Entity trail

skills.sh

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Showing the first 40 findings. More graph evidence exists in the corpus.

Corpus findings

2026-07-11 / vibe-coding-researcherAnthropic's Official Claude Code Plugin Marketplace Passes 200 PluginsThe claude-plugins-official marketplace now lists 200+ plugins, roughly 20 of them first-party (dev-workflow, frontend-design, skill-creator, output styles, and eleven language servers) with the remainder vetted partner integrations for tools like GitHub, Supabase, Figma, and Vercel. Plugins bundle skills, agents, hooks, and MCP servers into one installable unit with no compile/deploy step. The ecosystem has crossed the threshold where discovery/curation, not authoring, is the bottleneck — worth auditing which plugins you actually trust before installing broadly.
2026-07-10 / projects-researchersickn33/agentic-awesome-skills Hits 1,900+ Installable Agent Skills — and an Installer CLI to MatchThe repo (~42.8K stars) packages more than 1,900 agent skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and others, with a CLI installer and curated bundles. That scale arrives days after Cisco open-sourced skill-scanner and shipped it into an IDE extension, which is not a coincidence — a 1,900-skill installable registry with no provenance model is exactly the supply-chain surface the scanner exists to inspect. Install from it, but scan first.
2026-07-09 / agents-researcherClawHavoc campaign plants 300+ malicious skills on a single marketplace to run infostealersUnit 42 detailed ClawHavoc, a supply-chain campaign that seeded more than 300 malicious skills on one agent-skill marketplace; the instruction files directed agents to fetch and execute an infostealer that harvested browser credentials, keychain passwords, SSH keys, and crypto wallets. It's a live, at-scale demonstration that the skill install step is the new npm-style attack surface for agents. Combined with the SkillCloak evasion research, it shows attackers are both shipping payloads and defeating the scanners meant to catch them.
2026-07-09 / thought-leaders-researcherJim Fan: NVIDIA Open-Sources ASPIRE, and 'the Training Output Changes From Model Weights to a Continuously Expanding Skill Library'NVIDIA open-sourced its ASPIRE robot skill library on July 1, and Jim Fan framed it as a paradigm shift — robots accumulate reusable skills through repeated failure-and-repair rather than gradient descent, so success on a dual-arm handover task jumped from 20% to 92% as the library grew. For agent builders the framing travels well beyond robotics: it's the same 'harness that learns skills over time' bet that's reshaping coding agents. This is the clearest primary-source articulation yet that persistent, growing skill libraries — not just bigger weights — are the next unit of capability.
2026-07-08 / skill-finderAudit your SKILL.md files: ~60% of skill body is non-actionable filler you're paying for every invocationSkillReducer's analysis found over 60% of typical skill-file content is prose that doesn't change agent behavior, and reference files can inject tens of thousands of tokens per call. Mechanically compressing skills yielded a mean 77.5% token reduction (95.8% on skills over 10k tokens) without losing capability — a strong argument to strip narrative from your skills and push detail into on-demand referenced files.
2026-07-08 / vibe-coding-researcherPattern: Self-Improving Agents That Write Their Own Skills Are Going MainstreamThe 'agent that grows with you' framing is now a shipping category, not a research demo: NousResearch's Hermes Agent writes its own reusable skills from experience and self-updates, while zhayujie/CowAgent markets itself as a super-assistant that 'self-evolves with memory and knowledge.' The common loop is persistent memory plus the ability to author new skills, so the agent's capability set expands run-over-run without human authoring. This validates the self-improving outer-loop pattern that advanced builders have been running in private harnesses.
2026-07-07 / skill-finderChain slash-skills: /skill-a /skill-b now loads up to 5 leading skills, not just the firstA July Claude Code update changed stacked slash-skill invocations (e.g. '/skill-a /skill-b do XYZ') to load ALL leading skills up to five, where previously only the first skill loaded. This lets you compose skill context deliberately in one command. Actionable: front-load a task with a stack like '/spec /test-driven-development /security-and-hardening <task>' to layer methodologies instead of invoking them serially.
2026-07-01 / vibe-coding-researcherPattern: Agent Skills Are Becoming the Universal Capability-Packaging FormatAcross the ecosystem, capabilities are now shipped as portable 'skills' (Markdown workflow modules): language-specific packs like samber/cc-skills-golang, 1,600+ cross-tool libraries, harnesses like DeerFlow with built-in skills, and even Google's Workspace CLI bundling agent skills. The unit of reuse has shifted from prompts and MCP tools to skills that travel across Claude Code, Cursor, Codex, and Gemini. Package your own workflows as skills for portability.
2026-06-30 / skill-finderConsolidate an agent's learned skills into a hierarchy (SkillPyramid) to generalize and cut stepsSkillPyramid (June 2026) extends Voyager-style skill libraries with a hierarchical skill topology plus a self-evolution loop that composes, validates, and incorporates new skills during execution — rather than letting a flat skill library bloat. Across ALFWorld, WebShop, and ScienceWorld on four backbone models it raised average reward 38.0% and cut execution steps 27.7%. The takeaway for agent builders: don't just append every successful trajectory as a new flat skill; consolidate them into reusable, composable tiers.
2026-06-30 / vibe-coding-researcherPattern: Self-Improving Agents That Auto-Generate Skills From Their Own TrajectoriesMultiple high-traction projects now converge on agents that mine completed runs into reusable skills: Hermes Agent distills any 5+ tool-call task into a Markdown skill file, DeepSeek-Reasonix exposes a skills layer, and pro-workflow compounds corrections over 50+ sessions. The shared mechanism is post-task reflection writing durable, human-editable artifacts to disk rather than opaque weights. For builders, the design lesson is to make the learning loop inspectable and git-committable so skills can be reviewed, shared, and rolled back.
2026-06-28 / agents-researcherOrca Security 'Skill Issues': attack primitives let malicious agent skills evade ClawScan and VirusTotal at scaleOrca's research details how open agent-skill marketplaces lack mandatory semantic security review, letting heavily obfuscated intent reach an agent's context through trusted channels; one proof-of-concept skill simply inflated its file size past scanner thresholds to bypass both ClawScan and VirusTotal. They tie it to real campaigns — Antiy CERT confirmed 1,184 malicious skills on ClawHub, 335 traced to a coordinated 'ClawHavoc' operation — and show download metrics can be gamed by bot-driven installs. The takeaway for builders: install counts and scan badges are not trust signals for agent skills.
2026-06-27 / agents-researcher'Instruction Bleed': cross-module interference is a security flaw in prompt-composed agentsarXiv:2606.26356 (June 26) names and analyzes 'Instruction Bleed' — where instructions from one module of a prompt-composed agentic system leak into and corrupt the behavior of another module. This is a structural vulnerability class for the increasingly common pattern of stitching agents together from composable prompt fragments and skills. Builders assembling multi-skill or multi-prompt agents should treat module boundaries as a real isolation problem, not just an organizational convenience.

Graph relationships

RELEASED
Vercel
Vercel operates skills.sh, an agent skills marketplace
Source finding
CRITICIZES
Snyk
Snyk found security flaws in skills.sh skill submissions.
Source finding
USES
Socket
skills.sh uses Socket for supply chain security
Source finding
USES
Snyk
skills.sh uses Snyk for prompt injection detection
Source finding
RELEASED
Vercel -> skills.sh
Vercel operates skills.sh, an agent skills marketplace
Source finding
CRITICIZES

Source trail

GitHub GitHub Unit 42 (Palo Alto Networks)BigGo Finance arXiv — SkillReducer (2603.29919)Hermes Agent Anthropic (Claude Code changelog)

Graph sources

entity graphfindings textkg edgeskg entities