slidemind 0.4.1 → 0.4.2

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "slidemind",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Connect Claude Code to the slidemind PowerPoint add-in — build and edit native, on-brand PowerPoint decks against the active corporate design, from the terminal.",
   "author": {
     "name": "statworx",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "slidemind",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Connect Codex to the slidemind PowerPoint add-in — build and edit native, on-brand PowerPoint decks against the active corporate design. Requires the slidemind CLI (npm install -g slidemind); the skills explain the install when it is missing.",
   "author": {
     "name": "statworx",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "slidemind",
-  "version": "0.4.1",
+  "version": "0.4.2",
   "description": "Connect Claude Code, Codex & opencode to the slidemind PowerPoint add-in — let your coding agent build and edit native, on-brand PowerPoint decks against your active corporate design, from the terminal.",
   "type": "module",
   "bin": {

package/skills/search/SKILL.md

@@ -115,12 +115,16 @@ Follow `workflow/search.md` for the discipline; this is the CLI shape of its loo
    return nothing right now; pick another target.
 2. **Choose the target + intent.** Slide engines (`subtype slide`), content collections and scopes
    support two intents: **content** (the slide's text is the signal — title, body, tables, notes)
-   and **visual** (the slide image is the signal). Image/icon engines (`subtype image`) are
-   **visual-only**, and so are **template collections** (`subtype template`): their text is
+   and **visual** (the slide image is the signal). Image/icon engines (`subtype image`) search
+   **visually** by default, and so do **template collections** (`subtype template`): their text is
    placeholder, so query the structure the content needs ("loop diagram with 5 steps",
    "three-column comparison"), never the topic. Match the intent to the ask: "a slide that says X" /
    "covers topic Y" → `--intent content`; "a slide that looks like X" / brand imagery →
-   `--intent visual`. `--intent auto` lets the engine decide.
+   `--intent visual`. `--intent auto` lets the engine decide. An image engine also takes
+   **`--intent keyword`**: a lexical match on the asset's FILE NAME, no embedding at all — the
+   one way to find a NAMED asset, such as a colleague's photo (`JaneDoe_business.png`), which a
+   visual search for "Jane Doe" ranks no better than any other face. Every query word must occur
+   in the file name; type names without accents (`Andre`, not `André`).
 3. **Search — no window to choose.** `slidemind search "<query>" --engine <id> --intent
    <auto|content|visual> [--top N]` (leave `--to` off). A **scope** target additionally needs
    `--result-type slide|image` (it has no subtype of its own; the CLI defaults it to `slide`). Omit
@@ -271,7 +275,7 @@ insert live, fold into a deck, engine fetch). You are the local harness — this
 | Verb (`workflow/search.md`) | Your equivalent (local harness) |
 |---|---|
 | **discover engines** ("list what you can reach") | `slidemind ls engines [--type collection\|search\|scope] [--subtype …]` — returns the engine catalog **plus the search scopes** (pick an `id`; never guess one). The catalog is per-user; `--to` is accepted but never needed. No window needed where the add-in serves the pane-free routes. |
-| **engine search** (with `intent`) | `slidemind search "<query>" --engine <id> --intent <auto\|content\|visual> [--top N] [--deck <deck>]` — leave `--to` off → a `searchId` + numbered results, plus the exact follow-up commands for the path it took; each result may carry a `source:` link — **always cite it back** |
+| **engine search** (with `intent`) | `slidemind search "<query>" --engine <id> --intent <auto\|content\|visual\|keyword> [--top N] [--deck <deck>]` — leave `--to` off → a `searchId` + numbered results, plus the exact follow-up commands for the path it took; each result may carry a `source:` link — **always cite it back** |
 | **search a scope** (unfiltered corpus, no engine) | `slidemind search "<query>" --engine <scope:all\|scope:sharepoint> --result-type <slide\|image> [--intent …]` — `--result-type` is required for a scope (defaults to `slide`). Results reuse identically to engine results. |
 | **pull an on-demand thumbnail** for a stored result | `slidemind view-slide --search <searchId> --pick <n>` — SLIDE-library results only; image/icon results have no preview ("no image returned") — download and Read the file instead (add `--to <searchWindow>` only on the relayed path) · or `slidemind search … --json` for the structured payload. |
 | **read a result's SOURCE deck** (the presentation it came from) | `slidemind read-source --search <searchId> --pick <n> [--from-slide N] [--to-slide N] [--out <file.md>]` — Markdown of the whole source presentation, one section per slide (add `--to <searchWindow>` only on the relayed path). Indexed text, not the live file. Slide results only. |

package/src/cli/help.mjs

@@ -143,7 +143,8 @@ export function printHelp(cmd = null) {
       `                                     --engine <id>   engine, or scope:all | scope:sharepoint to search unfiltered\n` +
       `                                                     (default: first image engine; scope:all for slide intents)\n` +
       `                                     --result-type <t>  slide | image — required for a scope:* target\n` +
-      `                                     --intent <i>    auto | content | visual (slide engines)\n` +
+      `                                     --intent <i>    auto | content | visual (slide engines) | keyword\n` +
+      `                                                     (image engines: match the FILE NAME, e.g. a person's photo)\n` +
       `                                     --top <N>       max results\n` +
       `                                     --deck <deck>   use this deck's bound design\n` +
       `                                     --to <presId>   pin a window on the relayed path (ignored pane-free)\n` +

package/src/cli/search.mjs

@@ -53,9 +53,9 @@ export async function cmdSearch(rest) {
       }
     } else if (a === "--intent") {
       intent = rest[++i];
-      if (!intent) fail("--intent expects auto|content|visual");
-      if (!["auto", "content", "visual"].includes(intent)) {
-        fail(`--intent expects auto|content|visual, got '${intent}'`);
+      if (!intent) fail("--intent expects auto|content|visual|keyword");
+      if (!["auto", "content", "visual", "keyword"].includes(intent)) {
+        fail(`--intent expects auto|content|visual|keyword, got '${intent}'`);
       }
     } else if (a === "--top") {
       const next = rest[++i];
@@ -73,7 +73,7 @@ export async function cmdSearch(rest) {
   const query = queryParts.join(" ").trim();
   if (!query) {
     fail(
-      `usage: slidemind search "<query>" [--engine <id|scope:all|scope:sharepoint>] [--result-type slide|image] [--intent auto|content|visual] [--top <N>] [--deck <deck>] [--to <presId>] [--json]`,
+      `usage: slidemind search "<query>" [--engine <id|scope:all|scope:sharepoint>] [--result-type slide|image] [--intent auto|content|visual|keyword] [--top <N>] [--deck <deck>] [--to <presId>] [--json]`,
     );
   }
 
@@ -118,7 +118,13 @@ export async function cmdSearch(rest) {
   // as slide results (the footer then taught add-slide instead of
   // download-result). Omitted subtype → the backend derives it from what the
   // results actually are.
-  let subtype = intent === "content" ? "slide" : null;
+  //
+  // `--intent keyword` is the opposite case: a lexical FILE-NAME match that the
+  // add-in runs over the image index only (it coerces keyword to content on
+  // any other index), so it asserts "image" the way content asserts "slide".
+  // It is what finds a named asset — a colleague's photo `JaneDoe_business.png`
+  // — which no embedding of the query "Jane Doe" ranks reliably.
+  let subtype = intent === "content" ? "slide" : intent === "keyword" ? "image" : null;
   // `--engine Icons` — a display name straight off `ls engines` — would reach
   // the backend verbatim and 404 as "Engine not found". Humans type names,
   // agents paste ids; when the value cannot be an id (spaces, non-hex), look it