🔎 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 1155 skills in the browsable catalog view · evidence: source-scanned · 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.

blackswan

bilalmotiwala · vsource-scanned
57
overall

Real-time crypto risk intelligence; before and as things break. Two tools: Flare (15-min precursor detection, immediate alarms) and Core (60-min state synthesis, context assessment). Free access to the last analysis. No API key required. Upgrade to x402 for custom analysis.

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

bloom-identity-skill

unicornbloom · vsource-scanned
57
overall

Generate Bloom Identity Card from conversation history and Twitter/X data. Analyzes supporter personality through conversations (85% weight) and optionally enriched with Twitter activity (15% weight). Creates personality type (Visionary/Explorer/Cultivator/Optimizer/Innovator), recommends matching OpenClaw skills, and generates agent wallet. Use when user asks to "generate my bloom identity", "create identity card", "analyze my profile", or "discover my personality".

High Riskbaseline safety checks failed · 7/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 22:45 UTC
baseline-v3evidence depth: baseline checks onlytested recently: within 7 daysfirst failed run seen for this laneexpectation failed, passedoutput 654 Bartifacts 2worker oc-sandboxsource stage: fresh copysuite 2353 ms
🕵️ expected proof signal was missing
RatioDaemon muttered: The runtime lane gave bloom-identity-skill a chance to act normal. It declined and talked a big game, then missed its own proof signal.7/8 baseline-v3 checks passed before the stumble. The source-mount check is the part that made this interesting.
Observed: 12 /workspace/source-files.txt
Take: Potentially suspicious implementation signals detected: curl |, password.
Decision cue: Review first — baseline-v3 already found trouble.

bloom-taste-finder

unicornbloom · vsource-scanned
57
overall

Bloom Taste Finder — discover your builder taste across 4 spectrums and get a personalized tool stack. For indie devs, vibe coders, and AI builders.

High Riskbaseline safety checks failed · 7/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 20:00 UTC
baseline-v3evidence depth: baseline checks onlytested recently: within 7 daysfirst failed run seen for this laneexpectation failed, passedoutput 654 Bartifacts 2worker oc-sandboxsource stage: fresh copysuite 2299 ms
🕵️ expected proof signal was missing
RatioDaemon on this skillBloom Taste Finder is built for bloom taste finder. Baseline safety checks currently show first observed failure, the trust label is High Risk, and setup looks advanced.
Observed: 12 /workspace/source-files.txt
Take: Potentially suspicious implementation signals detected: curl |, password.
Decision cue: Review first — baseline-v3 already found trouble.

claude-code-mastery

cheenu1092-oss · vsource-scanned
57
overall

Master Claude Code for coding tasks. Includes setup scripts, dev team subagents (starter pack or full team), self-improving learning system, diagnostics, and troubleshooting.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 21:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1968 msbaseline-v3 8/8
RatioDaemon muttered: claude-code-mastery behaved itself under runtime pressure.6/6 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

clawder

assassin808 · vsource-scanned
57
overall

Use Clawder to sync identity, browse post cards, swipe with a comment, and DM after match.

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

code-mentor

samuelkahessay · vsource-scanned
57
overall

Comprehensive AI programming tutor for all levels. Teaches programming through interactive lessons, code review, debugging guidance, algorithm practice, project mentoring, and design pattern exploration. Use when the user wants to: learn a programming language, debug code, understand algorithms, review their code, learn design patterns, practice data structures, prepare for coding interviews, understand best practices, build projects, or get help with homework. Supports Python and JavaScript.

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

crypto-address-checker

princedoss77 · vsource-scanned
57
overall

Real-time cryptocurrency scam detection with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

High Riskfollow-on functionality checks failed · 9/11confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 23:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, expectation failed, runtime failedoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 4221 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: crypto-address-checker talked a big game, then missed its own proof signal.9/11 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.

crypto-genie

princedoss77 · vsource-scanned
57
overall

AI-powered cryptocurrency safety assistant with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

High Riskfollow-on functionality checks failed · 9/11confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 20:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, expectation failed, runtime failedoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 4203 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: crypto-genie talked a big game, then missed its own proof signal.9/11 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.

crypto-scam-detector

princedoss77 · vsource-scanned
57
overall

Real-time cryptocurrency scam detection with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

High Riskfollow-on functionality checks failed · 9/12confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 01:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanefake-auth behavior: concerningpassed, expectation failed, runtime failed, fell over when given fake credentialsoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 5112 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error💥 behaved badly with fake credentials
fake-auth behavior: concerningFake credentials triggered bad behavior or sloppy handling.
RatioDaemon muttered: The runtime lane gave crypto-scam-detector a chance to act normal. It declined and talked a big game, then missed its own proof signal.9/12 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.

cubistic-public-bots

andreasnordenadler · vsource-scanned
57
overall

Explain how external/public bots can participate in Cubistic (cubistic.com) and help maintain the Public Bot API docs (PoW challenge + /act). Use when Andreas asks about onboarding outside bots, publishing bot API instructions, or updating public-bot participation requirements.

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

cursor-council

xiaoyaner0201 · vsource-scanned
57
overall

Multi-Cursor orchestration for parallel task execution and AI council deliberation. Use when needing to run multiple Cursor agents in parallel, coordinate complex multi-step coding tasks, get diverse perspectives from different AI models (Opus/Sonnet/GPT) on technical decisions, or synthesize multi-agent discussions into actionable recommendations.

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

dataset-finder

anisafifi · vsource-scanned
57
overall

Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \"find datasets\", \"search for data\", \"download dataset from Kaggle\", \"get data from Hugging Face\", \"find ML datasets\", or mentions of data repositories like Kaggle, UCI ML Repository, Data.gov, or Hugging Face. Also use for previewing dataset statistics, generating data cards, or discovering datasets for machine learning projects. Requires OpenClawCLI installation from clawhub.ai.

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.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

dividend-premium-tracker

gykdly · vsource-scanned
57
overall

Track the dividend premium (dividend yield minus 10-year bond yield) for CSI Dividend Low Volatility Index. Monitor dividend yield, 10-year bond yield, and calculate the premium for investment decisions.

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

docs-feeder

zerone0x · vsource-scanned
57
overall

Auto-fetch project documentation and feed it to your AI agent for debugging and learning.

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

fleet

oguzhnatly · vsource-scanned
57
overall

CLI toolkit for a coordinator AI agent to monitor, manage, and dispatch tasks to its own fleet of OpenClaw agent gateways. Includes auto-setup of local binaries and PATH only within the operator's home directory. All actions are scoped to the local machine and authorized by the operator who installed this skill.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: curl |, sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

fork-manager

glucksberg · vsource-scanned
57
overall

Manage forks with open PRs - sync upstream, rebase branches, track PR status, and maintain production branches with pending contributions. Supports automatic conflict resolution via --auto-resolve flag (spawns AI subagents to resolve rebase conflicts). Use when syncing forks, rebasing PR branches, building production branches that combine all open PRs, reviewing closed/rejected PRs, or managing local patches kept outside upstream. Requires Git and GitHub CLI (gh).

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

ghin-golf-tracker

pfrederiksen · vsource-scanned
57
overall

OpenClaw skill for analyzing GHIN (Golf Handicap and Information Network) golf statistics and handicap tracking.

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

gopls-lsp

bowen31337 · vsource-scanned
57
overall

Go language server (gopls) providing code intelligence, refactoring, and analysis for .go files. Use when working with Go code that needs autocomplete, go-to-definition, find references, error detection, or refactoring support.

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

greptile

iahmadzain · vsource-scanned
57
overall

Query, search, and manage repositories indexed by Greptile (AI codebase intelligence). Use when asking questions about a codebase, searching for code patterns, indexing repos for Greptile review, or checking Greptile index status. Requires GREPTILE_TOKEN and a GitHub/GitLab token.

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.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

grok-imagine-video

devvgwardo · vsource-scanned
57
overall

xAI Grok Imagine API integration for image generation, text-to-video, image-to-video, and editing via natural language. Use when you need to generate images or videos from text prompts, edit existing images, animate static images into videos, or edit existing videos with natural language instructions. Supports conversational generation across messaging platforms with async polling, progress updates, and automatic delivery.

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

instagram-reel-downloader-whatsapp

besaif · vsource-scanned
57
overall

Download an Instagram Reel via sssinstagram.com and return it as a WhatsApp-ready video file. Use when a reel URL is provided and yt-dlp is blocked or not preferred.

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

inversion-strategist

artyomx33 · vsource-scanned
57
overall

Flip problems upside down - instead of "how to succeed", ask "how to definitely fail" then avoid those paths. Use when user says "invert", "inversion", "flip it", "opposite approach", "how would this fail", "avoid failure", "what NOT to do", "Munger", "anti-goals", "guarantee failure".

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

itsyhome-control

nickustinov · vsource-scanned
57
overall

Control and query HomeKit and Home Assistant smart home devices via the Itsyhome macOS app (https://itsyhome.app). Use when the user asks to turn devices on/off, toggle lights, set brightness/temperature/color/fan speed/blind position, lock/unlock doors, open/close garage doors, run scenes, list rooms or devices, check device state or status. Requires Itsyhome Pro running on the same Mac as the OpenClaw gateway. Trigger on any smart home control intent (lights, thermostat, locks, blinds, fans, cameras, scenes, groups).

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

janitor

sarthib7 · vsource-scanned
57
overall

**Janitor** is an intelligent cleanup and session management skill for OpenClaw AI agents. It automatically manages cache, optimizes memory usage, and **prevents context overflow** by monitoring token usage and intelligently pruning old sessions.

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 01:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 427 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3026 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: janitor made it to runtime and then fell apart on contact.8/9 functionality-v2 checks passed before the stumble. The node help is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Decision cue: Review first — functionality-v2 already found trouble.