@minhpnq1807/contextos 0.5.45 → 0.5.46

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.5.46
+
+- **Configurable prompt suggestion limits:** `ctx --config` and interactive `ctx setup` now let users choose how many suggested files, skills, and workflows appear in prompt context. Defaults are five each, with caps of 20 files, 10 skills, and 5 workflows.
+- **Limit-aware prompt hooks and debug:** `UserPromptSubmit` hooks, direct fallback scoring, the private `ctx-mcp` bridge request, and `ctx debug` now all honor the saved suggestion limits instead of using hard-coded counts.
+- **Document authoring skill intent:** Prompts that create, edit, update, or maintain documents, workspace docs, README files, wiki pages, manuals, guides, specs, or ADRs now prioritize documentation skills such as `doc-coauthoring`, `documentation`, `docs-architect`, `readme`, and `wiki-page-writer`.
+- **Safer document skill gating:** Document-processing and workspace-automation skills such as Azure Document Intelligence, DocuSign, Asana, Slack, Google Docs, and Notion no longer win generic document-writing prompts unless the provider or processing task is explicitly named.
+- **Setup summary clarity:** The setup wizard summary now reports the saved prompt suggestion limits alongside the enabled prompt sections so users can review output volume immediately.
+
 ## 0.5.45
 
 - **Project-aware MCP skill suggestions:** Skill ranking now reads `package.json` keywords and dependencies such as `@modelcontextprotocol/sdk`. MCP projects can recommend `mcp-builder`, `mcp-management`, `mcp-tool-developer`, and `agent-memory-mcp` for context retrieval, scorer, hook, and prompt-injection debugging tasks even when the prompt does not explicitly say `mcp`.

package/README.md

@@ -444,7 +444,7 @@ This warning comes from a transitive dependency in the local embedding/WASM stac
 | `ctx sync --workflows --dry-run` | Previews workflow sync without writing files. | You want to inspect source workflows and target roots first. | Prints planned sync/index output and skips copying target files. |
 | `ctx skills` | Installs community skill libraries. | You want curated skills without running the full setup wizard. | Opens the community installer, uses a portable shell on Windows/Linux/macOS, repairs unsafe skill symlinks, and syncs installed skills to selected agents. |
 | `ctx embeddings warm -- "task"` | Prepares local semantic embedding caches. | First install, CI smoke checks, or after changing AGENTS.md/project files/skills/workflows. | Loads/downloads `Xenova/all-MiniLM-L6-v2` and writes rule, file-path, skill, and workflow vectors to `~/.ctx/contextos/embeddings.db`. |
-| `ctx --config` | Opens an interactive multi-select panel for prompt sections. | You want to reduce ContextOS prompt output noise. | Toggles critical rules, suggested files, suggested skills, and suggested workflows globally under `~/.ctx/contextos/output-config.json`. |
+| `ctx --config` | Opens an interactive panel for prompt sections and suggestion limits. | You want to reduce ContextOS prompt output noise. | Toggles critical rules, suggested files, suggested skills, and suggested workflows globally under `~/.ctx/contextos/output-config.json`, then lets you set suggestion counts for files, skills, and workflows. |
 | `ctx refresh` | Refreshes the active Codex marketplace plugin and rebuilds local indexes. | Local development updates or a stale file retrieval index. | Copies the current package to `$CODEX_HOME/marketplaces/contextos`, rebuilds file-path embeddings and import adjacency, and refreshes code-review-graph embeddings when available. |
 | `ctx ruler -- <args>` | Forwards args to the installed `ruler` CLI. | You need native Ruler commands such as `init`, `apply`, or `revert`. | Preserves Ruler stdout/stderr and exit status. |
 | `ctx skillshare -- <args>` | Forwards args to the installed `skillshare` CLI. | You need native skillshare commands such as `status`, `target list`, `doctor`, `push`, or `pull`. | Preserves skillshare stdout/stderr and exit status. |
@@ -515,13 +515,13 @@ Prompt scoring does not walk the repository for file candidates or import expans
 
 If a prompt has no usable context candidates, the hook fails open without emitting an empty `hook context` block, records `emptyContextReason` in the workspace runtime file, and starts a detached `autowarm` rebuild with a cooldown. That background rebuild refreshes file vectors, skill/workflow vectors, import adjacency, and available code-review-graph node embeddings for the next prompt while keeping repository walking out of the current prompt hot path.
 
-Use `ctx --config` to choose which prompt sections ContextOS injects. Interactive `ctx setup` now includes the same multi-select step, while `ctx setup --yes` keeps the current saved config for automation. The panel supports multiple selection with `Space` and persists the global choice in `~/.ctx/contextos/output-config.json`. Disabling rules hides both critical and additional relevant rule sections; compliance metadata remains available for reports.
+Use `ctx --config` to choose which prompt sections ContextOS injects and how many suggestions each section may show. Interactive `ctx setup` includes the same section picker and limit prompts, while `ctx setup --yes` keeps the current saved config for automation. The panel supports multiple selection with `Space` and persists the global choice in `~/.ctx/contextos/output-config.json`. Defaults are five suggested files, five skills, and five workflows; caps are 20 files, 10 skills, and 5 workflows. Disabling rules hides both critical and additional relevant rule sections; compliance metadata remains available for reports.
 
-Injected prompt sections are intentionally compact: rules show only detected rule text, files show basenames without paths, skills show unique names as a comma-separated inline list without descriptions, and workflows show names with their agent chain. Stop hooks persist reports silently; run `ctx report` or `ctx evidence` when you want the detailed compliance output.
+Injected prompt sections are intentionally compact: rules show only detected rule text, files show a comma-separated inline list of basenames without paths, skills show unique names as a comma-separated inline list without descriptions, and workflows show names with their agent chain. Stop hooks persist reports silently; run `ctx report` or `ctx evidence` when you want the detailed compliance output.
 
 Codex may flatten newlines in its `UserPromptSubmit hook (completed)` preview. The injected `additionalContext` payload remains multiline; this is a Codex preview display limitation.
 
-Skill ranking uses bounded project hints from root/workspace `package.json` files and known mobile config files such as `app.json`, `app.config.*`, and `eas.json`. This lets Expo/EAS tasks activate specialized skills without walking the source tree on every prompt.
+Skill ranking uses bounded project hints from root/workspace `package.json` files and known mobile config files such as `app.json`, `app.config.*`, and `eas.json`. This lets Expo/EAS and MCP tasks activate specialized skills without walking the source tree on every prompt. Document-authoring prompts also get explicit intent handling for README, wiki, workspace documentation, guides, specs, and ADR work, while document-processing or workspace-automation providers only rank highly when the prompt actually names that provider or processing task.
 
 After `ctx refresh`, ContextOS invalidates the private hook bridge socket so prompts fall back to direct scoring until Codex restarts the long-running `ctx-mcp` process. Hook clients also discard a same-inode socket if an older bridge revision is detected.
 

package/bin/ctx.js

@@ -34,7 +34,7 @@ import { scanSkills, warmSkillEmbeddings } from "../plugins/ctx/lib/skill-discov
 import { parsePassthroughArgs, runPassthrough } from "../plugins/ctx/lib/passthrough.js";
 import { parseAgentList, parseSetupArgs, setupSummaryLines } from "../plugins/ctx/lib/setup-wizard.js";
 import { multiSelect } from "../plugins/ctx/lib/multi-select.js";
-import { configureOutputSections, enabledOutputSectionsLabel, loadOutputConfig } from "../plugins/ctx/lib/output-config.js";
+import { configureOutputSections, enabledOutputSectionsLabel, loadOutputConfig, outputConfigLimits, outputConfigLimitsLabel } from "../plugins/ctx/lib/output-config.js";
 import { syncWorkflows, warmWorkflowEmbeddings } from "../plugins/ctx/lib/workflow-discoverer.js";
 import { checkForUpdate } from "../plugins/ctx/lib/update-notifier.js";
 import { fetchSkillsForAgents, printSkillRecommendations, getAllLibraries, getInstallCommands } from "../plugins/ctx/lib/skill-library.js";
@@ -586,18 +586,20 @@ function contextOSWorkspaceDataDir(cwd = process.cwd()) {
 
 async function debug(task) {
   const cwd = process.cwd();
+  const limits = outputConfigLimits(loadOutputConfig({ dataRoot: contextOSDataDir() }));
   const scored = await scoreContext({
     cwd,
     prompt: task,
     dataDir: contextOSDataDir(),
-    maxFiles: 7,
-    maxSkills: 7,
+    maxFiles: limits.files,
+    maxSkills: limits.skills,
+    maxWorkflows: limits.workflows,
     embeddingTimeoutMs: Number(process.env.CONTEXTOS_EMBEDDING_DEBUG_TIMEOUT_MS || 5000)
   });
   const rules = scored.scoredRules;
-  const relevantFiles = scored.suggestedFiles.slice(0, 7);
-  const suggestedSkills = (scored.suggestedSkills || []).slice(0, 7);
-  const suggestedWorkflows = (scored.suggestedWorkflows || []).slice(0, 2);
+  const relevantFiles = scored.suggestedFiles.slice(0, limits.files);
+  const suggestedSkills = (scored.suggestedSkills || []).slice(0, limits.skills);
+  const suggestedWorkflows = (scored.suggestedWorkflows || []).slice(0, limits.workflows);
   const scheduled = scheduleContext({ rules, relevantFiles, suggestedSkills, suggestedWorkflows });
 
   console.log("ContextOS debug");
@@ -728,6 +730,21 @@ async function askSetupYesNo(rl, question, defaultValue = true) {
   return !/^n(o)?$/i.test(answer.trim());
 }
 
+async function askOutputLimit({ option, currentValue }) {
+  if (!process.stdin.isTTY) return currentValue;
+  const rl = readline.createInterface({ input, output });
+  try {
+    const answer = await rl.question(`◇ ${option.label} limit (0-${option.max}, current ${currentValue}): `);
+    const trimmed = answer.trim();
+    if (!trimmed) return currentValue;
+    const value = Number(trimmed);
+    if (!Number.isFinite(value)) return currentValue;
+    return Math.max(0, Math.min(option.max, Math.trunc(value)));
+  } finally {
+    rl.close();
+  }
+}
+
 async function setup({ args = [], cwd = process.cwd() } = {}) {
   const options = parseSetupArgs(args);
   const interactive = !options.yes && process.stdin.isTTY;
@@ -777,7 +794,8 @@ async function setup({ args = [], cwd = process.cwd() } = {}) {
     console.log("◇ Configure prompt output:");
     outputConfig = await configureOutputSections({
       dataRoot: contextOSDataDir(),
-      select: multiSelect
+      select: multiSelect,
+      askLimit: askOutputLimit
     });
   }
 
@@ -786,7 +804,8 @@ async function setup({ args = [], cwd = process.cwd() } = {}) {
   for (const line of setupSummaryLines({
     cwd,
     ...options,
-    promptSections: enabledOutputSectionsLabel(outputConfig)
+    promptSections: enabledOutputSectionsLabel(outputConfig),
+    promptLimits: outputConfigLimitsLabel(outputConfig)
   })) console.log(`│  ${line}`);
   console.log("");
 
@@ -871,7 +890,8 @@ try {
   } else if (command === "--config" || command === "config") {
     await configureOutputSections({
       dataRoot: contextOSDataDir(),
-      select: multiSelect
+      select: multiSelect,
+      askLimit: askOutputLimit
     });
   } else if (command === "install") {
     const copy = args.includes("--copy");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@minhpnq1807/contextos",
-  "version": "0.5.45",
+  "version": "0.5.46",
   "description": "Task-aware AGENTS.md context injection and compliance reporting for Codex, Claude Code, and Antigravity.",
   "type": "module",
   "bin": {

package/plugins/ctx/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "ctx",
-  "version": "0.5.45",
+  "version": "0.5.46",
   "description": "Inject task-relevant AGENTS.md rules into Codex through plugin hooks.",
   "author": {
     "name": "ContextOS"

package/plugins/ctx/lib/output-config.js

@@ -13,9 +13,16 @@ export const OUTPUT_SECTION_OPTIONS = [
   { value: "workflows", label: "Suggested workflow for this task", hint: "Include matching workflow recommendations." }
 ];
 
+export const OUTPUT_LIMIT_OPTIONS = [
+  { value: "files", label: "Suggested files", defaultValue: 5, max: 20 },
+  { value: "skills", label: "Suggested skills", defaultValue: 5, max: 10 },
+  { value: "workflows", label: "Suggested workflows", defaultValue: 5, max: 5 }
+];
+
 export function defaultOutputConfig() {
   return {
-    sections: Object.fromEntries(OUTPUT_SECTION_OPTIONS.map((option) => [option.value, true]))
+    sections: Object.fromEntries(OUTPUT_SECTION_OPTIONS.map((option) => [option.value, true])),
+    limits: Object.fromEntries(OUTPUT_LIMIT_OPTIONS.map((option) => [option.value, option.defaultValue]))
   };
 }
 
@@ -49,9 +56,19 @@ export function enabledOutputSectionsLabel(config = loadOutputConfig()) {
   return enabled.length ? enabled.join(", ") : "(none)";
 }
 
+export function outputConfigLimits(config = loadOutputConfig()) {
+  return normalizeOutputConfig(config).limits;
+}
+
+export function outputConfigLimitsLabel(config = loadOutputConfig()) {
+  const limits = outputConfigLimits(config);
+  return OUTPUT_LIMIT_OPTIONS.map((option) => `${option.value}: ${limits[option.value]}`).join(", ");
+}
+
 export async function configureOutputSections({
   dataRoot = defaultDataRoot(),
   select,
+  askLimit,
   logger = console.log
 } = {}) {
   if (typeof select !== "function") throw new Error("configureOutputSections requires a multi-select function");
@@ -64,11 +81,19 @@ export async function configureOutputSections({
     }))
   });
   const selectedSet = new Set(selected);
+  const limits = {};
+  for (const option of OUTPUT_LIMIT_OPTIONS) {
+    limits[option.value] = typeof askLimit === "function"
+      ? await askLimit({ option, currentValue: current.limits[option.value] })
+      : current.limits[option.value];
+  }
   const saved = saveOutputConfig({
-    sections: Object.fromEntries(OUTPUT_SECTION_OPTIONS.map((option) => [option.value, selectedSet.has(option.value)]))
+    sections: Object.fromEntries(OUTPUT_SECTION_OPTIONS.map((option) => [option.value, selectedSet.has(option.value)])),
+    limits
   }, { dataRoot });
   logger(`│  Saved ContextOS prompt section config: ${outputConfigPath(dataRoot)}`);
   logger(`│  Enabled sections: ${enabledOutputSectionsLabel(saved)}`);
+  logger(`│  Suggest limits: ${outputConfigLimitsLabel(saved)}`);
   return saved;
 }
 
@@ -80,6 +105,16 @@ function normalizeOutputConfig(config = {}) {
       typeof config.sections?.[option.value] === "boolean"
         ? config.sections[option.value]
         : defaults.sections[option.value]
+    ])),
+    limits: Object.fromEntries(OUTPUT_LIMIT_OPTIONS.map((option) => [
+      option.value,
+      normalizeLimit(config.limits?.[option.value], option)
     ]))
   };
 }
+
+function normalizeLimit(value, option) {
+  const number = Number(value);
+  if (!Number.isFinite(number)) return option.defaultValue;
+  return Math.max(0, Math.min(option.max, Math.trunc(number)));
+}

package/plugins/ctx/lib/prompt-hook.js

@@ -3,15 +3,11 @@ import { appendJsonLine, writeJsonFile } from "./fs-utils.js";
 import { maybeAutoWarmWorkspace } from "./auto-warm.js";
 import { callCtxScoreContext } from "./ctx-mcp-client.js";
 import { resolveHookCwd } from "./hook-io.js";
-import { loadOutputConfig } from "./output-config.js";
+import { loadOutputConfig, outputConfigLimits } from "./output-config.js";
 import { scoreContext as scoreContextDirect } from "./score-context.js";
 import fs from "node:fs";
 import path from "node:path";
 
-const PROMPT_FILE_LIMIT = 7;
-const PROMPT_SKILL_LIMIT = 7;
-const PROMPT_WORKFLOW_LIMIT = 2;
-
 export async function handlePromptPayload(
   payload,
   {
@@ -33,6 +29,8 @@ export async function handlePromptPayload(
   const cwd = resolvePromptTargetCwd({ cwd: hookCwd, prompt });
   const openFiles = payload.openFiles || payload.open_files || payload.files || [];
   const dataDir = dataPath ? path.dirname(dataPath) : undefined;
+  const effectiveOutputConfig = outputConfig || loadOutputConfig();
+  const promptLimits = outputConfigLimits(effectiveOutputConfig);
 
   let scored;
   try {
@@ -40,9 +38,9 @@ export async function handlePromptPayload(
       cwd,
       prompt,
       openFiles,
-      maxFiles: PROMPT_FILE_LIMIT,
-      maxSkills: PROMPT_SKILL_LIMIT,
-      maxWorkflows: PROMPT_WORKFLOW_LIMIT
+      maxFiles: promptLimits.files,
+      maxSkills: promptLimits.skills,
+      maxWorkflows: promptLimits.workflows
     }, {
       dataDir: mcpDataDir || dataDir,
       timeoutMs: Number(process.env.CONTEXTOS_MCP_BRIDGE_TIMEOUT_MS || 2000)
@@ -53,9 +51,9 @@ export async function handlePromptPayload(
         cwd,
         prompt,
         openFiles,
-        maxFiles: PROMPT_FILE_LIMIT,
-        maxSkills: PROMPT_SKILL_LIMIT,
-        maxWorkflows: PROMPT_WORKFLOW_LIMIT,
+        maxFiles: promptLimits.files,
+        maxSkills: promptLimits.skills,
+        maxWorkflows: promptLimits.workflows,
         dataDir: mcpDataDir || dataDir,
         embeddingTimeoutMs: Number(process.env.CONTEXTOS_HOOK_EMBEDDING_TIMEOUT_MS || 500),
         fileEmbeddingTimeoutMs: Number(process.env.CONTEXTOS_HOOK_FILE_EMBEDDING_TIMEOUT_MS || 1000)
@@ -76,10 +74,9 @@ export async function handlePromptPayload(
 
   if (scored.error) throw new Error(scored.error);
   const scoredRules = scored.scoredRules || [];
-  const relevantFiles = (scored.suggestedFiles || []).slice(0, PROMPT_FILE_LIMIT);
-  const suggestedSkills = (scored.suggestedSkills || []).slice(0, PROMPT_SKILL_LIMIT);
-  const suggestedWorkflows = (scored.suggestedWorkflows || []).slice(0, PROMPT_WORKFLOW_LIMIT);
-  const effectiveOutputConfig = outputConfig || loadOutputConfig();
+  const relevantFiles = (scored.suggestedFiles || []).slice(0, promptLimits.files);
+  const suggestedSkills = (scored.suggestedSkills || []).slice(0, promptLimits.skills);
+  const suggestedWorkflows = (scored.suggestedWorkflows || []).slice(0, promptLimits.workflows);
   const scheduled = scheduleContext({ rules: scoredRules, relevantFiles, suggestedSkills, suggestedWorkflows, outputConfig: effectiveOutputConfig });
   const contextEmptyReason = emptyContextReason({ scheduled, outputConfig: effectiveOutputConfig, injectContext });
   const autoWarm = autoWarmWorkspace({

package/plugins/ctx/lib/setup-wizard.js

@@ -37,7 +37,8 @@ export function setupSummaryLines({
   agents = DEFAULT_AGENTS,
   syncRules = true,
   syncSkills = true,
-  promptSections = null
+  promptSections = null,
+  promptLimits = null
 } = {}) {
   const lines = [
     `Installation directory: ${cwd}`,
@@ -47,5 +48,6 @@ export function setupSummaryLines({
     `skillshare skill sync: ${syncSkills ? "enabled" : "skipped"}`
   ];
   if (promptSections !== null) lines.push(`Prompt sections shown: ${promptSections}`);
+  if (promptLimits !== null) lines.push(`Prompt suggest limits: ${promptLimits}`);
   return lines;
 }

package/plugins/ctx/lib/skill-discoverer.js

@@ -20,9 +20,10 @@ const GENERIC_SKILL_TOKENS = new Set([
   "users", "when", "where", "whether", "with"
 ]);
 const SPECIALIZED_SKILL_TOKENS = new Set([
-  "android", "authorization", "cicd", "eas", "expo", "frontend", "ios", "next", "nextjs",
-  "mcp", "modelcontextprotocol", "postgres", "postgresql", "react", "react-native", "tailwind",
-  "typescript", "ui"
+  "android", "architecture", "authorization", "cicd", "documentation", "docs", "document",
+  "eas", "expo", "frontend", "ios", "next", "nextjs", "mcp", "modelcontextprotocol",
+  "postgres", "postgresql", "react", "react-native", "readme", "tailwind", "typescript",
+  "ui", "wiki", "writer"
 ]);
 
 const scanCache = new Map();
@@ -312,6 +313,8 @@ function isSkillDomainEligible(normalizedPrompt, enriched, projectTokens = new S
   if (isMcpSkill(skillText) && !isMcpRelevantTask(normalizedPrompt, projectTokens)) return false;
   if (isOffensiveSecuritySkill(skillText) && !isSecurityTask(normalizedPrompt)) return false;
   if (isPlatformCommerceSkill(skillText) && !isPlatformCommerceTask(normalizedPrompt, skillText)) return false;
+  if (isDocumentProcessingSkill(skillText) && !isDocumentProcessingTask(normalizedPrompt, skillText)) return false;
+  if (isWorkspaceAutomationSkill(skillText) && !isWorkspaceAutomationTask(normalizedPrompt, skillText)) return false;
   if (!/\beas\b/.test(normalizedPrompt)) return true;
   if (!/\b(android|ios)\b/.test(skillText)) return true;
   return /\b(eas|expo|cicd)\b/.test(skillText);
@@ -319,6 +322,10 @@ function isSkillDomainEligible(normalizedPrompt, enriched, projectTokens = new S
 
 function skillIntentBonus(normalizedPrompt, enriched, projectTokens = new Set()) {
   const skillText = normalize(`${enriched.name} ${enriched.description}`);
+  if (isDocumentAuthoringTask(normalizedPrompt)
+    && /\b(documentation|document|docs|doc|readme|wiki|writer|writing|coauthor|technical documentation|architecture documentation|onboarding|office productivity)\b/.test(skillText)) {
+    return 0.48;
+  }
   if (isMcpRelevantTask(normalizedPrompt, projectTokens)
     && /\b(mcp|model context protocol|modelcontextprotocol|agent memory|tool developer|tool builder)\b/.test(skillText)) {
     return 0.48;
@@ -368,6 +375,20 @@ function skillRelevancePriority(normalizedPrompt, enriched, projectTokens = new
   const skillText = normalize(`${enriched.name} ${enriched.description}`);
   const skillName = normalize(enriched.name);
   let priority = 0;
+  if (isDocumentAuthoringTask(normalizedPrompt)) {
+    if (skillName === "doc coauthoring") priority += 1300;
+    if (skillName === "documentation") priority += 720;
+    if (skillName === "docs architect") priority += 700;
+    if (skillName === "readme") priority += 660;
+    if (skillName === "wiki page writer") priority += 640;
+    if (skillName === "wiki architect") priority += 620;
+    if (skillName === "wiki onboarding") priority += 600;
+    if (skillName === "writer" || skillName === "docx" || skillName === "office productivity") priority += 560;
+    if (skillName === "agents md") priority += 420;
+    if (/\b(code documentation doc generate|documentation generation doc generate|api documentation|api documenter|reference builder|architecture)\b/.test(skillText)) priority += 320;
+    if (/\b(documentation|document|docs|doc|readme|wiki|writer|writing|coauthor|technical documentation)\b/.test(skillText)) priority += 130;
+    if (/\b(mcp|model context protocol|metasploit|penetration|exploit)\b/.test(skillText)) priority -= 220;
+  }
   if (isMcpRelevantTask(normalizedPrompt, projectTokens)) {
     if (skillName === "mcp builder") priority += 760;
     if (skillName === "mcp management") priority += 740;
@@ -448,6 +469,11 @@ function isFrontendCheckoutTask(normalizedPrompt) {
   return /\b(modal|display|show|checkout|library|frontend|webapp|page|button)\b/.test(normalizedPrompt);
 }
 
+function isDocumentAuthoringTask(normalizedPrompt) {
+  return /\b(create|write|edit|update|draft|generate|author|maintain|work on|produce)\b.*\b(document|documents|documentation|docs|doc|readme|wiki|workspace|workspaces|manual|guide|onboarding|spec|adr)\b/.test(normalizedPrompt)
+    || /\b(document|documents|documentation|docs|doc|readme|wiki|workspace|workspaces|manual|guide|onboarding|spec|adr)\b.*\b(create|write|edit|update|draft|generate|author|maintain|work on|produce)\b/.test(normalizedPrompt);
+}
+
 function isMcpTask(normalizedPrompt) {
   return /\b(mcp|model context protocol|tool server|tools server|server tool|bridge|proxy)\b/.test(normalizedPrompt);
 }
@@ -489,6 +515,36 @@ function isPlatformCommerceTask(normalizedPrompt, skillText) {
   return true;
 }
 
+function isDocumentProcessingSkill(skillText) {
+  return /\b(azure ai document|document intelligence|formrecognizer|document translation|cosmos db|azure cosmos|search documents|docusign)\b/.test(skillText);
+}
+
+function isDocumentProcessingTask(normalizedPrompt, skillText) {
+  if (/\bdocusign\b/.test(skillText)) return /\bdocusign|signature|envelope|sign\b/.test(normalizedPrompt);
+  if (/\bcosmos db|azure cosmos\b/.test(skillText)) return /\bcosmos|database|nosql|query|container\b/.test(normalizedPrompt);
+  if (/\bsearch documents\b/.test(skillText)) return /\bazure search|vector search|semantic search|index\b/.test(normalizedPrompt);
+  return /\bextract|ocr|analyze|translate|translation|form recognizer|document intelligence|azure\b/.test(normalizedPrompt);
+}
+
+function isWorkspaceAutomationSkill(skillText) {
+  return /\b(asana|bitbucket|slack|coda|google docs|google drive|google sheets|google slides|notion|telegram)\b/.test(skillText)
+    && /\b(automation|automate|workspace|workspaces|manage docs|documents)\b/.test(skillText);
+}
+
+function isWorkspaceAutomationTask(normalizedPrompt, skillText) {
+  if (/\basana\b/.test(skillText)) return /\basana\b/.test(normalizedPrompt);
+  if (/\bbitbucket\b/.test(skillText)) return /\bbitbucket\b/.test(normalizedPrompt);
+  if (/\bslack\b/.test(skillText)) return /\bslack\b/.test(normalizedPrompt);
+  if (/\bcoda\b/.test(skillText)) return /\bcoda\b/.test(normalizedPrompt);
+  if (/\bgoogle docs\b/.test(skillText)) return /\bgoogle docs\b/.test(normalizedPrompt);
+  if (/\bgoogle drive\b/.test(skillText)) return /\bgoogle drive\b/.test(normalizedPrompt);
+  if (/\bgoogle sheets\b/.test(skillText)) return /\bgoogle sheets\b/.test(normalizedPrompt);
+  if (/\bgoogle slides\b/.test(skillText)) return /\bgoogle slides\b/.test(normalizedPrompt);
+  if (/\bnotion\b/.test(skillText)) return /\bnotion\b/.test(normalizedPrompt);
+  if (/\btelegram\b/.test(skillText)) return /\btelegram\b/.test(normalizedPrompt);
+  return true;
+}
+
 export function projectSkillHints({ cwd = process.cwd() } = {}) {
   const hints = new Set();
   const packagePaths = workspacePackagePaths(cwd);