Install
$ agentstack add skill-iblai-api-iblai-agent-skills ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
iblai-agent-skills
Manage an agent's skills via the API: browse the org's skill catalog, toggle which skills an agent has assigned, and manage the catalog itself (create / edit / delete reusable skills). Use when giving an agent reusable skill instructions.
Auth & conventions
- Base URL:
https://api.iblai.app - Header:
Authorization: Api-Token $IBLAI_API_KEYon every request. - Path vars:
{org}=$IBLAI_ORG,{username}=$IBLAI_USERNAME,
{mentor} = the agent's unique id (e.g. d17dc729-60fd-4363-81a0-f67d9318b03e).
- Not connected yet? Run
/iblai-loginfirst to populateIBLAI_ORG,
IBLAI_USERNAME, and IBLAI_API_KEY.
Reads
- GET
https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/mentors/{mentor}/claw-config/— gate (skills require a sandbox). - GET
https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/agent-skills/— platform skill catalog. - GET
https://api.iblai.app/dm/api/ai-mentor/orgs/{org}/mentors/{mentor}/skills/— skills assigned to this agent.
Writes
Assignment (toggle)
- POST
…/mentors/{mentor}/skills/— assign a skill to the agent:
``json { "skill": "uuid (required)", "enabled": "boolean" } ``
- PATCH
…/mentors/{mentor}/skills/{assignmentId}/— enable / disable an assignment:
``json { "enabled": "boolean" } ``
- DELETE
…/mentors/{mentor}/skills/{assignmentId}/— unassign the skill (no body).
Catalog CRUD
- POST
…/orgs/{org}/agent-skills/— create a catalog skill:
``json { "name": "string (required)", "slug": "string (required)", "description": "string", "version": "string", "instruction": "string", "metadata": "object", "enabled": "boolean" } ``
- PATCH
…/orgs/{org}/agent-skills/{id}/— update the catalog skill (partial). - DELETE
…/orgs/{org}/agent-skills/{id}/— delete the catalog skill (no body). Destructive — confirm with the user first.
Example
Create a catalog skill, then assign it to the agent:
# Create the skill in the org catalog
curl -X POST \
"https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/agent-skills/" \
-H "Authorization: Api-Token $IBLAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Cite Sources",
"slug": "cite-sources",
"description": "Always cite sources inline.",
"instruction": "When answering, cite each claim with a source.",
"enabled": true
}'
# Assign it to the agent (use the returned skill uuid)
curl -X POST \
"https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/mentors/$MENTOR/skills/" \
-H "Authorization: Api-Token $IBLAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "skill": "8f1c…uuid", "enabled": true }'
Notes
- Skills require a connected sandbox — the feature is gated via the
claw-config/ endpoint above. If it returns 404 the agent has no sandbox wired up; connect one first via /iblai-agent-sandbox.
- The catalog (
agent-skills/) is org-scoped and shared across agents; the
assignment list (mentors/{mentor}/skills/) is per-agent. Editing a catalog skill affects every agent it is assigned to.
- Toggling
enabledon an assignment keeps the skill assigned but inactive;
use DELETE to remove the assignment entirely.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.