garrytan · malikrohail · Mar 24, 2026
diff --git a/AGENTS.md b/AGENTS.md
@@ -15,6 +15,7 @@ Skills live in `.agents/skills/`. Invoke them by name (e.g., `/office-hours`).
 | `/plan-eng-review` | Lock architecture, data flow, edge cases, and tests. |
 | `/plan-design-review` | Rate each design dimension 0-10, explain what a 10 looks like. |
 | `/design-consultation` | Build a complete design system from scratch. |
+| `/find-skills` | Query the external Agent Skills / skills.sh marketplace for vendor/framework-specific skills. |
 | `/review` | Pre-landing PR review. Finds bugs that pass CI but break in prod. |
 | `/debug` | Systematic root-cause debugging. No fixes without investigation. |
 | `/design-review` | Design audit + fix loop with atomic commits. |

diff --git a/CLAUDE.md b/CLAUDE.md
@@ -75,6 +75,7 @@ gstack/
 ├── benchmark/       # /benchmark skill (performance regression detection)
 ├── canary/          # /canary skill (post-deploy monitoring loop)
 ├── codex/           # /codex skill (multi-AI second opinion via OpenAI Codex CLI)
+├── find-skills/     # /find-skills skill (external marketplace search for Agent Skills / skills.sh)
 ├── land-and-deploy/ # /land-and-deploy skill (merge → deploy → canary verify)
 ├── office-hours/    # /office-hours skill (YC Office Hours — startup diagnostic + builder brainstorm)
 ├── investigate/     # /investigate skill (systematic root-cause debugging)

diff --git a/README.md b/README.md
@@ -46,11 +46,11 @@ Fork it. Improve it. Make it yours. And if you want to hate on free open source
 
 Open Claude Code and paste this. Claude does the rest.
 
-> Install gstack: run **`git clone https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`** then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade. Then ask the user if they also want to add gstack to the current project so teammates get it.
+> Install gstack: run **`git clone https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`** then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /find-skills, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade. Then ask the user if they also want to add gstack to the current project so teammates get it.
 
 ### Step 2: Add to your repo so teammates get it (optional)
 
-> Add gstack to this project: run **`cp -Rf ~/.claude/skills/gstack .claude/skills/gstack && rm -rf .claude/skills/gstack/.git && cd .claude/skills/gstack && ./setup`** then add a "gstack" section to this project's CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, and tells Claude that if gstack skills aren't working, run `cd .claude/skills/gstack && ./setup` to build the binary and register skills.
+> Add gstack to this project: run **`cp -Rf ~/.claude/skills/gstack .claude/skills/gstack && rm -rf .claude/skills/gstack/.git && cd .claude/skills/gstack && ./setup`** then add a "gstack" section to this project's CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /find-skills, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, and tells Claude that if gstack skills aren't working, run `cd .claude/skills/gstack && ./setup` to build the binary and register skills.
 
 Real files get committed to your repo (not a submodule), so `git clone` just works. Everything lives inside `.claude/`. Nothing touches your PATH or runs in the background.
 
@@ -145,6 +145,7 @@ Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-
 | `/plan-eng-review` | **Eng Manager** | Lock in architecture, data flow, diagrams, edge cases, and tests. Forces hidden assumptions into the open. |
 | `/plan-design-review` | **Senior Designer** | Rates each design dimension 0-10, explains what a 10 looks like, then edits the plan to get there. AI Slop detection. Interactive — one AskUserQuestion per design choice. |
 | `/design-consultation` | **Design Partner** | Build a complete design system from scratch. Researches the landscape, proposes creative risks, generates realistic product mockups. |
+| `/find-skills` | **Marketplace Search** | Find the best external Agent Skills / skills.sh skills for a technology or workflow query. |
 | `/review` | **Staff Engineer** | Find the bugs that pass CI but blow up in production. Auto-fixes the obvious ones. Flags completeness gaps. |
 | `/investigate` | **Debugger** | Systematic root-cause debugging. Iron Law: no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fixes. |
 | `/design-review` | **Designer Who Codes** | Same audit as /plan-design-review, then fixes what it finds. Atomic commits, before/after screenshots. |
@@ -165,6 +166,7 @@ Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-
 
 | Skill | What it does |
 |-------|-------------|
+| `/find-skills` | **Marketplace Search** — query Agent Skills / skills.sh for external vendor/framework-specific skills and get copy-paste install commands. |
 | `/codex` | **Second Opinion** — independent code review from OpenAI Codex CLI. Three modes: review (pass/fail gate), adversarial challenge, and open consultation. Cross-model analysis when both `/review` and `/codex` have run. |
 | `/careful` | **Safety Guardrails** — warns before destructive commands (rm -rf, DROP TABLE, force-push). Say "be careful" to activate. Override any warning. |
 | `/freeze` | **Edit Lock** — restrict file edits to one directory. Prevents accidental changes outside scope while debugging. |
@@ -234,7 +236,7 @@ Data is stored in [Supabase](https://supabase.com) (open source Firebase alterna
 ## gstack
 Use /browse from gstack for all web browsing. Never use mcp__claude-in-chrome__* tools.
 Available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review,
-/design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse,
+/design-consultation, /find-skills, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse,
 /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro,
 /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard,
 /unfreeze, /gstack-upgrade.

diff --git a/SKILL.md b/SKILL.md
@@ -8,7 +8,7 @@ description: |
   test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots.
   Also suggest adjacent gstack skills by stage: brainstorm /office-hours; strategy
   /plan-ceo-review; architecture /plan-eng-review; design /plan-design-review or
-  /design-consultation; auto-review /autoplan; debugging /investigate; QA /qa; code review
+  /design-consultation; external marketplace /find-skills; auto-review /autoplan; debugging /investigate; QA /qa; code review
   /review; visual audit /design-review; shipping /ship; docs /document-release; retro
   /retro; second opinion /codex; prod safety /careful or /guard; scoped edits /freeze or
   /unfreeze; gstack upgrades /gstack-upgrade. If the user opts out of suggestions, stop

diff --git a/SKILL.md.tmpl b/SKILL.md.tmpl
@@ -8,7 +8,7 @@ description: |
   test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots.
   Also suggest adjacent gstack skills by stage: brainstorm /office-hours; strategy
   /plan-ceo-review; architecture /plan-eng-review; design /plan-design-review or
-  /design-consultation; auto-review /autoplan; debugging /investigate; QA /qa; code review
+  /design-consultation; external marketplace /find-skills; auto-review /autoplan; debugging /investigate; QA /qa; code review
   /review; visual audit /design-review; shipping /ship; docs /document-release; retro
   /retro; second opinion /codex; prod safety /careful or /guard; scoped edits /freeze or
   /unfreeze; gstack upgrades /gstack-upgrade. If the user opts out of suggestions, stop

diff --git a/autoplan/SKILL.md b/autoplan/SKILL.md
@@ -479,6 +479,36 @@ Then prepend a one-line HTML comment to the plan file:
   button, modal, layout, dashboard, sidebar, nav, dialog). Require 2+ matches. Exclude
   false positives ("page" alone, "UI" in acronyms).
 
+## External Skill Marketplace Check
+
+If `PROACTIVE` is `"false"`, skip this step entirely.
+
+Use this step when the user's request or current plan/design context clearly names a
+platform, vendor, framework, or tool that may already have a strong external skill in
+the Agent Skills / skills.sh marketplace.
+
+1. Extract 2-6 concrete technology keywords from the user's request or current plan/design context.
+2. Write the original request (or a short summary of the current plan/design) to a temp file:
+
+```bash
+TMP_QUERY=$(mktemp /tmp/gstack-marketplace-query-XXXX.txt)
+cat > "$TMP_QUERY" <<'EOF'
+[original user request or current plan/design summary]
+EOF
+~/.claude/skills/gstack/bin/gstack-marketplace-search --query-file "$TMP_QUERY" --keyword "keyword-1" --keyword "keyword-2" --limit 3 --json
+rm -f "$TMP_QUERY"
+```
+
+3. If the helper returns `"status": "ok"` with non-empty `results`, surface an
+   **External Skills Worth Considering** section with up to 3 results:
+   - scoped name
+   - one-line why it matches
+   - install command
+4. Never auto-install or auto-run marketplace skills. This step is recommendation-only.
+5. If the helper returns `unavailable` or no results, continue silently.
+6. If a gstack built-in skill already covers the need well, prefer the gstack skill and
+   present the external result only as optional context.
+
 ### Step 3: Load skill files from disk
 
 Read each file using the Read tool:

diff --git a/autoplan/SKILL.md.tmpl b/autoplan/SKILL.md.tmpl
@@ -137,6 +137,8 @@ Then prepend a one-line HTML comment to the plan file:
   button, modal, layout, dashboard, sidebar, nav, dialog). Require 2+ matches. Exclude
   false positives ("page" alone, "UI" in acronyms).
 
+{{MARKETPLACE_SKILL_DISCOVERY}}
+
 ### Step 3: Load skill files from disk
 
 Read each file using the Read tool: