# Prompt Recipes



<a id="section-goal"></a>

You drive Context by talking to your Agent. These are phrasings that work for common requests; replace the placeholders in angle brackets. Each one is a starting point — the Agent researches, asks back where needed, and stops at the decisions that are yours.


<a id="section-produce"></a>

## Producing and revising

| You want to | Say | What happens |
| --- | --- | --- |
| Start | "Initialize a Context knowledge workspace in `<directory>` and build knowledge for `<repository or module>` and `<document link>`. Research first, then give me the work-start report." | Workspace setup, source research, then a work-start report for you to confirm |
| Add material | "Add `<new material>` as a source, re-plan the affected parts and give me a new work-start report." | Source registration and a revised plan |
| Revise | "Revise `<article>`: `<problem>`. Keep the source references." | A revision task and a review report for the changed page |
| Reorganize | "Research the approved knowledge again and propose a more intuitive directory and title structure. Revise after I confirm." | A structure proposal, then revisions |
| Plan a large project | "Plan a knowledge project for `<repositories and documents>`." | The `context-plan` Skill researches and writes a `PLAN-*.md` for review |


<a id="section-maintain"></a>

## Updating, evaluating and migrating

| You want to | Say | What happens |
| --- | --- | --- |
| Update | "The sources have moved to `<version>`. Find the affected knowledge and review the updates." | Impact assessment, targeted revisions, a review report |
| Evaluate | "Evaluate the current knowledge base with `<question set>`, grade each answer on the four-level criteria and give me P50/P90." | An evaluation run with grades and timings |
| Migrate | "Research what Context can do, then migrate the current knowledge base …" | See [Migrating an Existing Knowledge Base](</context/llms/pages/317bd2af0c9c24b663877af1911573d8.txt>) for the full prompt |


<a id="section-deliver"></a>

## Building and asking

| You want to | Say | What happens |
| --- | --- | --- |
| Build and preview | "Build the knowledge package and documentation site, and give me a local preview." | `context build`, then a local HTTP preview whose URL is checked before it is shared; publishing to hosting needs your separate authorization |
| Ask a question | "Using the `<package>` knowledge, how does `<feature>` work?" | `context-inspect-search` answers from the knowledge with sources and reports gaps |

The commands and Skills behind these requests are listed in [Commands and Skills](</context/llms/pages/2e3119bc24e49da0e10fbf2c002d5472.txt>).

---

## Sources

- note:20261012/usage-practices.md · usage-practices.md L5–L7
- note:20261012/usage-practices.md · usage-practices.md L62–L70
- [context/plugins/context/README.md L33–L40 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/README.md#L33-L40>)
- note:20261012/usage-practices.md · usage-practices.md L62–L72
- note:20261012/usage-practices.md · usage-practices.md L47–L60
- [context/packages/context/docs/guides/package-outputs.md L417–L421 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/packages/context/docs/guides/package-outputs.md#L417-L421>)
- [context/plugins/context/skills/context-inspect-search/SKILL.md L1–L30 · 3b0ce0a](<https://github.com/context4ai/context/blob/3b0ce0a0a1761f5fceb3bb48fb9dc29b54c0786b/plugins/context/skills/context-inspect-search/SKILL.md#L1-L30>)