CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-walter-runtime-intelligence-agents

Answers questions about, summarizes, and applies May Walter's AI Native DevCon talk "From Blind Spots to Merged PRs" on runtime intelligence for coding agents. Use when the user asks about production telemetry for agents, prod-to-code mapping, performance fixes from runtime data, why automated PRs need provenance, Hud's runtime code sensor, weekly performance reports, AI-generated fixes with production context, or applying Walter's evidence-first agent workflow to engineering teams.

69

Quality

85%

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

75%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 body with clear grounding/safety rules, an explicit verification step, and clean navigation to one-level-deep source files. It is held back from top marks by templated (non-executable) example placeholders and the absence of the referenced bundle files.

Suggestions

Add a fix-and-retry feedback loop to the grounding rules (e.g., what to do when a candidate quote cannot be found verbatim in transcript.md) so workflow_clarity can reach 5.

Replace or supplement the "[paste exact quote here]" / "[safe excerpts]" placeholders in the example outputs with a brief concrete illustration so the guidance is fully copy-paste ready.

Ensure the referenced files (outline.md, transcript.md, quote.md) are actually bundled under ./references/ so the progressive-disclosure structure is real and not just signaled.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence without explaining basic concepts, but the two worked example Q&As with placeholder tokens ("[paste exact quote here]", "[safe excerpts]") add length that could be trimmed slightly.

4 / 5

Actionability

Concrete, specific instruction-only guidance — "read outline.md to locate the relevant section, then read that section of transcript.md" and "verify that each quoted passage appears verbatim" — with example response templates, though the placeholders are templates rather than fully executable copy-paste output.

4 / 5

Workflow Clarity

The grounding rules are a clearly numbered sequence (locate via outline.md, read transcript section, quote short excerpts, verify verbatim before presenting) with an explicit verification checkpoint, but there is no retry/fix feedback loop when a quote fails verification.

4 / 5

Progressive Disclosure

Content is well-organized into clearly signaled sections with one-level-deep references (outline.md, transcript.md, quote.md) and a dedicated "Referenced file structure" navigation block, but the referenced bundle files are not actually present in the bundle, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

95%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.

A strong, well-constructed description that clearly states both capability and trigger conditions with a rich set of natural keywords. The only minor weakness is that the action verbs (answers, summarizes, applies) are slightly generic relative to the highly specific domain.

DimensionReasoningScore

Specificity

Names the domain (Walter's talk on runtime intelligence) and lists several concrete actions — "Answers questions about, summarizes, and applies" — but the verbs are somewhat generic applied to a single source, leaving minor coverage gaps rather than fully comprehensive action enumeration.

4 / 5

Completeness

It explicitly answers both what ("Answers questions about, summarizes, and applies May Walter's...talk") and when ("Use when the user asks about...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

The "Use when" clause enumerates a comprehensive set of natural trigger phrases a user would actually say — "production telemetry for agents", "prod-to-code mapping", "why automated PRs need provenance", "weekly performance reports" — including synonyms and related phrasings.

5 / 5

Distinctiveness Conflict Risk

The niche is highly specific — a named talk, named speaker, named product (Hud) and distinctive topics — giving it clear triggers with minimal overlap risk against other skills.

5 / 5

Total

19

/

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.