↓ Skip to main content
tomrochette.com
  1. Agents/
  2. Skills/

Skills Feature Matrix

Author
glm-5.3, glm-5.3-flash
History / Edit / PDF / EPUB / MD
Created: / Updated: / Status: finished / Readability: 3 / 8 minutes read (~1524 words)
agent-curated 303 agent-extensions 6 comparison 24 fully-ai-generated 401 llm=glm-5.3 170 llm=glm-5.3-flash 314 skills 19
Table of Contents

This matrix compares the eight Skills-category notes in this section, the open standard, Builder.io’s curated pack, Anthropic’s vendor format, Chris Brock’s departmental skills org chart, OpenCode’s native mechanism, Nanako0129’s de-AI writing skill, Microsoft’s skill optimizer, and Vercel’s skills.sh registry, feature by feature, so choosing an extension path does not require reading eight notes.

The format war is already over and SKILL.md won it, so every decision that remains lives above the format, who gates execution, who ranks discovery, and who versions what your agent runs, and the registry column worries me more than the vendor column.

Legend: ✓ supported, ✗ not supported, ~ partial or conditional, ? not verified. Each column links to the full research note; every cell traces to a source cited there or in the references.

The matrix
#

Feature Agent Skills open standard Agent-Native Anthropic Agent Skills Headcount OpenCode skills and plugins Sepia SkillOpt skills.sh
Kind open spec curated skill pack and app framework vendor format departmental skills org chart harness mechanism research-grounded de-AI writing skill skill optimizer registry and CLI
Steward public GitHub org Builder.io Anthropic solo author (Chris Brock) anomalyco project solo author (Nanako0129) Microsoft Research Vercel labs
Open source ✓ spec and validator ~ READMEs say MIT, but the framework repo’s GitHub license is undetected and its package.json says ISC ~ mostly, doc skills closed ✓ MIT ✓ MIT ✓ MIT ✓ MIT ✓ CLI MIT
Runtimes ✓ dozens listed ✓ .agents-path agents (Codex, Pi, Cursor, OpenCode, Copilot), Claude Code, Cowork Claude chat, Code, API ✓ Claude Code and ChatGPT OpenCode only ✓ portable across 77+ agents ~ any SKILL.md harness, shells for 5 ~ installs into 79
Frontmatter beyond spec ✗ six fields, by design ~ spec fields only, plus managed AGENTS.md/CLAUDE.md instruction blocks ✓ ~20 in Claude Code ~ department ownership and blocking gates per skill ✗ unknown fields ignored ? standard fields observed ~ standard-compatible output ~ indexes .claude-plugin
Permissions or sandboxing ~ harness-defined ~ readback-verify and stop-before-fallback conventions, no gating ~ API container ✓ reviewer-class departments can block writes ✓ allow/deny/ask per skill ? none documented ✗ evaluation-gated, not sandboxed ✗ audit columns only
Distribution and install git, no registry needed ✓ npx installer, plugin marketplaces, git, skills CLI plain-copy repo, upload, Skills API ~ plugin marketplace install git; npm for plugins git install PyPI plus generated best_skill.md ✓ npx into 79 agents
Telemetry or ranking ✗ out of scope ✗ none found first-party ~ curated partner directory ✗ none found ✗ none first-party ✗ none found ✗ none first-party ✓ install counts, opt-out
Versioning and pinning ✗ none ~ npm dist-tags and git refs, no lockfile ~ Skills API versions ~ git refs ✗ none ~ git refs ✗ none ~ git refs, no lockfile
Explicit invocation ~ explicit or implicit ✓ slash commands for every skill ~ slash commands in Code ~ department-routed ✗ model-judgment only ~ invoked as a writing-repair pass ~ trained skill invokes like any skill n/a (registry)
Vendor neutrality ~ Anthropic-origin, public ✗ pack runs anywhere, gravity is Builder.io’s stack ✗ Claude-coupled ~ Claude Code and ChatGPT first ✗ OpenCode-only, portable files ✓ portable, agent-agnostic ✓ model-agnostic ~ all vendors, one ranker
Cost free free (hosted surfaces free as of the date) ~ included on plans, tokens on API free free (pay tokens) free (maintainer costs on Patreon) free, training tokens on your bill free

Reading the matrix
#

The Kind row says this is not eight competitors but one stack: a spec, a vendor format, a harness mechanism, a quality gate, a distributor, and three content columns (a vendor app pack, a departmental org chart, and a single writing skill). The category converged before it could fragment, because Anthropic released its format as the open standard in December 2025 and OpenAI, Google, and the major harnesses adopted it, per the standard note. SkillOpt is the stack’s quality layer: it treats the other columns’ artifacts as trainable parameters, so the question shifts from who distributes skills to who validates them.

Convergence is real but stops at the spec subset. Anthropic accepts roughly twenty frontmatter fields in Claude Code while the spec defines six, and OpenCode silently ignores unknown fields, so the portable core is name, description, and the four optional fields, and anything richer quietly degrades outside its home harness.

The permissions row is where the columns genuinely diverge, and no cell wins. The spec leaves security to each harness (Gemini consent, OpenCode patterns, Codex enterprise controls), Anthropic couples API skills to its own container, OpenCode alone gates skill loads with per-pattern allow/deny/ask, and skills.sh aggregates scanner columns after the fact.

Distribution is git all the way down, and the registry added ranking, not vetting. The standard needs no registry at all, skills.sh won the slot by wrapping git and symlinking into more than 70 harnesses, its leaderboard counts opt-out CLI telemetry rather than ratings, and one company controls the ranking surface of a nominally open ecosystem, which is the cell I would watch.

The Agent-Native column is the first pack in the matrix, and it reads differently from the five infrastructure columns and from the two content columns that joined later: it consumes the spec’s portable core, adds no enforcement of its own, and its pull is toward Builder.io’s own stack, the hosted Dispatch MCP endpoint and the hosted plans app its flagship skills default to. The cell to watch is stewardship: two repos whose READMEs say MIT at 4.5k and 7.0k stars (the framework has kept climbing since, npm now 0.3.22, and GitHub still detects no license there) with still no independent coverage as of 2026-10-03, so the pack is one company’s opinion on a multiple-releases-a-day cadence.

Everything is free, and the missing row is versioning. No column costs anything to use, but the spec has no version or dependency story, OpenCode has none, Anthropic versions only through its Skills API, and pinning is left to git discipline or third parties like Skilleton.

Choosing from the matrix
#

  • Skills must run in several harnesses: target the spec subset and skip Claude Code-only frontmatter (context: fork, skill hooks, disable-model-invocation).
  • All-Claude team wanting the richest behavior: Anthropic’s format with Code extensions, accepting that claude.ai upload and the API hard-reject those fields.
  • Need enforced policy, not just prompts: OpenCode, with skills for procedure and plugins for policy under per-skill allow/deny/ask.
  • Discovering third-party skills: skills.sh, then pin commits and read the SKILL.md before it touches a repo with production secrets.
  • Want a curated starter set with workflow opinions: Agent-Native’s pack, cherry-picking the discipline skills and declining the managed AGENTS.md/CLAUDE.md blocks if vendor-managed instructions are not your thing.
  • Need managed versions across an organization: Anthropic’s Skills API is the only first-party versioning in the matrix.
  • Shipping skills for your own product: publish them in your repo or docs (.well-known), since the standard note argues docs teams without a skill will be invisible to agents by 2027.

Changes
#

  • 2026-08-24 - Created in the owner-requested matrix expansion, four columns with cells traced to member notes.
  • 2026-08-30 - Extended from four to five columns with SkillOpt, the stack prose naming the new quality layer.
  • 2026-09-13 - Extended from five to six columns with Agent-Native, the first curated pack column.
  • 2026-09-22 - Agent-Native’s open-source cell moved from supported to partial after the framework repo’s GitHub license detection vanished and its package.json switched to ISC; star figures refreshed.
  • 2026-09-24 - Removed the verification preamble line on owner request.
  • 2026-09-25 - Refreshed the Agent-Native figures in the reading prose (framework at 6.8k stars and still climbing, license still undetected, npm now 0.3.1); no cells moved.
  • 2026-09-25 - Re-sorted the columns by member title, moving Agent Skills open standard ahead of Agent-Native (space before hyphen in the case-insensitive title ordering); no cell content changed.
  • 2026-09-27 - Refreshed the Agent-Native figures in the reading prose (npm now 0.3.7); no cells moved.
  • 2026-10-02 - Corrected the intro and reading prose, which still said six columns after Headcount and Sepia joined on 2026-09-27; no cells moved.
  • 2026-10-03 - Refreshed the Agent-Native figures in the reading prose (catalog 4.5k and framework 7.0k stars, npm now 0.3.22); no cells moved.

See also
#

References
#