Sprint Retrospective
Run a sprint retrospective — gather data, analyze incidents, propose action items. Any agent can facilitate.
Claude assistants and Claude Code workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.
Run a sprint retrospective — gather data, analyze incidents, propose action items. Any agent can facilitate.
End-of-sprint checklist — finalize results, clean up worktrees, update docs, prepare for retro. Any agent can run this.
How to write integration tests for error processors in packages/core/src/processors/.
Set up Telegram and read or send messages in the owner's personal account through tg. Use when asked to install or connect Telegram, find a chat or person, read a conversation, or send a message.
pi-rukas's bundled vipune memory doctrine — full reference for using the vipune CLI as a project-scoped semantic memory store. Encodes the 5-type memory taxonomy (fact, preference, procedure, guard, observation), the active/candidate status split as the long-term/short-term mechanism, freshness verification before acting on recalled memories, conflict handling via --supersedes, periodic consolidation reflexes, the hard prohibition on storing secrets, and pi-rukas-specific framing (multi-agent shared DB, session autosave). Use this skill whenever starting a project task; before delegating work; before making architectural decisions; after task completion; when the user mentions "remember"/"recall"/"vipune"; when surprised by codebase reality vs recalled memory; or when encountering a known-feeling pitfall. Project-scoped, semantic-search-driven; designed to make every session smarter than the last without context bloat or memory rot.
Use when repository work is implemented and must be verified, committed, pushed, and submitted as a pull request.
Prevent AI style drift on legacy projects by scanning the codebase for implicit conventions, resolving conflicts with the operator one at a time, and writing an enforceable .ai-style-rules.md (Golden Files, naming rules, DONTs) plus an optional CLAUDE.md hook. Use when onboarding an AI agent onto a hand-written legacy codebase or extracting a project's unwritten coding rules.
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
Pre-implementation checks to run before writing any new code — prevents pattern reuse failures, API misuse, and spec drift
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.
Analyze PowerPoint slides qualitatively using vision AI. Arguments: <deckpath> [--render] [--slides 1,5,10]
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
How to run the adversarial code-review evaluator once local tests pass, before the PR opens
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Automate SEO research with Ahrefs -- analyze backlink profiles, research keywords, track domain metrics history, audit organic rankings, and perform batch URL analysis through the Composio Ahrefs integration.
Automate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.
Automate Apollo.io lead generation -- search organizations, discover contacts, enrich prospect data, manage contact stages, and build targeted outreach lists -- using natural language through the Composio MCP integration.
Automate Capsule CRM operations -- manage contacts (parties), run structured filter queries, track tasks and projects, log entries, and handle organizations -- using natural language through the Composio MCP integration.
Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.
Automate headless CMS operations in Contentful -- list spaces, retrieve space metadata, and update space configurations through the Composio Contentful integration.
Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.
Automate web crawling and data extraction with Firecrawl -- scrape pages, crawl sites, extract structured data, batch scrape URLs, and map website structures through the Composio Firecrawl integration.
Automate Gong conversation intelligence -- retrieve call recordings, transcripts, detailed analytics, speaker stats, and workspace data -- using natural language through the Composio MCP integration.
Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.