feat: Add onboarding and health check skills#4
Conversation
- recoup-getting-started: first-run onboarding flow (validate API key, discover capabilities, demo query, next steps) - recoup-health-check: diagnostic skill (connectivity, auth, credits, plugin inventory, troubleshooting) - Updated all manifests (claude, codex, cursor) to v0.2.0 - Rewrote README with install instructions, skill table, and plugin ecosystem overview - Complements llms.txt (PR #231) — together they form the complete agent onboarding story
|
Warning Review limit reached
More reviews will be available in 50 minutes and 19 seconds. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (6)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
4 issues found across 6 files
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="skills/recoup-health-check/SKILL.md">
<violation number="1" location="skills/recoup-health-check/SKILL.md:31">
P2: Step 1 hardcodes the API URL instead of using `RECOUP_API`, which can make connectivity results inconsistent with the environment being diagnosed.</violation>
<violation number="2" location="skills/recoup-health-check/SKILL.md:89">
P1: The functional test can produce false positives because `.data | length` returns `0` for missing/error payloads, and `>= 0` always passes.</violation>
</file>
<file name="skills/recoup-getting-started/SKILL.md">
<violation number="1" location="skills/recoup-getting-started/SKILL.md:3">
P2: This new skill duplicates onboarding trigger phrases already used by `skills/getting-started`, creating ambiguous routing between two "getting started" skills.</violation>
<violation number="2" location="skills/recoup-getting-started/SKILL.md:44">
P2: 403 is misdiagnosed as an invalid API key in Step 1, which conflicts with the file’s own error table and can send users to the wrong remediation path.</violation>
</file>
Reply with feedback, questions, or to request a fix.
Re-trigger cubic
| ```bash | ||
| # Quick search — minimal payload, fast response | ||
| curl -s "$RECOUP_API/research?q=test&type=artists&beta=true" \ | ||
| -H "x-api-key: $RECOUP_API_KEY" | jq '.data | length' |
There was a problem hiding this comment.
P1: The functional test can produce false positives because .data | length returns 0 for missing/error payloads, and >= 0 always passes.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At skills/recoup-health-check/SKILL.md, line 89:
<comment>The functional test can produce false positives because `.data | length` returns `0` for missing/error payloads, and `>= 0` always passes.</comment>
<file context>
@@ -0,0 +1,120 @@
+```bash
+# Quick search — minimal payload, fast response
+curl -s "$RECOUP_API/research?q=test&type=artists&beta=true" \
+ -H "x-api-key: $RECOUP_API_KEY" | jq '.data | length'
+```
+
</file context>
|
|
||
| ```bash | ||
| # Basic connectivity test (no auth required) | ||
| curl -s -o /dev/null -w "%{http_code}" https://api.recoupable.com/api/health |
There was a problem hiding this comment.
P2: Step 1 hardcodes the API URL instead of using RECOUP_API, which can make connectivity results inconsistent with the environment being diagnosed.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At skills/recoup-health-check/SKILL.md, line 31:
<comment>Step 1 hardcodes the API URL instead of using `RECOUP_API`, which can make connectivity results inconsistent with the environment being diagnosed.</comment>
<file context>
@@ -0,0 +1,120 @@
+
+```bash
+# Basic connectivity test (no auth required)
+curl -s -o /dev/null -w "%{http_code}" https://api.recoupable.com/api/health
+```
+
</file context>
| curl -s -o /dev/null -w "%{http_code}" https://api.recoupable.com/api/health | |
| curl -s -o /dev/null -w "%{http_code}" "$RECOUP_API/health" |
| @@ -0,0 +1,136 @@ | |||
| --- | |||
| name: recoup-getting-started | |||
| description: First-run onboarding for AI agents using Recoup. Validates API credentials, discovers available capabilities, runs a demo query, and recommends next steps. Triggers on "get started with Recoup", "set up Recoup", "how do I use Recoup", first plugin install, or any onboarding request. This is the default entry point for new agents. | |||
There was a problem hiding this comment.
P2: This new skill duplicates onboarding trigger phrases already used by skills/getting-started, creating ambiguous routing between two "getting started" skills.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At skills/recoup-getting-started/SKILL.md, line 3:
<comment>This new skill duplicates onboarding trigger phrases already used by `skills/getting-started`, creating ambiguous routing between two "getting started" skills.</comment>
<file context>
@@ -0,0 +1,136 @@
+---
+name: recoup-getting-started
+description: First-run onboarding for AI agents using Recoup. Validates API credentials, discovers available capabilities, runs a demo query, and recommends next steps. Triggers on "get started with Recoup", "set up Recoup", "how do I use Recoup", first plugin install, or any onboarding request. This is the default entry point for new agents.
+---
+
</file context>
| ``` | ||
|
|
||
| **Expected response:** JSON with `id`, `name`, `email`, `plan`. If you get | ||
| `401` or `403`, the key is invalid — the user needs to generate one at |
There was a problem hiding this comment.
P2: 403 is misdiagnosed as an invalid API key in Step 1, which conflicts with the file’s own error table and can send users to the wrong remediation path.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At skills/recoup-getting-started/SKILL.md, line 44:
<comment>403 is misdiagnosed as an invalid API key in Step 1, which conflicts with the file’s own error table and can send users to the wrong remediation path.</comment>
<file context>
@@ -0,0 +1,136 @@
+```
+
+**Expected response:** JSON with `id`, `name`, `email`, `plan`. If you get
+`401` or `403`, the key is invalid — the user needs to generate one at
+<https://developers.recoupable.com/agents>.
+
</file context>
1 participant
What
Adds two skills to the platform plugin (which was previously an empty skeleton):
recoup-getting-startedFirst-run onboarding for AI agents:
/accounts/merecoup-health-checkDiagnostic skill for troubleshooting:
Why
Complements llms.txt (PR #231) — together they form the complete agent onboarding story:
llms.txttells agents what Recoup doesAddresses roadmap P0: "Agent onboarding docs — optimize first tokens an LLM gets back from our docs"
Changes
skills/recoup-getting-started/SKILL.md(new)skills/recoup-health-check/SKILL.md(new)Summary by cubic
Adds two agent skills to
recoup-platform-pluginfor first-run onboarding and health diagnostics. This completes the onboarding story alongsidellms.txtby validating setup, discovering capabilities, and guiding next steps.recoup-getting-started: Validates API key (/accounts/me), discovers installed plugins, runs a demo artist search, and suggests the next action.recoup-health-check: Checks API connectivity, validates auth, reports credit balance, inventories plugins, runs a functional search, and lists common fixes.v0.2.0; addedskillspath and updated descriptions/tags toward onboarding and health checks.Written for commit 66c344d. Summary will update on new commits.