systemsmith

Translate natural-language requests about AI-agent behavior, skills, MCP tools/servers, prompts, routing, context loading, memory, hooks, plugins, permissions, delegation, portability, or other agentic-system behavior into the concrete runtime mechanism and change surface. Use when a request is phrased as what the AI should understand/do rather than how the target harness actually observes, triggers, routes, persists, or enforces that behavior.

Generate or rewrite Markdown from unstructured notes, transcripts, scratch text, or rough drafts while preserving meaning and producing valid Markdown syntax. Use when the requested output is specifically a Markdown artifact.

Choose or review the representation form for information that will already be shown: table, list, hierarchy, prose, diagram, code abstraction, chart, or another structure. Use when the same content could be organized in multiple ways and readability, comparison, scanning, or structural clarity depends on the representation.

Apply when producing any markdown artifact for someone else (or future-you) to read — READMEs, analysis documents, Confluence pages, status reports, troubleshooting write-ups, skill content, conversation summaries, ticket descriptions, post-mortems, snapshots of system state, or any document that contains concrete current-state values. Defines the "snapshot + reproducer" rule (every static value must be paired with the command/query/script that regenerates it), the single-source-of-truth rule (reference canonical homes instead of duplicating values), and fact-vs-assumption marking. Trigger keywords include writing or producing or creating or drafting a README, analysis, Confluence page, status update, summary, snapshot, current state, documenting data, posting findings, file tree, port number, version number, table count, or any concrete value that may drift over time.

Core principles for technical communication such as commits, PR descriptions, branch names, and technical documentation. Use when writing or refining engineering-facing messaging and when other skills need a shared communication baseline.

Design or review any human- or agent-facing information surface so the consumer sees the minimum sufficient information at the right abstraction level for the current task, with clear routes to deeper detail only when relevant. Use for chat, docs, code, APIs, dashboards, charts, websites, profiles, messages, UIs, agent instructions, or other information-bearing interfaces.

Mandatory credential protection skill for all agents. Prevents reading, exposing, or leaking credentials, secrets, API keys, tokens, passwords, and auth-capable config files.

Analyze the current conversation or mine historical chat sessions for correction patterns, wrong conclusions, or unnecessary user intervention. Use when the user wants to improve prompts, skills, workflows, or guardrails based on repeated mistakes.

Guide for working through a Jira story efficiently by separating context gathering, immutable evidence collection, codebase exploration, human-in-the-loop specification refinement, execution planning, and implementation. Use when turning a ticket into a reliable engineering workflow instead of jumping straight to code.

Transform a user's raw thoughts, dictation, transcript, notes, brainstorm, or conversational explanation into a structured communication artifact while preserving meaning, examples, nuance, and recoverable detail. Use for articles, documentation, skills, READMEs, messages, briefs, posts, or similar outputs when the source structure is incidental and the output should organize ideas by meaning rather than original speaking order.