yelmuratoff

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 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").

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.

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".

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.

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.

Regenerate everything from schemas — templates, docs, Studio types. Run after changing any schema file. Trigger on "/generate-all".

Review JSON schemas in schema/ for correctness, consistency, completeness. Check that schemas match Dart models, parsers, and Studio. Trigger on "/review-schema".

Verify Studio site is fully in sync with schemas. Build, test, check for hardcoded values. Trigger on "/sync-studio".

Add a new config option end-to-end — schema, config model, parser, pipeline integration, templates. Studio picks it up automatically. Trigger on "/add-config-option <section.field_name>" (e.g. "targets.openapi", "rules.require_descriptions").

Add a new field to analytics events end-to-end — schema, model, parser, renderer, tests, templates. Trigger on "/add-event-field <field_name>" or when user asks to add a field to events.

Full project review — schemas, Dart code, Studio, templates, docs. Checks everything is in sync. Trigger on "/review-all".

Review Dart library code for quality, architecture, SOLID, test coverage, and consistency with schemas. Trigger on "/review-code" or "/review-code <path>".

Run full validation — dart analyze, dart test, studio build, schema consistency checks. Trigger on "/validate".

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").

Use this skill when modifying ISpect network, WebSocket, database, BLoC, or trace logging behavior, including requests like "add capture", "fix redaction", "interceptor logs wrong data", "DB trace broken", "request IDs missing", or "payload should not leak". It preserves correlation IDs, redaction defaults, and package boundaries.

Scaffold a new database or storage interceptor in `packages/ispectify_db/example` using the shared ISpect DB tracing API. Use when adding support for a new backend such as Hive, SharedPreferences, Drift, Isar, Realm, Sembast, ObjectBox, Firestore, secure storage, or another storage driver.

Use this skill when asked to test, verify, validate, run checks, fix analyzer failures, or confirm CI readiness for an ISpect package, including vague requests like "check this package", "проверь тесты", "why CI fails", or "make it green". It chooses the correct Dart vs Flutter commands and adds README/version checks only when relevant.

Use this skill when asked to update versions, prepare a release, sync changelogs, rebuild README files, fix README drift, validate package dependencies, or handle prerelease bumps in ISpect, including "release prep", "bump dev version", "sync docs", "README check failed", or "version mismatch".

Write or update CHANGELOG.md entries following the project's established style. Use when adding features, fixing bugs, or making any changes that need changelog documentation. Trigger on "/changelog" or when the user asks to update the changelog.

Scaffold a new network interceptor package (e.g. Chopper, Retrofit) using the shared ispectify base. Trigger on "/new-network-package" or when the user asks to add support for a new HTTP client.

Scaffold a new video downloader implementation following the Downloader Protocol.

Scaffold a new video platform module (like kinescope/) for downloading from a different service.

Verify the project compiles, imports resolve, and CLI help works.