Loading...
Loading...
Found 5,150 Skills
Build and test the longest uncovered user journey from spec.md. Reads the product spec, checks existing journeys, picks the longest untested path, writes a UI test with screenshots at every step, then runs 3 polish rounds (testability → refactor UI test → UI review) until everything is clean. Use when the user says "next journey", "add journey", "test the next flow", "journey builder", or "cover more user paths".
Agent skill for repo-architect - invoke with $agent-repo-architect
Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]"
Retrieve ALL information from a Jira ticket (description, comments, subtasks, attachments metadata, labels, sprint, status, assignee, reporter, linked issues, custom fields, acceptance criteria) and persist it as a single Markdown file. Use whenever the user says "fetch ticket", "retrieve Jira", "pull ticket info", "get ticket details", "look up ticket", "grab the Jira", "what does ticket X say", "check the ticket", "read the ticket", "show me the ticket", or provides a Jira ticket URL or key like PROJECT-1234. Also triggered by the orchestrating-jira-workflow skill as Phase 1 of the end-to-end pipeline. Trigger even if the user only pastes a ticket key with no other context — that alone means "fetch this ticket." This skill ONLY retrieves — it never modifies the ticket or starts implementation.
Automatically create a PR to register insights, conventions, and best practices obtained from the current project as rules in the TBSten/skills repository. It runs the entire end-to-end process: collecting insights from the project's CLAUDE.md, .claude/rules/ directory and codebase, packaging them as reusable Claude Code rules, and creating the PR. Rules are files stored in .claude/rules/, and unlike skills, they do not require frontmatter. RULE.md serves as the main rule body, while detailed documentation (<rule-name>.md / <rule-name>.ja.md) is placed directly under the rules/ directory. Use when the user requests: "Register insights as rules", "contribute rule", "Share this rule", "Register as a rule", "Compile rules into a PR", "Turn this convention into a rule", "Turn best practices into rules". gh CLI and git must be installed.
Run Codex code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extract, score, and backlog new skill ideas from recent coding sessions.
Use whenever a beo session is starting, resuming, recovering from interruption, checking status, deciding what to do next, or when the correct beo skill is not obvious. This is the default bootstrap and routing entry point for the beo pipeline. Use first for prompts like "continue", "resume", "what's next?", "status?", "pick this back up", "where are we?", or any new feature request where the current phase is unclear.
Use when the user wants to analyze EKS application logs during or after a FIS experiment. Triggers on "analyze app logs", "application log analysis", "check application behavior", "分析应用日志", "查看应用表现", "应用日志分析". Supports two modes: real-time monitoring (during experiment) and post-hoc analysis (after experiment). Reads experiment context from aws-fis-experiment-prepare/execute outputs.
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
Reset Claude Code buddy/companion by changing the season seed (fk_) in cli.js and removing the companion field from ~/.claude.json, allowing re-hatching a new buddy. Triggers: buddy reset, reroll buddy, new buddy, change buddy, reset companion, reroll companion, buddy reroll
Connect Codex CLI as an MCP server — giving you codex_run and codex_review as native tool calls instead of black-box bash commands. codex_run covers six modes: explore (broad codebase discovery), inspect (targeted read-only and injected-context follow-up), build (write/edit code), debug (reproduce→diagnose→fix→verify), test (write/run tests), research (web search only). codex_review runs independent code review in an isolated thread. Each mode bakes in task-specific instructions so Codex performs well per task type. Use this skill whenever the user mentions: "set up codex MCP", "connect codex to claude", "codex MCP server", "install codex tools", "configure codex integration", or wants Codex available as native tools in any agent. Distributed via `npx skills add` — no global install needed.