agent_sync

Create or edit AgentSync configuration — AGENTS.md, rules, skills, commands, subagents, settings, MCP servers, hooks, or per-tool configs. Use this skill when adding a rule, creating or scaffolding a skill, writing a slash command, defining a subagent persona, editing permissions, configuring an MCP server, setting up the `.ai/src/` directory, or running `agentsync sync` / `add` / `customize` / `resolve` / `simplify` / `profile` — even when the user does not name "AgentSync" explicitly but is editing files in `.ai/src/`, `.claude/`, `.cursor/`, or another tool-config directory.

Create or edit AgentSync configuration — AGENTS.md, rules, skills, commands, subagents, settings, MCP servers, hooks, or per-tool configs. Use this skill when adding a rule, creating or scaffolding a skill, writing a slash command, defining a subagent persona, editing permissions, configuring an MCP server, setting up the `.ai/src/` directory, or running `agentsync sync` / `add` / `customize` / `resolve` / `simplify` / `profile` — even when the user does not name "AgentSync" explicitly but is editing files in `.ai/src/`, `.claude/`, `.cursor/`, or another tool-config directory.

Bump the AgentSync version, write a CHANGELOG entry summarising changes since the last tag, and prepare a clean release commit. Use this skill when the user asks to release, ship, cut a version, bump major/minor/patch, tag, or prepare a new version — including phrasings like "let's ship 0.12", "поднять версию", "сделай релиз", or when asked to update CHANGELOG.md after a stretch of work.

One imperative sentence on what this skill does + concrete trigger conditions. Be pushy — list contexts including ones where the user doesn't name the domain ("even when phrased as 'X' or 'Y'"). Pack relevant keywords. Stay under 1024 characters.

Create a well-structured git commit for staged or unstaged changes — analyze the diff, match the project's existing commit style, write a clear message, and create the commit. Use this skill when the user asks to commit, save changes, check in code, write a commit message, prepare changes for push, or wrap up a piece of work — even when they don't say "commit" explicitly (e.g. "let's save this", "ship it", "сохрани изменения").

Design, debug, and refine prompts for LLM-based coding tools, agents, and pipelines. Use this skill when writing or rewriting a system prompt, agent persona, slash-command body, rule, or skill description; tuning a prompt that produces vague, incomplete, off-format, hallucinated, or over-/under-triggering output; choosing among techniques like XML tags, few-shot examples, role-setting, reasoning steps, or recap; debugging a model that ignores instructions, leaks information, or over-engineers solutions; or designing the persona, autonomy posture, or tool-use rules of an autonomous agent — even when the user does not explicitly mention "prompt engineering" or "system prompt". Not for AgentSync file structure, frontmatter, or scaffolding new rule/skill/command files — use the `agentsync` skill for that.

Design, debug, and refine prompts for LLM-based coding tools, agents, and pipelines. Use this skill when writing or rewriting a system prompt, agent persona, slash-command body, rule, or skill description; tuning a prompt that produces vague, incomplete, off-format, hallucinated, or over-/under-triggering output; choosing among techniques like XML tags, few-shot examples, role-setting, reasoning steps, or recap; debugging a model that ignores instructions, leaks information, or over-engineers solutions; or designing the persona, autonomy posture, or tool-use rules of an autonomous agent — even when the user does not explicitly mention "prompt engineering" or "system prompt". Not for AgentSync file structure, frontmatter, or scaffolding new rule/skill/command files — use the `agentsync` skill for that.

Investigate and fix a GitHub issue in this repo — pull the issue with `gh`, trace it to the root cause across `lib/` and `bin/`, fix portably, and cover it with a bats regression test. Use this skill when the user asks to fix, resolve, or tackle a GitHub issue (by number or URL), debug a reported bug from the tracker, or work through an issue end-to-end — including phrasings like "fix #42", "tackle issue 17", "resolve this GH issue", "почини issue #N", or "разберись с багом из тикета".

Rewrite text so it reads like a real human wrote it, or generate long-form prose (blog posts, essays, articles, newsletters, social posts, op-eds, short stories) in that same plain, grounded voice. Strips common AI tells, including em dashes, semicolons, framing colons, inflated vocabulary (utilize, leverage, delve, tapestry, robust), contrastive negation, significance inflation, forced triads, sycophantic openers, and chatbot closers. Trigger whenever the user asks to humanize, de-AI, or de-slop text, even with casual phrasing like "make this less AI-sounding," "fix the AI vibe," or equivalent phrasing in any language. Also trigger when the user asks Claude to write a prose deliverable they will publish or share, like an article, blog post, essay, newsletter, or short story. Do not use for code, casual chat replies, or technical documentation.

Add support for a new AI coding tool to AgentSync's sync engine — create the tool YAML, configure targets and converters, add base templates, and write tests. Use this skill when integrating a new AI assistant, IDE, or editor into AgentSync, when a user asks "can AgentSync sync to X", or when extending the sync surface to a new agent — even if the user names the tool by brand without saying "tool" or "integration".

Create or edit AgentSync configuration — AGENTS.md, rules, skills, commands, subagents, settings, MCP servers, hooks, or per-tool configs. Use this skill when adding a rule, creating or scaffolding a skill, writing a slash command, defining a subagent persona, editing permissions, configuring an MCP server, setting up the `.ai/src/` directory, or running `agentsync sync` / `add` / `customize` / `resolve` / `simplify` — even when the user does not name "AgentSync" explicitly but is editing files in `.ai/src/`, `.claude/`, `.cursor/`, or another tool-config directory.

Create a well-structured git commit for staged or unstaged changes — analyze the diff, match the project's existing commit style, write a clear message, and create the commit. Use this skill when the user asks to commit, save changes, check in code, write a commit message, prepare changes for push, or wrap up a piece of work — even when they don't say "commit" explicitly (e.g. "let's save this", "ship it", "сохрани изменения").

Investigate and fix bugs, errors, or unexpected behavior systematically — reproduce, locate, understand the root cause, fix it, and add a regression test. Use this skill when the user reports a failure (test, runtime, build, CI), shares a stack trace or error message, says something doesn't work, asks why something is broken, or asks for a fix that requires diagnosis — even when the word "debug" is not used (e.g. "this is broken", "почему падает", "не работает X").

Restructure existing code without changing its behavior — reduce duplication, improve naming, simplify complex logic, extract helpers, split overgrown functions, untangle dependencies. Use this skill when the user asks to refactor, clean up, simplify, DRY out, rename, extract a helper, split a file, or make code "nicer" — including when they describe code-quality concerns without using the word "refactor" (e.g. "this is messy", "приведи в порядок", "это можно сделать чище").

Perform a structured code review on a diff, PR, or staged changes — surface correctness, security, error-handling, architecture, testing, and clarity issues with file/line references and severity. Use this skill when the user asks to review code, audit a diff or PR, find bugs in changes before merging, sanity-check work before pushing, or look over an implementation — including when phrased softly ("look over this", "check if this is OK", "глянь, всё ли нормально", "посмотри на это").