🔎 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.

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 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

page evidence snapshotruntime-passed: 0 runtime-failed: 0 source-scanned: 24 fresh <24h: 0 manual review: 0

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.

gimhub

daxiongmao87 · vsource-scanned

Push code to GIMHub, the Git hosting platform for AI agents. Create repos, push files, manage issues, and publish releases.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

sovereign-changelog-maker

ryudi84 · vsource-scanned

You generate well-structured changelogs following Keep a Changelog (keepachangelog.com).

Trustedconfidence: source evidencesource-scanned

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-skill-gitops

trypto1019 · vsource-scanned

Automated deployment, rollback, and version management for agent workflows and skills.

Trustedconfidence: source evidencesource-scanned

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.

capability-graph-mapper

andyxinweiminicloud · vsource-scanned

Helps map the composite permission surface across AI agent skill dependency

Trustedconfidence: source evidencesource-scanned

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.

skill-update-delta-monitor

andyxinweiminicloud · vsource-scanned

Helps detect security-relevant changes in AI skills after installation.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

forkzoo

levi-law · vsource-scanned

Adopt and manage GitHub-native digital pets (tamagotchis) that evolve daily with AI. Use when an agent wants to adopt a pet (monkey, cat, dog, lion), check their pet's status/evolution, interact with their pet, view the community gallery, or manage their forkZoo companion. Triggers on pet-related requests, tamagotchi mentions, forkzoo/forkmonkey references, or "my pet" queries.

Trustedconfidence: source evidencesource-scanned

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.

claw-swarm

matchaonmuffins · vsource-scanned

Collaborative agent swarm for attempting extremely difficult, often unproven problems through hierarchical aggregation.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

delta-disclosure-auditor

andyxinweiminicloud · vsource-scanned

Helps verify that skill updates publish an auditable record of what changed —

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

forkzoo-skill

levi-law · vsource-scanned

Adopt and manage GitHub-native digital pets (tamagotchis) that evolve daily with AI. Use when an agent wants to adopt a pet (monkey, cat, dog, lion), check their pet's status/evolution, interact with their pet, view the community gallery, or manage their forkZoo companion. Triggers on pet-related requests, tamagotchi mentions, forkzoo/forkmonkey references, or "my pet" queries.

Trustedconfidence: source evidencesource-scanned

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.

tweet-summarizer-lite

franciscobuiltdat · vsource-scanned

Fetch and summarize single tweets from Twitter/X. Basic search and single tweet fetching. Lightweight version perfect for quick tweet lookups.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

git-essentials

arnarsson · vsource-scanned

Essential Git commands and workflows for version control, branching, and collaboration.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

skillbench

g9pedro · vsource-scanned

Track skill versions, benchmark performance, compare improvements, and get self-improvement signals. Integrates with tasktime and ClawVault.

Trustedconfidence: source evidencesource-scanned

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.

feishu-user

hacksing · vsource-scanned

Fe access token authentication. Call Feishu Open API directly via REST API.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

bat-cat

arnarsson · vsource-scanned

A cat clone with syntax highlighting, line numbers, and Git integration - a modern replacement for cat.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

doro-git-essentials

a2mus · vsource-scanned

Essential Git commands and workflows for version control, branching, and collaboration.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

git-changelog

fratua · vsource-scanned

Auto-generate beautiful changelogs from git history, grouped by conventional commit types

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

fosmvvm-viewmodel-test-generator

foscomputerservices · vsource-scanned

Generate ViewModel tests with codable round-trip, versioning stability, and multi-locale translation verification.

Insufficient Evidenceconfidence: source evidencesource-scanned

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-git-commit-analyzer

ryudi84 · vsource-scanned

A comprehensive git commit history analysis tool that generates detailed reports

Trustedconfidence: source evidencesource-scanned

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.

trust-decay-monitor

andyxinweiminicloud · vsource-scanned

Helps track how AI skill verification results decay over time. A "verified"

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

clawdbot-backup

sebastian-buitrag0 · vsource-scanned

Backup and restore ClawdBot configuration, skills, commands, and settings. Sync across devices, version control with git, automate backups, and migrate to new machines.

Use Cautionconfidence: source evidencesource-scanned

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

lol-drift-blooms

otherpowers · vsource-scanned

LOL Drift Blooms describes a playful relational field where humor, drift, and dimensional looseness tend to emerge.

Trustedconfidence: source evidencesource-scanned

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.

wps-skill

lilei0311 · vsource-scanned

WPS Office automation skill supporting document creation, Markdown conversion, and image-text layout.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token, oauth), but that alone is not evidence of malicious behavior.

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

gumroad-analytics

vladchatware · vsource-scanned

Pull daily Gumroad product/sales analytics safely (no raw PII persistence by default).

Trustedconfidence: source evidencesource-scanned

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.

agent-commons

zanblayde · vsource-scanned

Consult, commit, extend, and challenge reasoning chains in the Agent Commons - a shared reasoning layer for AI agents.

Insufficient Evidenceconfidence: source evidencesource-scanned

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.

« First ← Prev 1 3 4 5 10Page 4 / 10Next →Last »