Loading...
Loading...
Found 26 Skills
Detect new or modified skills in .agents/skills/ by comparing git hashes against ai-skills, snapshot for rollback, review, publish to ai-skills, install locally, and cherry-pick lockfile to TARGET. Replaces /elevate-skill.
Generates high-quality Gherkin (BDD) scenarios from functional requirements using a two-agent iterative cycle: a generator agent that creates/modifies the Gherkin and a reviewer agent that validates it and proposes improvements. The cycle repeats automatically until the Gherkin passes review. Use this skill whenever the user mentions: "generate Gherkin", "BDD scenarios", "Gherkin test cases", "Feature/Scenario/Given/When/Then", "requirements to Gherkin", "BDD specifications", or asks to transform functional requirements into behaviour tests. Also applies when the user brings a requirements document and wants test cases, acceptance criteria, or user stories with executable examples.
Resume work from a previous session, restoring context after a break, continuing work after /clear, or picking up where you left off. Triggers include "resume work", "continue work", "pick up where I left off", "restore context", and "resume session".
Issue quality primitives: lint, enrich, decompose. `/issue lint [#N|--all]` — Score issues against org-standards. `/issue enrich [#N]` — Fill gaps with sub-agent research. `/issue decompose [#N]` — Split oversized issues into atomic sub-issues.
This skill should be used when the user asks to refactor specific files or directories, simplify recently changed code, clean up dead code in a limited scope, or invokes `/refactor` with paths or semantic queries.
Transform messy work updates into clean, standardized end-of-day Slack sync summaries. Use when asked to "format my updates", "create a sync", "write a standup", or "summarize my work" for Slack.
Migration workflow - research → analyze → plan → implement → review
Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. Supports optional loop count via Claude Code's /loop command.
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local web viewer. Use when (1) scaffolding a new knowledge base for any research topic, (2) ingesting articles/papers/PDFs/web pages into raw/, (3) compiling or restructuring wiki articles from existing raw material, (4) answering questions against the wiki and filing durable answers back, (5) running lint passes for dead links / orphan pages / coverage gaps / audit shape, (6) processing human feedback from the audit/ directory and applying corrections. Not for general note-taking, daily journals, or non-wiki Obsidian use.
Post content to Binance Square through Shift's Skill Router. Auto-run on messages like "post to square", "send this to Binance Square", or "发到币安广场".
Run a task in a loop until an exit condition is met. Use when the user says "loop", "loop this", "keep trying until", "babysit", "poll", or wants iterative autonomous execution.
Dry-run Stacks contract calls against mainnet state before broadcasting — catches errors, prevents wasted gas