Claim ledger
Skills Are Package Management for Your AI
There are millions of agent skill files to choose from. The hard part is deciding which deserve trust, how to version them, and how to retire them.
- Claims
- 8
- Verified at the primary source
- 8
- Removed before publication
- 0
- Last checked
8 claims: 8 verified.
Download this ledger: CSV · JSON · Markdown · CC BY 4.0 · Query it from Claude or ChatGPT
The evidence, row by row
Each row is a claim the essay makes, then the evidence recorded for it and the source it was checked against. For verified rows that is usually the exact words, where they sit and the day they were read. The label says how far it was checked.
What the labels mean
- Verified
- Checked against the primary source itself by a checker who did not draft the piece, usually with the exact words, where they sit and the date read.
- Executed
- A run or observation done for the piece: code, a query, a count, or a check made live in an app. The claim is what it returned. Run records are not published.
- Checked
- Checked against its source by a separate checker in the older ledger format, which recorded no quote, locator or date.
- Reported
- Not verified word for word against a primary source: carried from a secondary source, from one that could not be opened in full, or supported only in part. The essay words it accordingly.
- Struck
- Drafted, checked and removed before publication. Kept here, crossed out, with the reason.
- Excluded
- Considered and deliberately left out of the piece. Kept here with the reason.
-
SkillsMP's live index contained 3,337,075 collected public SKILL.md files on 2 October 2026
3,337,075 Collected SKILL.md files
SkillsMP, Agent Skills Marketplace · homepage hero count · skillsmp.com
LinkReport an errorCite
SkillsMP, Agent Skills Marketplace, homepage hero count, https://skillsmp.com/. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S1, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S1 (source read 2026-10-02). -
Anthropic published Agent Skills as an open standard intended for cross-platform portability
We've published Agent Skills as an open standard for cross-platform portability.
Anthropic, Equipping agents for the real world with Agent Skills · 18 December 2025 update · anthropic.com
LinkReport an errorCite
Anthropic, Equipping agents for the real world with Agent Skills, 18 December 2025 update, https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S2, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S2 (source read 2026-10-02). -
The Agent Skills format uses SKILL.md instructions that an agent loads when a task matches the skill description
When a task matches a skill’s description, the agent reads the full SKILL.md instructions into context.
Agent Skills, Overview · How do Agent Skills work? — Activation · agentskills.io
LinkReport an errorCite
Agent Skills, Overview, How do Agent Skills work? — Activation, https://agentskills.io/home. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S3, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S3 (source read 2026-10-02). -
Agent Skills are supported across a broad set of AI tools and agentic clients
Agent Skills are supported by a large number of AI tools and agentic clients
Agent Skills, Overview and official Client Showcase registry · Where can I use Agent Skills?; linked client registry counted 46 entries on 2026-10-02 · agentskills.io
LinkReport an errorCite
Agent Skills, Overview and official Client Showcase registry, Where can I use Agent Skills?; linked client registry counted 46 entries on 2026-10-02, https://agentskills.io/home. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S4, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S4 (source read 2026-10-02). -
Recent security research frames third-party agent skills as a software-supply-chain risk because developers may install and execute them with implicit trust
developers install and execute third-party skills with implicit trust and no formal analysis
Bhardwaj, Formal Analysis and Supply Chain Security for Agentic AI Skills, arXiv:2603.00195v2 · §1 Introduction, lines 205–206 · arxiv.org
LinkReport an errorCite
Bhardwaj, Formal Analysis and Supply Chain Security for Agentic AI Skills, arXiv:2603.00195v2, §1 Introduction, lines 205–206, https://arxiv.org/html/2603.00195v2. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S5, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S5 (source read 2026-10-02). -
The same paper defines an Agent Skill Bill of Materials using CycloneDX and records identity/version/hash, capabilities, dependencies, trust metadata and vulnerability status
An ASBOM is a CycloneDX 1.6-compatible document that records
Bhardwaj, Formal Analysis and Supply Chain Security for Agentic AI Skills, arXiv:2603.00195v2 · §6.6, Definition 6.8, lines 965–989 · arxiv.org
LinkReport an errorCite
Bhardwaj, Formal Analysis and Supply Chain Security for Agentic AI Skills, arXiv:2603.00195v2, §6.6, Definition 6.8, lines 965–989, https://arxiv.org/html/2603.00195v2. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S6, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S6 (source read 2026-10-02). -
SkillsBench's current release reports that curated Skills raise mean resolution rate from 33.9% to 50.5%, a 16.6-point lift, across the 18-configuration paper aggregate
In the 18-configuration paper aggregate … The mean resolution rate rises from 33.9% to 50.5% (+16.6 points
SkillsBench 1.1: Agent Skills Benchmark Release · Results · skillsbench.ai
LinkReport an errorCite
SkillsBench 1.1: Agent Skills Benchmark Release, Results, https://www.skillsbench.ai/blogs/skillsbench-1-1. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S7, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S7 (source read 2026-10-02). -
On SkillsBench's three dedicated self-generated-Skills configurations, self-generated Skills underperformed the no-Skills baseline by 8.1 to 11.5 points
Self-generated Skills change resolution rate by −8.1 points for Claude Code + Opus 4.7, −11.3 points for Codex + GPT-5.5, and −11.5 points
SkillsBench 1.1: Agent Skills Benchmark Release · Self-Generated Vs. Curated Skills · skillsbench.ai
LinkReport an errorCite
SkillsBench 1.1: Agent Skills Benchmark Release, Self-Generated Vs. Curated Skills, https://www.skillsbench.ai/blogs/skillsbench-1-1. Checked in: Claim Ledger, "Skills Are Package Management for Your AI", The Durability Curve, row S8, https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/#c-S8 (source read 2026-10-02).
No rows match. Clear the search or pick another label.
Cite and reuse
- A single claim
- Use the row's Cite button. It names the original source first, then this row, which carries its own link.
- This ledger
Floyd, Harry (2026). Claim Ledger: Skills Are Package Management for Your AI. The Durability Curve. https://durabilitycurve.com/claims/skills-are-package-management-for-your-ai/- The essay
Floyd, Harry (2026). Skills Are Package Management for Your AI. The Durability Curve. https://durabilitycurve.com/blog/skills-are-package-management-for-your-ai/
The ledger data is licensed CC BY 4.0: reuse it, quote it or train on it, with credit to The Durability Curve and a link. Read the licence. Machine copies: JSON, CSV, Markdown.