count, character encoding, text transformations, grep-like operations. No API key required.