CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

talk-smith-connecting-context-future-transports

Use when the user asks about Shaun Smith's AI Native DevCon talk on MCP transports, remote Streamable HTTP servers, stateless protocol direction, Hugging Face MCP adoption, and future context transports.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Plugins/aidevcon/skills/talk-smith-connecting-context-future-transports/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized reference-skill body: lean, safety-aware, and with a clear grounding workflow that includes explicit verification rules against the transcript. The only gaps are minor — a duplicated topic list and bundle files referenced but absent from the package under review.

DimensionReasoningScore

Conciseness

The body is lean with no explanation of concepts Claude already knows; grounding rules ("Read `outline.md` first to locate the relevant section or concept"), safety rules, and per-mode guidance all earn their place. It misses anchor 5 only through minor redundancy: the topic list appears twice (the intro sentence "Shaun Smith explains the evolving MCP transport landscape..." and again as the "Core Concepts" bullet list), so one instance could be trimmed.

4 / 5

Actionability

For an instruction-only skill the guidance is concrete and executable: a file reading order ("Read `outline.md` first", "Use `quote.md` for short supporting excerpts, then verify against `transcript.md`"), attribution rules, and per-mode handling for Q&A, Apply, and Compare. Not 5 because there are no worked examples (e.g., of the "cite the transcript line IDs" format), leaving a minor gap between instruction and execution.

4 / 5

Workflow Clarity

The grounding sequence is explicit and ordered (outline → quote excerpt → transcript verification) with genuine validation checkpoints: "if a line is from the host or an audience member, say so" and "If the transcript does not support a claim, say that the talk does not address it" — an explicit unsupported-claim guardrail. As a simple single-purpose reference skill with an unambiguous core action and these verification rules, it matches anchor 5 under the simple-skill exception; no destructive or batch operations apply to cap it.

5 / 5

Progressive Disclosure

References to `outline.md`, `quote.md`, and `transcript.md` are one level deep, each clearly signaled with a distinct role (locate, excerpt, verify), and the body stays a proper overview. It falls short of anchor 5 because the three referenced files are not present in the reviewed bundle (no references/ or sibling files exist to verify), so the structure is exemplary but its file layout cannot be confirmed.

4 / 5

Total

17

/

20

Passed

Description

51%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly distinctive and trigger-rich — a user asking about this specific talk would almost certainly surface it — but it is purely a 'when' clause. It never states what the skill does (answer, summarize, apply, compare), leaving the 'what' half of completeness unaddressed and yielding low action specificity.

Suggestions

Open with a 'what' clause stating the skill's actions, e.g. "Answers questions about, summarizes, and applies Shaun Smith's 'Connecting Context' AI Native DevCon talk..." before the 'Use when' trigger.

List the concrete actions the body already defines (factual Q&A, applying the talk to user contexts, comparing with other DevCon sessions) so the description carries specific verbs, not just topics.

Add the talk title 'Connecting Context' and a natural variant like "DevCon talk on MCP transports" as trigger terms to round out keyword coverage.

DimensionReasoningScore

Specificity

Phrases like "Use when the user asks about Shaun Smith's AI Native DevCon talk on MCP transports..." name the domain (and its topics) with precision, but the description contains no concrete actions — nothing like "answers questions", "summarizes", or "compares talks" — matching the anchor 'Names the domain but actions are minimal or generic'. Not 3 because no 1-2 concrete actions are listed at all; not 1 because the domain is far from vague.

2 / 5

Completeness

Only the 'when' is explicitly present ("Use when the user asks about..."); what the skill actually does with the talk content is never stated, matching anchor 2's 'only when is present without what'. Not 3 because that anchor requires a clear 'what' with missing 'when' — the inverse of this description; not 1 because the 'when' clause is specific and explicit, not extremely vague.

2 / 5

Trigger Term Quality

Natural user phrases are well covered: "Shaun Smith", "AI Native DevCon", "MCP transports", "remote Streamable HTTP servers", "stateless protocol direction", "Hugging Face MCP adoption". It falls short of anchor 5 only because obvious synonyms are missing — the talk title "Connecting Context" (present in the body's heading) is never mentioned, and no variants like "DevCon talk" or "MCP transport landscape" appear.

4 / 5

Distinctiveness Conflict Risk

Naming a specific speaker, conference, and five distinct technical topics creates a clear niche with distinct triggers and minimal conflict risk against any generic skill, matching anchor 5. Only marginal overlap could occur with sibling talk-reference skills in the same skill-set, which is below the threshold for anchor 4's 'minor overlap risk'.

5 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

jscraik/Agent-Skills

Path

Plugins/aidevcon/skills/talk-smith-connecting-context-future-transports/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.