dversoza
UserReusable skills for extending coding assistants
Categories
Indexed Skills (9)
pr-feedback
Address PR review feedback including inline threads, general comments, bot-generated reviews, PR description findings, check run annotations (inline lint/type/security findings shown in the Files changed tab), code scanning alerts, and CI failures. Use when asked to handle, address, resolve, respond to, or work through PR review comments, review feedback, inline findings, or CI check failures. Triggers on requests like "address PR comments", "handle review feedback", "resolve PR reviews", "fix review comments", "go through PR feedback", "check CI failures", "fix the inline findings on the PR".
opensearch
Read-only OpenSearch/Elasticsearch querying, index introspection, and search-query (DSL) execution. Use when the user asks to query OpenSearch or Elasticsearch, run a search query/DSL, check a cluster's health, list indices, inspect an index mapping, count documents, fetch a document by id, or debug why a search does/doesn't match. Triggers on requests like "query opensearch", "run this search DSL", "list the indices", "show the users mapping", "how many docs in X", "why doesn't this wildcard match", "check the cluster health".
redis
Read-only Redis / ElastiCache querying, key inspection, and cache debugging. Use when the user asks to query Redis, check a Celery queue depth, count keys, inspect or dump a key, check a TTL, look at the session cache, check Redis memory or evictions, see connected clients, read the slowlog, or find out whether something is cached. Triggers on requests like "query redis", "check the celery queue depth", "how many keys in redis", "inspect this redis key", "check redis memory", "look at the session cache", "is this cached", "what's the TTL on X", "is the queue backed up".
1password
Secure 1Password CLI (op) access patterns. Use when any task requires reading secrets, tokens, API keys, passwords, or credentials from 1Password. Also use when another skill or workflow needs to retrieve a secret from a vault. Provides secure read patterns and strict rules to prevent secret leakage into conversation context, terminal output, or environment variables visible to Claude. NEVER bypass these patterns by running op commands directly without following the security rules below.
asana
Create, read, and update Asana tasks from the command line. Use whenever the user wants to interact with Asana: list their tasks or a project's tasks, look up a task by id or link, create a new task, update a task's title, notes, due date, assignee, or project membership, or mark a task complete. Triggers on requests like "what's on my Asana", "list my Asana tasks", "create an Asana task for X", "add a task to project Y", "update the due date on that task", "mark this Asana task done", "show me the tasks in <project>". Wraps the Asana REST API in an `asana` CLI. Deliberately does not delete tasks.
postgres
Read-only PostgreSQL database querying, schema introspection, and query planning. Use when the user asks to query a database, look up data, check a table, describe a schema, list tables, show indexes, explain a query plan, or any other read-only PostgreSQL interaction. Triggers on requests like "query the users table", "show me the schema", "what tables are in staging", "run this SQL", "describe the orders table", "check the database", "how many rows in X", "explain this query".
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
concise-writing
Enforced concise style for everything the assistant writes: PR descriptions, commit messages, code comments, PR reviews and replies, tickets, chat messages, and docs. Simplified Technical English (adapted from ASD-STE100) plus hard per-artifact budgets, enforced by a blocking PreToolUse hook (scripts/concise_check.py). Use when writing or rewriting any of these artifacts, when a hook denial asks for a rewrite, or on requests like 'make this concise', 'STE rewrite', 'less verbose'.
backlog-grooming
Groom a project's backlog end-to-end by analyzing every open ticket against the actual codebase and git history, across Jira or Asana. Use when the user asks to groom / triage / clean up / prioritize a backlog, find low-hanging fruit, detect tickets that are already done but still open, assess epics for closure, or propose new tickets. A provider adapter extracts the backlog into a canonical dataset, then provider-neutral analysis cross-references code and merged PRs and produces a prioritized, propose-only grooming report. It NEVER mutates the tracker unless the user explicitly approves a separate execution pass.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.