Skip to content
Skills Directory
Skills
Learn
Security
Categories
Docs
Blog
Pro
Advertise
Submit a skill
Browse Secure Claude Skills
Search verified agent skills and review security grades before installing ·
full A–Z index
Plugin Scanner
A
Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure, and supply-chain risks before installing or trusting them. Use when evaluating agent ecosystem content before installation, publication, or use. Trigger with "scan this skill", "check this MCP server", "audit this agent plugin", or "verify this AI tool".
ai-agents
python
rust
Votes:
0
GitHub stars:
2,902
Hol Guard
A
Protects local AI coding-agent workflows with HOL Guard pre-execution controls, approvals, receipts, and verification. Use when enabling Guard for a supported local harness, reviewing a Guard block, or validating protection before trusted tool execution. Trigger with "hol guard", "protect this workspace", "review guard approvals", or "check guard status".
ai-agents
python
rust
Votes:
0
GitHub stars:
2,902
Langfuse Trace Ingestion Medic
A
Investigate missing, partial or incorrectly nested Langfuse observations by reconciling a captured OTLP batch with Observations API v2 readbacks. Use when traces disappear after a serverless exit, exported spans are absent, or parent context differs. Trigger with "Langfuse spans missing", "flush succeeded but no observations" or "why is this Langfuse child at the root?".
ai-agents
python
bash
Votes:
0
GitHub stars:
2,902
Langfuse Prompt Release Guardian
A
Review Langfuse prompt promotions or rollbacks using explicit versions, fresh label snapshots, reviewed content hashes and runtime variable contracts. Verify supplied prompt webhooks without treating signatures as release approval. Use when reviewing this evidence. Trigger with "promote this Langfuse prompt", "check a prompt rollback" or "is this signed prompt update enough to deploy?".
ai-agents
python
bash
Votes:
0
GitHub stars:
2,902
Langfuse Experiment Guardian
A
Compare Langfuse experiment baseline and candidate results at case level using reviewed dataset, content and evaluator identities. Detect missing cases, evaluator errors and critical regressions before proposing a release. Use when reviewing these cases. Trigger with "Langfuse experiment passed on average", "candidate lost evaluation cases" or "can this experiment replace our reviewed baseline?".
ai-agents
javascript
python
Votes:
0
GitHub stars:
2,902
Langfuse Data Boundary Auditor
A
Audit supplied Langfuse observation payloads for unapproved fields, incomplete cursor coverage and retention evidence gaps. Separate project retention from Cloud access windows and dataset/audit/external-copy scope. Use when reviewing this evidence. Trigger with "review a Langfuse debug export", "did anonymization leave metadata?" or "does retention cover all these Langfuse records?".
ai-agents
python
go
Votes:
0
GitHub stars:
2,902
Skills Directory
S
Skills Directory
3 slots · $399/mo · one ad per page · sponsors can never buy grades.
See placements
Langfuse Cost Forensics
A
Audit Langfuse recorded-cost observations for missing usage, unavailable cost, cursor gaps and scope mismatches. Separate explicit zero from unknown and partial subtotals from complete retrieved sets. Use when reviewing this evidence. Trigger with "Langfuse spend looks wrong", "missing generation cost" or "does this first page prove our total?".
ai-agents
python
go
Votes:
0
GitHub stars:
2,902
Ga4 Report Forensics
A
Investigate conflicting GA4 report numbers using request and response receipts. Compare windows, identities, filters and row coverage; distinguish sampling, thresholding and high-cardinality loss. Use when GA4 API and UI reports disagree or exported rows are missing. Trigger with "GA4 user counts differ", "missing GA4 rows" or "is this report sampled?".
ai-agents
python
go
Votes:
0
GitHub stars:
2,902
Ga4 Measurement Verifier
A
Check expected GA4 event names and counts against a realtime report receipt, preserving row coverage, minute-window and deployment-timing limits. Use when verifying tracking after a deployment or investigating missing events. Trigger with "did GA4 receive sign_up?", "check GA4 tracking after deploy" or "missing GA4 events".
ai-agents
python
go
Votes:
0
GitHub stars:
2,902
Ga4 Export Guardian
A
Investigate GA4 BigQuery export gaps, daily/intraday overlap and query scan risk from table-inventory and dry-run receipts. Use when exported days appear missing or a GA4 query may scan too much. Trigger with "missing GA4 BigQuery tables", "GA4 export delayed" or "check this GA4 query's scan budget".
ai-agents
python
go
Votes:
0
GitHub stars:
2,902
Coreweave Workload Health
A
Verify workload readiness, GPU allocation and observed activity from
ai-agents
python
bash
Votes:
0
GitHub stars:
2,902
Coreweave Cks Provisioning
A
Review original Terraform CKS cluster, VPC and node-pool plans for cost,
ai-agents
python
bash
Votes:
0
GitHub stars:
2,902
Coreweave Caios Stage Model
A
Plan CAIOS model transfers and verify exact object sizes, checksums and
ai-agents
python
bash
Votes:
0
GitHub stars:
2,902
Xletter
A
Use the xLetter HTTPS API for a reusable Agent mailbox, asynchronous text messages, message history, and public contact cards. Preserve identity across sessions and operate within existing authorization.
ai-agents
go
git
Votes:
0
GitHub stars:
61
Webask Results Digest
A
Summarize WebAsk survey distributions, filtered reports and free-text answers with get_quiz_summary, get_quiz_report and get_quiz_report_inputs. Use for survey findings, period comparisons or report figures; state percentage bases and incomplete-response caveats.
ai-agents
go
bash
Votes:
0
GitHub stars:
61
Visualize Opentelemetry Agent Traces With Agent Prism
A
Add Agent Prism's React trace viewer to inspect LLM calls, tool executions, retries, and agent workflows from OpenTelemetry or Langfuse-style trace data.
ai-agents
go
react
Votes:
0
GitHub stars:
61
Verify Scoped Kafka Tool Access Through Zilla Mcp
A
Review scoped MCP access to native Kafka, Schema Registry and Kafka Connect tools in Zilla, then return a tool-and-scope evidence matrix.
ai-agents
go
docker
Votes:
0
GitHub stars:
61
Use Clirelay As A Self Hosted Ai Gateway For Coding Agents
A
Route Claude Code, Codex, Gemini CLI, and OpenAI-compatible coding tools through a self-hosted gateway with tenant controls, request logs, quotas, and provider failover.
ai-agents
go
sql
Votes:
0
GitHub stars:
61
Turn Messy Datasets Into Auditable Reports With Data Master
A
Use data-master to preserve raw tabular data, hold ambiguous cleaning decisions for review, run unit-aware statistics and sensitivity checks, and produce Markdown, HTML and PDF reports with machine-verifiable audit evidence.
ai-agents
go
git
Votes:
0
GitHub stars:
61
Triage Lunora Deployment Errors And Migration Status Through Mcp
A
Inspect Lunora logs, grouped errors, query performance and pending migrations through MCP, then return a scoped incident handoff without changing the deployment.
ai-agents
go
node
Votes:
0
GitHub stars:
61
1
2
…
34732