diff --git a/README.md b/README.md index 727ddbc..5bbb6a8 100644 --- a/README.md +++ b/README.md @@ -85,14 +85,11 @@ This IG may propose becoming a Working Group if: ## Work Tracking -| Item | Status | Champion | Notes | -| :--- | :--- | :--- | :--- | -| Requirements alignment | In Progress | All facilitators | Review approaches, identify common requirements and gaps | -| Agent Skills spec coordination | In Progress | Ola | Use [agentskills/agentskills Discussions](https://github.com/agentskills/agentskills/discussions) for intersecting topics; see [contributing guide](https://github.com/agentskills/agentskills/blob/main/CONTRIBUTING.md) | -| Experimental findings repo | Proposed | Ola | Dedicated repo for implementations and evaluation results | -| SEP-2076 review | In Progress | Yu Yi | Skills as first-class primitive proposal | -| Registry skills.json proposal | In Progress | Ozz | Skills metadata in registry schema | -| MCP Skills Convention v0.1 | Proposed | TBD | Documented pattern (not spec) for skills over existing primitives | +Work items are tracked as [GitHub Issues](https://github.com/modelcontextprotocol/experimental-ext-skills/issues). Key coordination channels: + +- **Agent Skills spec coordination:** Use [agentskills/agentskills Discussions](https://github.com/agentskills/agentskills/discussions) for intersecting topics; see [contributing guide](https://github.com/agentskills/agentskills/blob/main/CONTRIBUTING.md) +- **SEP-2076 review:** [Skills as first-class primitive proposal](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2076) (Champion: Yu Yi) +- **Registry skills.json proposal:** [Skills metadata in registry schema](https://github.com/modelcontextprotocol/registry/discussions/895) (Champion: Ozz) ## Success Criteria diff --git a/docs/approaches.md b/docs/approaches.md index 5d862aa..cd0af40 100644 --- a/docs/approaches.md +++ b/docs/approaches.md @@ -60,6 +60,8 @@ Examples: - Expose skills via tools like `list_skills` and `read_skills`. Server instructions can direct the agent to call the skill tool first. - Expose skills as resources (e.g. skill://...), which can also be exposed through tools +**See also:** [#41](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/41) — Server-side reference implementation, [#55](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/55) — Recommended _meta keys for skill resources + **Implementations:** @@ -97,6 +99,8 @@ Several design considerations have been suggested in community discussion and pr - **Git-based distribution:** Versioned distribution via git (tags, pinned refs) can be viable without a formal registry. Clare Liguori (AWS) noted that Terraform operated without a formal registry for a long time — Feb 26 office hours. - **Domain-level discovery:** The [Agent Skills Discovery RFC](https://github.com/cloudflare/agent-skills-discovery-rfc) proposes `/.well-known/skills/` for organizations to publish skills at predictable URLs with content integrity (SHA-256 digests). This is complementary to MCP — it handles discovery and distribution while MCP handles runtime consumption. +**See also:** [#44](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/44) — Define well-known URI schemes and naming patterns for skill resources + **Community input:** > "Installless/temporary/ephemeral skill availability while server is installed feels like a good pattern. Clients could optionally offer to permanently install." — [Sam Morrow](https://github.com/SamMorrowDrums) (GitHub), via Discord @@ -113,6 +117,8 @@ Instead of exposing skill tools to the main agent, use MCP's Sampling with Tools **Source:** [jbnitorum](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2076#issuecomment-3806151745) +**See also:** [#42](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/42) — Test skills-via-sampling approach + ## 4. Gateway/Composition Pattern A gateway-style server that provides a group of MCPs as one, ensuring they get requisite configuration and instructions to work in harmony. @@ -141,6 +147,8 @@ A documented "MCP Skills Convention" as a middle path between ad-hoc experiments This mirrors how other ecosystems (e.g., Kubernetes) graduate patterns: start as convention, prove value, then formalize. Could be a concrete IG deliverable: "MCP Skills Convention v0.1." +**See also:** [#43](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/43) — Draft MCP Skills Convention v0.1 + **Advantages of the convention approach:** - Since MCP supports dynamically updating tools, the latest skills manifest can be included in tool descriptions diff --git a/docs/experimental-findings.md b/docs/experimental-findings.md index 01cf717..2e2ea9e 100644 --- a/docs/experimental-findings.md +++ b/docs/experimental-findings.md @@ -1,5 +1,7 @@ # Experimental Findings +> **Contributing findings?** See [#50](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/50) for the contribution template proposal. + ## McpGraph: Skills in MCP Server Repo **Repo:** [TeamSparkAI/mcpGraph](https://github.com/TeamSparkAI/mcpGraph) @@ -86,3 +88,5 @@ Multiple community members have independently reported that models do not reliab > "Skills are ephemeral and/or time decaying — it clicks once and then give it some time and they lose the plot." — Kryspin (qcompute), via Discord > "I've seen lazy load skills with various degrees of success, actually looks like it might be model specific… [best pattern is] putting them in with a subagent that similarly named or mentions the topic in their description." — Kryspin (qcompute), via Discord + +**See also:** [#37](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/37) — Compare skill delivery mechanisms: file-based vs MCP-based diff --git a/docs/open-questions.md b/docs/open-questions.md index 29d2687..9cf6cee 100644 --- a/docs/open-questions.md +++ b/docs/open-questions.md @@ -2,6 +2,8 @@ ## 1. Is this a registry problem or an MCP server problem? +> **See also:** [#44](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/44) — Define well-known URI schemes and naming patterns for skill resources + Should skills be discoverable through registry metadata ("if you install this server, also install this skill") or contained within the MCP server itself? A third option is emerging: domain-level discovery via `/.well-known/skills/` (see [Agent Skills Discovery RFC](https://github.com/cloudflare/agent-skills-discovery-rfc)). This decouples skill discovery from both registries and MCP servers — an organization publishes skills at a predictable URL on its own domain. This could complement MCP-level discovery rather than replace it: `.well-known` handles "find available skills," MCP handles "load and use them at runtime." @@ -18,6 +20,8 @@ Or is the separation between "primitive server" and "skill that uses the primiti ## 4. How should skills relate to multiple servers? +> **Tracked in:** [#39](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/39) — Research skill dependency declaration and host-mediated resolution + A skill orchestrating tools from several servers can't live in any single server's instructions. **Related:** [agentskills/agentskills#110](https://github.com/agentskills/agentskills/issues/110) — Discusses how skills should declare their tool/server dependencies. The lack of explicit dependency configuration makes multi-server skill execution unpredictable: if required servers and tools aren't already loaded, the skill can't reliably execute. @@ -36,6 +40,9 @@ The agentskills.io spec currently has a freeform [compatibility field](https://a ## 5. Do clients actually leverage skills when presented via MCP? +> **Tracked in:** [#38](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/38) — Survey client resource-loading support across major MCP clients +> **See also:** [#37](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/37) — Compare skill delivery mechanisms: file-based vs MCP-based + Early experiments suggest they do, but more rigorous testing is needed. **Community input:** @@ -48,10 +55,14 @@ Early experiments suggest they do, but more rigorous testing is needed. ## 7. What would MCP have had to get right for skills to have been shipped over MCP from the beginning? +> **See also:** [#47](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/47) — Create evaluation matrix mapping approaches to requirements + — [Keith Groves](https://github.com/keithagroves) ## 8. What could MCP reasonably change so that it will be the obvious choice for new formats? +> **See also:** [#54](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/54) — The case for custom metadata instead of a URI convention + — [Keith Groves](https://github.com/keithagroves) **Community input:** @@ -94,6 +105,8 @@ Note: Some apps like Claude Code have started to indicate in the skill frontmatt ## 12. Why not just resources? +> **See also:** [#54](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/54) — The case for custom metadata instead of a URI convention, [#55](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/55) — Define recommended _meta keys for skill resources + **Core Maintainer input:** > "Why not just resources? That feels like the obvious implementation since skills are just files and resources already exist to expose files. i.e. just expose skills as resources the same as they're currently exposed on the filesystem and then just use the existing Agent Skills specification — client can find skills using resources/list to find SKILL.md files." — [Peter Alexander](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2076#discussion_r2736299627) @@ -108,6 +121,9 @@ See also [Approaches](approaches.md) for more notes on using resources. ## 13. What is the optimal relationship between skills and MCP? +> **Tracked in:** [#43](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/43) — Draft MCP Skills Convention v0.1 +> **See also:** [#47](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/47) — Create evaluation matrix mapping approaches to requirements + Skills already work as simple files that agents load directly. Adding MCP to the process should provide clear value beyond what standalone skills already offer. **Community input:** diff --git a/docs/use-cases.md b/docs/use-cases.md index 8d5cc05..1d3334f 100644 --- a/docs/use-cases.md +++ b/docs/use-cases.md @@ -30,6 +30,8 @@ Skills that leverage tools from multiple off-the-shelf servers where you can't ( Beyond multi-server tool orchestration, skills themselves may be composable — one skill depending on another skill's output or behavior. This extends the dependency model beyond tool availability to skill availability, and raises questions about declarative dependency metadata. See [Open Question 4](open-questions.md#4-how-should-skills-relate-to-multiple-servers) for the emerging proposal on host-mediated dependency resolution. +**See also:** [#39](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/39) — Skill dependency declaration, [#45](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/45) — Worked examples for multi-server composition + ## 4. Progressive Disclosure Skills broken into linked sets of files for effective context management, loaded progressively as the agent needs them rather than all at once. @@ -46,6 +48,8 @@ Skills broken into linked sets of files for effective context management, loaded **Related:** [Anthropic's guidance on progressive disclosure](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) +**See also:** [#45](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/45) — Worked examples for progressive disclosure, [#40](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/40) — Client-side reference implementation for model-driven resource loading + ## 5. Server-Skill Pairing Servers that are difficult or impossible to use effectively without an accompanying skill.