Close out a finished work cycle by distilling what was learned into a durable, per-module knowledge base — a file-based memory indexed by source file — so future PRDs, tasks, and agents reuse recorded decisions, gotchas, patterns, and contracts instead of re-deriving them. Use this skill at the END of a cycle, after implement-task and/or review, when the user says "close the cycle", "capture what we learned", "update the knowledge base", "record the learnings", "remember this for next time", or "post-mortem this feature". This is different from for-research (upfront, per-big-task, disposable): close-cycle writes permanent memory keyed to code units and grows across cycles.
EnglishResearch a BIG task upfront and cache the findings as a structured Markdown knowledge base (a file-based RAG) so that any later prompt, agent, or workflow step can retrieve exactly the context it needs in one shot — without re-exploring the codebase or overflowing the context window. Use this skill whenever a task is too big to hold in one prompt, whenever the user says "research this first", "cache the context", "build a knowledge base", "prepare context for the agents", or before starting a large feature, migration, or refactor. Also use it when repeated conversations keep re-discovering the same codebase facts.
EnglishBreak a PRD (Product Requirements Document) down into small, self-contained tasks organized as a file-based kanban board, designed so multiple AI agents can execute tasks in parallel. Each task is its own Markdown file. Use this skill whenever the user asks to turn a PRD, spec, or requirements document into tasks, tickets, a backlog, a kanban board, or a parallelizable work breakdown — even if they don't say "kanban". Also use it right after generating a PRD when the user asks "now split this into tasks" or "plan the implementation".
EnglishFast path for a small, self-contained change that doesn't justify the full PRD → kanban → implement pipeline — a cosmetic tweak, a copy/text change, a tiny localized bugfix, moving or restyling one element. Use this skill when the user asks for a single obvious change that touches one or two files with no design decision, no new module/API/schema, and no need for parallel agents — e.g. "move this button", "change the header color", "fix this label's text", "bump the timeout", "tweak the spacing". Escalate to write-prd / prd-to-kanban the moment it turns out bigger than that.
EnglishIncludes Close Cycle, For Research, Prd to Kanban, and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Close Cycle
Close out a finished work cycle by distilling what was learned into a durable, per-module knowledge base — a file-based memory indexed by source file — so future PRDs, tasks, and agents reuse recorded decisions, gotchas, patterns, and contracts instead of re-deriving them. Use this skill at the END of a cycle, after implement-task and/or review, when the user says "close the cycle", "capture what we learned", "update the knowledge base", "record the learnings", "remember this for next time", or "post-mortem this feature". This is different from for-research (upfront, per-big-task, disposable): close-cycle writes permanent memory keyed to code units and grows across cycles.
For Research
Research a BIG task upfront and cache the findings as a structured Markdown knowledge base (a file-based RAG) so that any later prompt, agent, or workflow step can retrieve exactly the context it needs in one shot — without re-exploring the codebase or overflowing the context window. Use this skill whenever a task is too big to hold in one prompt, whenever the user says "research this first", "cache the context", "build a knowledge base", "prepare context for the agents", or before starting a large feature, migration, or refactor. Also use it when repeated conversations keep re-discovering the same codebase facts.
Prd to Kanban
Break a PRD (Product Requirements Document) down into small, self-contained tasks organized as a file-based kanban board, designed so multiple AI agents can execute tasks in parallel. Each task is its own Markdown file. Use this skill whenever the user asks to turn a PRD, spec, or requirements document into tasks, tickets, a backlog, a kanban board, or a parallelizable work breakdown — even if they don't say "kanban". Also use it right after generating a PRD when the user asks "now split this into tasks" or "plan the implementation".
Quick Task
Fast path for a small, self-contained change that doesn't justify the full PRD → kanban → implement pipeline — a cosmetic tweak, a copy/text change, a tiny localized bugfix, moving or restyling one element. Use this skill when the user asks for a single obvious change that touches one or two files with no design decision, no new module/API/schema, and no need for parallel agents — e.g. "move this button", "change the header color", "fix this label's text", "bump the timeout", "tweak the spacing". Escalate to write-prd / prd-to-kanban the moment it turns out bigger than that.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Close Cycle skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.