Install
$ agentstack add skill-cloutdesk-agents-influencer-contract-review ✓ 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 No
- ✓ 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.
About
Influencer Contract Review
What this skill does
Inbound agreements arrive in many shapes — sometimes a creator's manager-drafted contract, sometimes a brand client's pre-populated template with an unusual exclusivity ask, sometimes a paid-media addendum that adds new usage rights. The first pass is always the same: classify the document, flag the high-risk clauses, identify missing standard clauses the agency's playbook expects, and summarize. This skill performs that first pass and produces a structured risk register the contract owner can scan in under a minute.
The skill does not negotiate — it surfaces. The negotiation pass lives in [influencer-contract-negotiation](../influencer-contract-negotiation/SKILL.md). A clean review can hand off directly to signature via [compliance-check](../compliance-check/SKILL.md); a dirty review escalates to the negotiation skill or to a human contract owner.
Composed into
agreement-reviewer— first-pass triage of every inbound agreement before deciding negotiate-vs-sign
Cloutdesk MCP tools typically called
| Tool | What for | |---|---| | cloutdesk__get_collab | Read the collab context the agreement attaches to | | cloutdesk__emit_event | Log the review-completed event for collab timeline |
Required scopes
collaborations:readevents:emit
Standalone usage
Drop this skill into:
- Claude Code / Claude Desktop —
.claude/skills/influencer-contract-review/SKILL.md(project-scoped) or~/.claude/skills/influencer-contract-review/SKILL.md(user-scoped) - OpenAI Codex —
.codex/skills/influencer-contract-review/SKILL.md - Other Anthropic Agent Skills-compliant runtimes — per the runtime's documented skills directory
For Microsoft Agent Framework consumers, this skill's behavior is inlined into the template-level microsoft.yaml manifests under their instructions: field rather than dropped in as a separate file.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cloutdesk
- Source: cloutdesk/agents
- License: MIT
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.