Agent Workflows · By mohitagw15856

Compress tool outputs, logs, and JSON before they enter the context window — structural compression via a deterministic stdlib script (schema + samples + stats instead of 300 raw rows), no API, no…

mohitagw15856/pm-claude-skills

A skill your agent uses when asked to expose a folder of notes or docs to Claude or another AI client, build an MCP server over Markdown or JSON files, let an agent read my knowledge base safely, or…

mohitagw15856/pm-claude-skills

Author a high-quality Agent Skill (SKILL.md) that an AI reliably triggers and executes well — strong frontmatter, a sharp description with trigger phrases, a clear output contract, quality checks…

mohitagw15856/pm-claude-skills

Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real.

mohitagw15856/pm-claude-skills

Run a real brainstorm — divergent generation without judgment, then convergent selection with explicit criteria — instead of listing ten obvious ideas and calling it creativity.

mohitagw15856/pm-claude-skills

Set up a repo or project so an AI coding agent works well in it — the CLAUDE.md, the context, the guardrails, and the conventions the agent needs to be useful instead of lost.

mohitagw15856/pm-claude-skills

A skill your agent uses when asked 帮爸妈办医保, 帮父母办养老金认证, 爸妈异地就医备案, 帮老人办银行业务, 父母被诈骗了怎么办, 教爸妈用手机办事, 代办委托书, or help an adult child handle 医保, 社保, 养老金, banking or scam protection for ageing parents in…

mohitagw15856/pm-claude-skills

Plan a session's context window like the budget it is — what loads up front, what gets linked instead, what stays fetch-on-demand, and how to keep the stable prefix cache-friendly so repeated turns…

mohitagw15856/pm-claude-skills

Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.

mohitagw15856/pm-claude-skills

Delegate so the work comes back right the first time — the brief that transfers outcome, context, and constraints (not just the task), the autonomy level stated explicitly, and the check-in design…

mohitagw15856/pm-claude-skills

Convert an email (or a whole thread) into real tasks — the actual asks extracted from the prose, each with owner, deadline, and the done-test, so nothing lives in the inbox as its own reminder.

mohitagw15856/pm-claude-skills

Execute a written plan with discipline — verify each step before advancing, surface deviations instead of improvising around them, and keep a visible execution log.

mohitagw15856/pm-claude-skills

Separate raw idea-generation from judgment so creativity isn't strangled by your inner critic — diverge with zero evaluation, then switch to hard critique.

mohitagw15856/pm-claude-skills

Get through the brutal logistics after a death — who to notify, what accounts and services to close, in what order, and what genuinely can't wait vs what can wait months — with explicit permission…

mohitagw15856/pm-claude-skills

Build a seasonal home-maintenance calendar so the small upkeep gets done before it becomes an expensive repair.

mohitagw15856/pm-claude-skills

Design the human approval surface for an agent system — which actions gate, how approvals batch without becoming rubber stamps, and what the audit trail must hold.

mohitagw15856/pm-claude-skills

Generate a big, wide spread of ideas for anything by running the prompt through many different lenses at once, then clustering and picking.

mohitagw15856/pm-claude-skills

Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end.

mohitagw15856/pm-claude-skills

Elicit the real requirements by interviewing the requester BEFORE building or writing anything — one question at a time, until the brief is buildable.

mohitagw15856/pm-claude-skills

Turn your notice period into a handoff that makes you missed for the right reasons — the transition doc nobody has to call you about, the knowledge-transfer sessions, and the graceful goodbye…

mohitagw15856/pm-claude-skills

Design an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI agents.

mohitagw15856/pm-claude-skills

Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting you right.

mohitagw15856/pm-claude-skills

Turn a topic, brainstorm, or document into a structured mind map.

mohitagw15856/pm-claude-skills

Generate and evaluate names for a product, feature, or release.

mohitagw15856/pm-claude-skills

Write an engineering RFC (Request for Comments) for a technical decision, architectural change, or significant implementation approach.

mohitagw15856/pm-claude-skills

Design a small team of AI agents to tackle a complex task in parallel — who does what, how they hand off, and how to keep them coordinated — instead of one overloaded agent doing everything serially.

mohitagw15856/pm-claude-skills

Write a performance self-review that's specific, evidenced, and balanced.

mohitagw15856/pm-claude-skills

Write a handoff summary so another agent or person (or a fresh session) can pick up the work with full context.

mohitagw15856/pm-claude-skills

Decompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result integration that catches contradictions.

mohitagw15856/pm-claude-skills

Triage an overwhelming task list into what actually gets done — the urgent/important sort applied honestly (with the two corrections the classic matrix needs), the do/schedule/delegate/drop verbs…

mohitagw15856/pm-claude-skills

Run any draft through the editor who owes you nothing — the buried lede surfaced, the throat-clearing cut, the hedges un-stacked, every paragraph made to answer so what — with a target of 30%…

mohitagw15856/pm-claude-skills

Review what an agent is actually allowed to do before you turn it loose — the tool-by-tool audit (each capability's blast radius), the least-privilege pass that removes what the task doesn't need…

mohitagw15856/pm-claude-skills

A short weekly ritual that clears the mental backlog, picks the one thing that matters, and keeps you honest about your dependence on autopilot.

mohitagw15856/pm-claude-skills

Write an executable work plan BEFORE starting a complex task — decomposed steps with verification points, risks pre-named, and explicit stop conditions — so execution becomes checking boxes instead…

mohitagw15856/pm-claude-skills