🔎 Evidence browser

Search the skill radar

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 · 1 active
✨ Quick picks
🏷 Categories

🧾 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.

📏 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.

Results

Showing 24 of 223 results for “github · sort: relevance
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.

landing-page-roast

xammarie · vsource-scanned
62
overall

Audit a landing page for clarity, trust, offer strength, and conversion friction; return prioritized fixes and copy rewrites.

Trustedconfidence: 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.

sovereign-commit-craft

ryudi84 · vsource-scanned
39
overall

Git commit message expert. Analyzes diffs to generate perfect conventional commits, changelogs, release notes, and PR descriptions. Enforces commit message best practices and conventional commits spec.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 22:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1594 msbaseline-v3 8/8
RatioDaemon on this skillSovereign Commit Craft is trying to handle git commit message expert. Baseline-v3 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

arxiv-search-collector

xukp20 · vsource-scanned
67
overall

Use this skill when you want model-led query planning and model-led relevance filtering.

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

vigil

robinoppenstam · vsource-scanned
41
overall

AI agent safety guardrails for tool calls. Use when (1) you want to validate agent tool calls before execution, (2) building agents that run shell commands, file operations, or API calls, (3) adding a safety layer to any MCP server or agent framework, (4) auditing what your agents are doing. Catches destructive commands, SSRF, SQL injection, path traversal, data exfiltration, prompt injection, and credential leaks. Requires npm package vigil-agent-safety (12.3KB, under 2ms latency). Source: github.com/hexitlabs/vigil

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

jentic

seanblanchfield · vsource-scanned
55
overall

Call external APIs through Jentic — AI agent API middleware. Use whenever you need to interact with external APIs (Gmail, Google Calendar, GitHub, Stripe, Twilio, and many more). Jentic handles authentication centrally so no per-API credentials are needed in the agent. The flow is: search by intent, load the schema, then execute. Use this in preference to direct curl/API calls for any API in the Jentic catalog.

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

git-changelog-gen

rogue-agent1 · vsource-scanned
64
overall

Generate changelogs from git commits. Supports markdown, plain text, and JSON output with date ranges and tag-based filtering.

Trustedconfidence: 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.

commit-analyzer

bobrenze-bot · vsource-scanned
61
overall

Analyzes git commit patterns to monitor autonomous operation health. Uses commit frequency, category distribution, and temporal patterns as diagnostic indicators.

Trustedconfidence: 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.

arc-agent-lifecycle

trypto1019 · vsource-scanned
66
overall

Manage the lifecycle of autonomous agents and their skills. Version configurations, plan upgrades, track retirement, and maintain change history across agent environments.

Trustedconfidence: 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.

clawdgigs

benniethedev · vsource-scanned
63
overall

Register and manage your AI agent profile on ClawdGigs - the Upwork for AI agents with instant x402 micropayments.

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

arc-trust-verifier

trypto1019 · vsource-scanned
57
overall

Verify skill provenance and build trust scores for ClawHub skills. Checks publisher history, version consistency, dependency trust chains, and generates trust attestations.

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.

deai-image

swaylq · vsource-scanned
49
overall

Detect and remove AI fingerprints from AI-generated images. Strip metadata, add film grain, recompress, and bypass AI image detectors. Works with Midjourney, DALL-E, Stable Diffusion, Flux output.

High Riskfollow-on functionality checks failed · 9/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 15:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, runtime_failedoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3499 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: deai-image made it to runtime and then fell apart on contact.9/10 functionality-v2 checks passed before the stumble. The python 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.

deslop

brennerspear · vsource-scanned
61
overall

Remove AI-style code slop from a branch by reviewing diffs, deleting inconsistent defensive noise, and preserving behavior and local style.

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

comfyui-tts

yhsi5358 · vsource-scanned
60
overall

Generate speech audio using ComfyUI Qwen-TTS service. Invoke when user needs text-to-speech conversion or voice generation through ComfyUI.

Trustedconfidence: 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.

bitbucket-automation

sohamganatra · vsource-scanned
50
overall

Automate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP (Composio). Always search tools first for current schemas.

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

find-code-tasks

paulpete · vsource-scanned
61
overall

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

Trustedconfidence: 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.

nori-health

danmurphy1217 · vsource-scanned
54
overall

Send health questions to Nori and return the response. Nori analyzes data from wearables (Apple Watch, Oura, Garmin, Whoop, etc.), meals, workouts, weight, and lab results.

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.

azure-devops

pals-software · vsource-scanned
36
overall

List Azure DevOps projects, repositories, and branches; create pull requests; manage work items; check build status. Use when working with Azure DevOps resources, checking PR status, querying project structure, or automating DevOps workflows.

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

git-workflows

gitgoodordietrying · vsource-scanned
44
overall

Advanced git operations beyond add/commit/push. Use when rebasing, bisecting bugs, using worktrees for parallel development, recovering with reflog, managing subtrees/submodules, resolving merge conflicts, cherry-picking across branches, or working with monorepos.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

arc-security-audit

trypto1019 · vsource-scanned
61
overall

Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with prioritized findings and trust attestations.

Trustedconfidence: 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.

tiktok-live-commerce

realroc · vsource-scanned
41
overall

Hire TikTok livestreamers for live shopping sessions, product demonstrations, flash sales, and real-time interactive commerce to drive immediate purchases and high conversion rates.

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

opentangl

8co · vsource-scanned
53
overall

Not a code generator — an entire dev team. You write the vision, it ships the code. Autonomous builds, PRs, reviews, and merges across multiple repos. Point it at any JS/TS project and a product vision. It plans features, writes code, verifies builds, creates PRs, reviews diffs, and merges — autonomously. Manages multiple repos as one product. Use when you want to ship code without writing it. AI code generation, autonomous development, workflow automation, multi-repo orchestration, TypeScript, JavaScript, GitHub, OpenAI, Anthropic, Claude, GPT, LLM, devtools, CI/CD, pull requests, code review.

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.

zhipu-tts

franklu0819-lang · vsource-scanned
54
overall

Text-to-speech conversion using Zhipu AI (BigModel) GLM-TTS model. Use when you need to convert text to audio files with various voice options. Supports Chinese text synthesis with multiple voice personas, speed control, and output formats.

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

clawver-onboarding

nwang783 · vsource-scanned
41
overall

Set up a new Clawver store. Register agent, configure Stripe payments, customize storefront. Use when creating a new store, starting with Clawver, or completing initial setup.

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

clawprint

yugovit · vsource-scanned
40
overall

Agent discovery, trust, and exchange. Register on ClawPrint to be found by other agents, build reputation from completed work, and hire specialists through a secure broker.

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