CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-lawson-agent-experience

Use when the user asks about Dana Lawson's talk "Built for Humans. Now Agents Are Here." (Netlify CTO, 2026) — including questions about Agent Experience (AX), the AX paradox, redesigning CLIs/build logs/deploy previews for agents, moving from APIs to capabilities, event-driven agent architectures, blueprints (skills/recipes/context/ADRs), software factories, autonomous development loops, sandbox + human-in-loop + audit/rollback trust principles, the expanded "builder persona," or applying Netlify's AX approach to the user's own platform.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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-structured reference skill with clear, actionable, well-sequenced workflows and good progressive-disclosure design. Main weaknesses are repeated quoting/citation guidance across subsections and reliance on reference files (outline.md, transcript.md, quote.md) that are not present in the bundle.

Suggestions

Consolidate the repeated 'quote short, non-sensitive excerpts and cite transcript line ranges' instruction into the Grounding rules once, then have each subsection reference it instead of restating it.

Confirm outline.md, transcript.md, and quote.md are actually bundled with the skill, since every workflow depends on them and they are absent here.

Consider a short top-of-body index listing the reference files and what each is for, so navigation does not require scanning every subsection.

DimensionReasoningScore

Conciseness

Mostly efficient and free of over-explaining known concepts, but the 'quote short, non-sensitive excerpts from transcript.md / cite line ranges' guidance is restated verbatim across nearly every subsection and could be consolidated into the grounding rules once.

3 / 5

Actionability

Concrete, specific procedural guidance (read outline.md, read the matching transcript.md range, quote verbatim, cite line numbers, emit covered/partial/missing verdicts, mark non-talk additions with a literal placeholder tag); the gap is that outline.md/transcript.md/quote.md are referenced but not present in the bundle.

4 / 5

Workflow Clarity

Each mode is a clearly sequenced numbered procedure with grounding checkpoints ('If the answer isn't in the transcript, say so explicitly', 'ask before scoring'), but the checkpoints are grounding-style rather than error-recovery feedback loops, so it sits just below the top anchor.

4 / 5

Progressive Disclosure

SKILL.md is a well-organized overview with clearly signaled one-level-deep references (outline.md, transcript.md, quote.md) and a clear 'check quote.md first' navigation hint; the only gap is that the referenced detailed files are not shipped in this bundle.

4 / 5

Total

15

/

20

Passed

Description

100%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.

An excellent description: specific, third-person, comprehensive in trigger terms, and unambiguous about both scope and activation conditions. No changes needed.

DimensionReasoningScore

Specificity

Names the specific talk plus a comprehensive list of concrete topics (AX, AX paradox, redesigning CLIs/build logs/deploy previews, APIs→capabilities, blueprints, software factories, trust principles, builder persona), matching the 'multiple specific concrete actions; comprehensive coverage' anchor.

5 / 5

Completeness

Explicitly answers both what (a reference skill for this specific talk and its topic set) and when ('Use when the user asks about...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Rich natural terms a user would actually say ('Dana Lawson's talk', 'Agent Experience (AX)', 'AX paradox', 'deploy previews', 'blueprints', 'Netlify') with synonyms (AX/Agent Experience); file-extension style triggers do not apply to a talk skill.

5 / 5

Distinctiveness Conflict Risk

Tied to one named person and one named talk, a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
jscraik/Agent-Skills
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.