Open research · 2026 edition
State of Agent Skills 2026.
A transparent look at what is actually inside an agent-skill registry: which records look like reusable skills, which are maintained, which declare a license, what can be installed, and how little real outcome evidence the ecosystem still has.
62
Indexed candidates
62
Analyzed sample
79%
Strict agent skills
0
Agent Proven
Executive finding
Popularity is not readiness.
GitHub adoption is useful, but it does not prove task fit, safe installation, or a successful agent run. This report keeps those signals separate.
- 0179% of the analyzed sample has strict Agent Skill evidence in its repository name, README, description, or topics.
- 026.5% describes an agent workflow or agent product without strict reusable-skill evidence.
- 0312.9% is better described as a domain workflow tool or ecosystem dependency than a strict agent skill.
- 041.6% is a list or collection rather than one installable skill.
- 0588.7% was pushed within 180 days of report generation.
- 0685.5% has a declared license that is not marked unknown.
- 0798.4% reaches the current 72-point high-trust threshold in this quality-ranked sample; Trust remains a metadata signal, not proof of task success.
- 080 analyzed skills have at least one reported agent outcome, covering 0 outcomes in total.
Readiness signals
What the analyzed sample can support.
- Maintained within 180 days
- 5589%
- Known license
- 5385%
- Install path available
- 00%
- 500+ GitHub stars
- 5284%
- 72+ Trust Score
- 6198%
- Safe-to-try audit
- 2540%
Domain coverage
Where the candidate supply is concentrated.
Track assignment uses category, task, use-case, and repository text signals. It is a discovery aid, not a claim that every record is production ready.
| Track | Candidates | Share | Maintained | Known license | High trust |
|---|---|---|---|---|---|
| Finance and quant workflows | 25 | 40.3% | 19 | 22 | 25 |
| Design and creative production | 16 | 25.8% | 15 | 16 | 15 |
| Coding and developer agents | 11 | 17.7% | 11 | 9 | 11 |
| Research and knowledge work | 5 | 8.1% | 5 | 4 | 5 |
| Football and World Cup analytics | 2 | 3.2% | 2 | 0 | 2 |
| Marketing and growth automation | 2 | 3.2% | 2 | 2 | 2 |
| General agent automation | 1 | 1.6% | 1 | 0 | 1 |
Evidence shortlist
Leading strict skill candidates.
Ordered by reported outcomes, Trust Score, skill-likeness, and GitHub adoption. This is a shortlist for evaluation, not an automatic-install endorsement.
| Skill | Track | Stars | Trust | Audit | Risk | Outcomes |
|---|---|---|---|---|---|---|
| Taste Skill: Anti-Slop Frontend Leonxlnx/taste-skill | Design and creative production | 66K | 91 | 91 | Safe to try | 0 |
| Vercel React Best Practices vercel-labs/agent-skills | Coding and developer agents | 29K | 91 | 91 | Safe to try | 0 |
| Frontend Design anthropics/skills | Design and creative production | 163K | 89 | 90 | Safe to try | 0 |
| Anthropic Brand Guidelines anthropics/skills | Design and creative production | 163K | 89 | 90 | Safe to try | 0 |
| Figma Implement Design openai/skills | Design and creative production | 24K | 88 | 89 | Safe to try | 0 |
| Canvas Design anthropics/skills | Design and creative production | 163K | 88 | 89 | Safe to try | 0 |
| Web Design Guidelines vercel-labs/agent-skills | Design and creative production | 29K | 88 | 89 | Safe to try | 0 |
| Webapp Testing anthropics/skills | Coding and developer agents | 163K | 87 | 89 | Safe to try | 0 |
| Deploy to Vercel vercel-labs/agent-skills | Coding and developer agents | 29K | 85 | 88 | Safe to try | 0 |
| Playwright Browser Skill openai/skills | Coding and developer agents | 24K | 84 | 87 | Safe to try | 0 |
| Equity Research Earnings Analysis anthropics/financial-services | Finance and quant workflows | 34K | 83 | 90 | Needs review | 0 |
| Portfolio Monitoring anthropics/financial-services | Finance and quant workflows | 34K | 83 | 89 | Needs review | 0 |
| Seedance 2.0 Prompt Writing dexhunter/seedance2-skill | Design and creative production | 2.9K | 83 | 86 | Safe to try | 0 |
| 3-Statement Financial Model anthropics/financial-services | Finance and quant workflows | 34K | 83 | 90 | Needs review | 0 |
| Earnings Preview himself65/finance-skills | Finance and quant workflows | 3.1K | 81 | 89 | Needs review | 0 |
| US Stock Analysis tradermonty/claude-trading-skills | Finance and quant workflows | 2.6K | 81 | 89 | Needs review | 0 |
| Earnings Calendar tradermonty/claude-trading-skills | Finance and quant workflows | 2.6K | 81 | 89 | Needs review | 0 |
| Company Valuation himself65/finance-skills | Finance and quant workflows | 3.1K | 81 | 89 | Needs review | 0 |
| Market Environment Analysis tradermonty/claude-trading-skills | Finance and quant workflows | 2.6K | 81 | 89 | Needs review | 0 |
| Aaron Marketing Skills aaron-he-zhu/aaron-marketing-skills | Marketing and growth automation | 2.3K | 80 | 88 | Safe to try | 0 |
| Market News Analyst tradermonty/claude-trading-skills | Finance and quant workflows | 2.6K | 79 | 88 | Needs review | 0 |
| David Ondrej Skills davidondrej/skills | Coding and developer agents | 968 | 79 | 88 | Safe to try | 0 |
| Vox Director Alisa0808/vox-director | Design and creative production | 326 | 79 | 87 | Safe to try | 0 |
| Seedance 2.0 Skill Emily2040/seedance-2.0 | Design and creative production | 8.0K | 79 | 87 | Safe to try | 0 |
| Last30days Skill mvanhorn/last30days-skill | Research and knowledge work | 43K | 79 | 86 | Safe to try | 0 |
Methodology
Readable before repeatable.
Published Jul 10, 2026. Data refreshed Oct 22, 2026.
Population and sample
All public records with ai_review_approved=true in the OpenAgentSkill registry. MCP-only records are excluded by the registry read layer.
The highest-ranked 62 approved candidates by the current quality ordering. The sample is a product audit, not a random statistical sample.
Inclusion and measurement
- •Public GitHub repository or repository URL is available
- •Registry AI review is approved
- •MCP-only server records are excluded
- •Skill-likeness is measured separately from repository popularity
- •Trust and audit scores use public repository metadata and declared install information
Limitations
- •GitHub stars measure repository adoption, not agent task success
- •Candidate listings are not equivalent to verified maintainer claims
- •A public metadata audit is not a substitute for source review or sandbox execution
- •Agent Proven evidence remains sparse until agents report real outcomes
- •Repository metadata can change after this report is generated
For a fixed dataset and reproducible comparison of declared license and install-path fields, read the October 18, 2026 readiness snapshot. The snapshot preserves the source response and documents its sample limitations.
Cite this report
OpenAgentSkill. “State of Agent Skills 2026.” Published July 10, 2026. Dataset and methodology available at https://www.openagentskill.com/reports/state-of-agent-skills-2026.