skillmds 1.0.15 → 1.0.16

package/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 All notable changes to `skillmds` are documented here. Versions follow [semver](https://semver.org).
 
+## 1.0.16
+
+- **Installs are no longer gated on verification.** Any skill installs directly — verified or not — with no flag, no prompt, and no second step, from both the CLI (`skillmd add`) and the MCP `skillmd_install` tool. Security flags (network_calls, executes_scripts, reads_secrets, docs_only) are still shown on the result as information, but never block. `--deny <flag>` remains available as an opt-in for anyone who wants to exclude a flag; `--allow-unverified` is now a no-op kept for backward compatibility.
+
 ## 1.0.15
 
 - Search is now **browsable in the interactive menu**: arrow through results, press Enter on one to see a card, and install it to your project or user directory — all without leaving the CLI (`← Back` at each level; Esc goes up one step, never quits).

package/bin/skillmd-mcp.mjs

@@ -70,13 +70,12 @@ const TOOLS = [
   {
     name: "skillmd_install",
     description:
-      "Install a skill by slug: validates it, then writes its SKILL.md into the agent's skills directory. Never executes any scripts. Unverified skills are refused unless allow_unverified is true. Do not set allow_unverified on your own initiative — only after the human has explicitly approved installing this specific unverified skill.",
+      "Install a skill by slug: writes its SKILL.md into the agent's skills directory. Never executes any scripts. Any skill installs; the response reports its security flags (docs_only / network_calls / executes_scripts / reads_secrets) as information.",
     inputSchema: {
       type: "object",
       properties: {
         slug: { type: "string", description: "owner/name, e.g. anthropic/pdf" },
         dest: { type: "string", description: "Target skills dir. Default ~/.claude/skills" },
-        allow_unverified: { type: "boolean", description: "Install even if the skill is not verified by SkillMD. Never set this on your own initiative — only after the human has explicitly approved this specific skill." },
       },
       required: ["slug"],
     },
@@ -193,13 +192,8 @@ async function handleCall(name, args) {
       }
       const skill = await api(`/api/skills/${owner}/${slugName}`);
       const flags = skill.security_flags ?? [];
-      if (skill.verified === false && !args.allow_unverified) {
-        return text(
-          `Refused: ${args.slug} is not yet verified by SkillMD (security flags: ${flags.join(", ") || "unscanned"}). ` +
-          `Review it at https://skillmd.com/skills/${args.slug}. Only call skillmd_install again with allow_unverified: true ` +
-          `if the human explicitly approves installing this specific unverified skill — do not decide this yourself.`,
-        );
-      }
+      // Verification never gates installs — any skill installs; flags are
+      // reported in the response as information, not a wall.
       const raw = reconstructSkillMd(skill); // returns raw_md verbatim when the registry has it
       if (lint) {
         const result = lint(raw, { slug: slugName });

package/dist/cli.js

@@ -894,7 +894,7 @@ function infoCommand() {
 }
 
 // ../cli/src/commands/add.ts
-import { Command as Command7 } from "commander";
+import { Command as Command7, Option } from "commander";
 import { existsSync as existsSync4 } from "fs";
 import pc7 from "picocolors";
 
@@ -1007,16 +1007,6 @@ var defaultDeps = {
       body: JSON.stringify({ via: "cli" })
     }).catch(() => {
     });
-  },
-  async confirmUnverified(c, score, secFlags) {
-    if (!process.stdin.isTTY) return false;
-    const { confirm: confirm2, isCancel: isCancel4 } = await import("@clack/prompts");
-    const ok = await confirm2({
-      message: `${c.name} is not yet verified by SkillMD (lint score ${score}${secFlags.length ? `; flags: ${secFlags.join(", ")}` : ""}). Install anyway?`,
-      initialValue: false
-    });
-    if (isCancel4(ok)) return false;
-    return ok === true;
   }
 };
 async function runAdd(arg, flags, deps = defaultDeps) {
@@ -1039,18 +1029,9 @@ async function runAdd(arg, flags, deps = defaultDeps) {
     }
     if (deniedFlags.length) {
       blocked.push({ name: c.name, reason: `denied security flags: ${deniedFlags.join(", ")}` });
-      lines.push(pc7.red(`\u2717 ${c.name} blocked \u2014 ${deniedFlags.join(", ")}`));
+      lines.push(pc7.red(`\u2717 ${c.name} blocked \u2014 you passed --deny ${deniedFlags.join(", ")}`));
       continue;
     }
-    if (c.registrySlug && c.verified === false && !flags.allowUnverified) {
-      const ok = !flags.yes && deps.confirmUnverified ? await deps.confirmUnverified(c, result.score, allFlags) : false;
-      if (!ok) {
-        blocked.push({ name: c.name, reason: "unverified registry skill (use --allow-unverified)" });
-        lines.push(pc7.yellow(`\u2717 ${c.name} blocked \u2014 not yet verified by SkillMD${allFlags.length ? ` (flags: ${allFlags.join(", ")})` : ""}`));
-        lines.push(pc7.dim(`  review at https://skillmd.com/skills/${c.registrySlug}, then re-run with --allow-unverified`));
-        continue;
-      }
-    }
     const files = c.files ?? [{ path: "SKILL.md", contents: c.raw }];
     for (const agentId of targets) {
       const dir = agentDir(agentId, scope);
@@ -1070,7 +1051,7 @@ async function runAdd(arg, flags, deps = defaultDeps) {
   return { written, blocked, exitCode, output: lines.join("\n") };
 }
 function addCommand() {
-  return new Command7("add").description("Install a skill from the registry, a GitHub repo, or a local path (lints before writing)").argument("<source>", "registry slug (owner/name), GitHub source, or local path").option("-g, --global", "install to the user directory instead of the project").option("-a, --agent <agents...>", "target specific agents").option("-s, --skill <names...>", "install only specific skills by name ('*' for all)").option("--copy", "copy files (default)", true).option("-y, --yes", "skip confirmation prompts").option("--allow-unverified", "allow installing unverified registry skills").option("--skip-lint", "install even if the skill fails lint").option("--deny <flags...>", "refuse skills with these security flags").action(async (source, opts, cmd) => {
+  return new Command7("add").description("Install a skill from the registry, a GitHub repo, or a local path (lints before writing)").argument("<source>", "registry slug (owner/name), GitHub source, or local path").option("-g, --global", "install to the user directory instead of the project").option("-a, --agent <agents...>", "target specific agents").option("-s, --skill <names...>", "install only specific skills by name ('*' for all)").option("--copy", "copy files (default)", true).option("-y, --yes", "skip confirmation prompts").addOption(new Option("--allow-unverified").hideHelp()).option("--skip-lint", "install even if the skill fails lint").option("--deny <flags...>", "refuse skills carrying any of these security flags (opt-in)").action(async (source, opts, cmd) => {
     const merged = { ...cmd.parent?.opts(), ...opts };
     const run = await runAdd(source, merged);
     console.log(run.output);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "skillmds",
-  "version": "1.0.15",
+  "version": "1.0.16",
   "description": "SkillMD for agents: the `skillmds` MCP server + the `skillmd` CLI (lint, scan, search, install, publish Agent Skills) from skillmd.com.",
   "type": "module",
   "bin": {