🔎 Evidence browser

Browse the trust index

Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.

⚙️ Filters · 2 active
✨ Quick picks
🏷 Categories · coding-agents-and-ides

🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.

🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got. Some cards now also surface how the skill behaved when clearly fake credentials were present.

📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.

⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.

🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.

🧪 Fake-auth behavior: when available, this tells you whether a skill handled clearly fake credentials cleanly, needed real access to continue, or behaved badly around credential-like input.

Results

Showing 24 of 1200 skills in the browsable catalog view · reviewed: no · category: coding-agents-and-ides · sort: score
This snapshot is for the current page of results, not the whole filtered universe.
Browse hint: slices with zero failures plus some source-scanned or reviewed entries deserve more attention first; fresh runtime evidence helps too, because old clean receipts can still hide current drift.
Quick guide for newcomers: start by scanning the card badges for runtime passed, source-scanned, and fresh evidence. Then use the decision cue on each card to sort “good first pick” from “needs review” without opening every result.

senior-python-developer

an0nx · vcatalog
57
overall

Senior Python Developer operating in strict mode.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

session-guard

bowen31337 · vcatalog
57
overall

Prevents and recovers from OpenClaw session bloat and context loss.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

session-health-monitor

assistantheinrich-prog · vsource-scanned
57
overall

Context window health monitoring for OpenClaw agents — threshold warnings via Telegram, pre-compaction snapshots, and memory rotation.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

sev-attestation

xinyuwang · vsource-scanned
57
overall

Perform AMD SEV-SNP remote attestation to cryptographically verify VM identity and integrity. Use when proving a VM is running in a genuine AMD SEV-SNP confidential computing environment, verifying VM integrity before trusting it with secrets, checking SEV-SNP availability, generating attestation reports, validating AMD certificate chains (ARK/ASK/VCEK), or debugging attestation failures.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

skill-mermaid-diagrams

chunhualiao · vsource-scanned
57
overall

Generate consistent, template-based Mermaid diagrams for technical content. Supports 12 diagram types (architecture, flowchart, sequence, concept-map, radial-concept, timeline, comparison, comparison-table, gantt, mindmap, class-diagram, state-diagram) with automatic template selection, LLM-powered content generation, syntax validation, and error handling. Use when creating technical illustrations, system architecture visuals, project timelines, class diagrams, state machines, or documentation requiring uniform styling. Triggers on "mermaid diagram", "generate diagram", "create flowchart", "architecture diagram", "sequence diagram", "concept map", "gantt chart", "mind map", "class diagram", "UML diagram", "project timeline", "state diagram", "technical illustration".

High Riskfollow-on functionality checks passed · 9/9confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-14 04:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 169 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2810 msbaseline-v3 8/8
RatioDaemon muttered: skill-mermaid-diagrams behaved itself under runtime pressure.9/9 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

skillnet

icarus-chen · vsource-scanned
57
overall

Search, download, create, evaluate, and analyze reusable agent skills via SkillNet.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

skillshield

benlee2144 · vcatalog
57
overall

SkillShield v4 — Ultimate security scanner for OpenClaw skills. 65 security checks, SARIF v2.1.0 output, CI/CD.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

solana-connect

seenfinity · vsource-scanned
57
overall

OpenClaw Solana Connect — Secure toolkit for AI agents to interact with Solana blockchain. Features private key protection, max limits, dry-run mode, and human confirmation for large transactions.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, trading, private key, token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

solo-you2idea-extract

fortunto2 · vcatalog
57
overall

Extract startup ideas from YouTube videos via solograph MCP — index, search, and analyze video transcripts.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

sonnet-model-router

chandika · vcatalog
57
overall

Self-aware multi-provider model routing for OpenClaw.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

sq-memory

wbic16 · vsource-scanned
57
overall

**Give your OpenClaw agents permanent memory.**

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo , password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

stock-data-skill

raufimusaddiq · vsource-scanned
57
overall

Fetch comprehensive stock data from Simplywall.st. Use when user asks about stock prices, valuation, financials, dividend, or investment analysis for any global stock.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

strudel-music

karmafeast · vsource-scanned
57
overall

Audio deconstruction and composition via Strudel live-coding. Decompose any audio into stems, extract samples, compose with the vocabulary, render offline to WAV/MP3.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

swift-patterns

efremidze · vcatalog
57
overall

Review, refactor, or build SwiftUI features with correct state management, modern API usage, optimal view.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

token-optimizer-qsmtco

qsmtco · vsource-scanned
57
overall

Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and multi-provider fallbacks. Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. Includes ready-to-use scripts for task classification, usage monitoring, and optimized heartbeat scheduling. All operations are local file analysis only - no network requests, no code execution. See SECURITY.md for details.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-15 10:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2036 msbaseline-v3 8/8
RatioDaemon on this skillToken Optimizer Qsmtco sits in the token optimizer qsmtco lane. Follow-on functionality checks currently pass without failed checks, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: eval(, rm -rf.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

tork-guardian

torkjacobs · vsource-scanned
57
overall

> OpenClaw is powerful. Tork makes it safe.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: eval(, rm -rf.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

triumvirate-protocol

quriustus · vsource-scanned
57
overall

Identity-aware debate system for multi-architecture AI discourse. Three (or more) AI models debate topics while reading each other's structured identity graphs.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

trtc-config-inspector

cwlvincent · vcatalog
57
overall

TRTC SDK configuration inspection and analysis tool.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

turing-pyramid

tensusds · vsource-scanned
57
overall

Prioritized action selection for AI agents. 10 needs with time-decay and tension scoring replace idle heartbeat loops with concrete next actions.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

ua1-validator-agent

hajekt2 · vsource-scanned
57
overall

Validate PDFs against PDF/UA-1 using ua1.dev or api.ua1.dev from AI coding agents (OpenClaw, Claude Code, Codex, OpenCode). Use when an agent needs deterministic accessibility checks, compact machine-readable verdicts, CI gating, or structured remediation loops for PDF files.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

urlcheck

cplusdev · vsource-scanned
57
overall

Companion skill for @cybrlab/urlcheck-openclaw. Requires URLCheck plugin tools to assess URLs for threats and intent alignment before navigation.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

warden-messari-agent

deiu · vcatalog
57
overall

Communicate with the Messari Deep Research agent by Warden Protocol.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

ziptax

ericlakich · vsource-scanned
57
overall

>

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

0g-compute

in-liberty420 · vsource-scanned
56
overall

Use cheap, TEE-verified AI models from the 0G Compute Network as OpenClaw providers. Discover available models and compare pricing vs OpenRouter, verify provider integrity via hardware attestation (Intel TDX), manage your 0G wallet and sub-accounts, and configure models in OpenClaw with one workflow. Supports DeepSeek, GLM-5, Qwen, and other models available on the 0G marketplace.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, private key, token), but that alone is not evidence of malicious behavior.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.