Loading...
Loading...
Found 41 Skills
Use this skill whenever designing, building, or reviewing a command-line tool that AI agents or automation will invoke — covers non-interactive flags, layered --help with examples, stdin/pipeline composition, actionable errors, idempotency, dry-run, destructive-action safety, and predictable command structure. Trigger even if the user doesn't explicitly say "agent-friendly" — apply whenever they are writing `--help` text, adding a new subcommand, designing error messages, or reviewing a CLI's UX.
Interactively prune stale non-terminal workflows from the pipeline. Use when the user says 'prune workflows', 'clean stale workflows', 'pipeline cleanup', or runs /prune. Runs a dry-run preview, displays candidates with staleness and safeguard skips, prompts the user to proceed/abort/force, then bulk-cancels approved workflows with a workflow.pruned audit event. Safeguards skip workflows with open PRs or recent commits unless force is set.
openerp (Kingdee Cloud·Star ERP CLI) Shared Base: Profile credential configuration, LoginBySign authentication and session reuse, general query (ExecuteBillQuery), output envelope and exit codes, dry-run. Must-read before using openerp for the first time, configuring profile, or troubleshooting authentication/query issues.
Comprehensive toolkit for validating, linting, testing, and automating Ansible playbooks, roles, and collections. Use this skill when working with Ansible files (.yml, .yaml playbooks, roles, inventories), validating automation code, debugging playbook execution, performing dry-run testing with check mode, or working with custom modules and collections.
Investigate LLM analytics evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).
Execute, validate, and debug Midscene YAML automation files. Handles dry-run, execution, report analysis, and iterative debugging.
Use when syncing or updating previously installed skills to their latest version. Always dry-run updates before applying, and check for breaking changes.
Find incomplete records, normalize field values in bulk, dedupe with `hubspot objects merge`, and audit custom properties. Builds on `bulk-operations` for JSONL piping and dry-run/digest/confirm.
Revolut X grid trading strategy. Use when the user asks to "backtest a grid strategy", "optimize grid parameters", "run a grid bot", "grid trading", "dry run grid", or runs revx strategy grid commands. Grid run is a long-running background process.
Monitor Catchtable for open reservation slots and attempt booking using a logged-in Chrome session.
Organize SpecStory AI coding sessions in .specstory/history into year/month folders. Run when user says "organize my history", "clean up specstory", "sort my sessions", or "organize specstory files".
Sync design tokens between code and Figma variables with strict drift reporting, mandatory approval gate, safe delta apply, and persisted reports.