CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

84%

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.

The body is a well-organized, instruction-only grounding skill with explicit verification and fallback steps, but it is critically undermined by its bundle: all three referenced files are absent, so the mandated workflow cannot actually be executed. Secondary issues are placeholder example outputs and an inconsistent read-order between outline.md and quote.md.

Suggestions

Ship the referenced bundle files (outline.md, transcript.md, quote.md) or remove the references — every step of the mandated workflow depends on files that are not present in the skill.

Reconcile the navigation order into one sequence: grounding rule 1 mandates reading outline.md first, while the "Key quotes" section says to check quote.md first; state a single ordered workflow.

Replace the placeholder example outputs ("[paste exact quote here]", "[safe excerpts]") with one worked example grounded in an actual transcript excerpt, and consolidate the outline-first instruction, which is repeated in the intro, grounding rules, and file-structure sections.

DimensionReasoningScore

Conciseness

The grounding and safety rules are tight and every section earns its place, but the outline-first instruction is stated three times (intro, grounding rule 1, file structure) and the example outputs are placeholder templates rather than trimmed content. Efficient with minor instances that could be trimmed, so 4 not 5.

4 / 5

Actionability

Concrete, executable instruction guidance: exact file names, "read outline.md to locate the relevant section, then read that section of transcript.md", a verbatim-quote verification step, and a copy-paste fallback phrasing for missing claims. Held at 4 because the examples are unworked placeholders ("[paste exact quote here]", "[safe excerpts]") and no citation convention (section/timestamp) is given.

4 / 5

Workflow Clarity

A clear locate-then-read-then-quote sequence exists with an explicit validation checkpoint (rule 4: verify each quote verbatim) and an error-recovery path (rule 3 fallback response). Not 5 because the ordering is inconsistent: grounding rule 1 says read outline.md first while "Key quotes" says check quote.md first, leaving the workflow order ambiguous.

4 / 5

Progressive Disclosure

The body clearly signals one-level-deep references (outline.md, transcript.md, quote.md) in a dedicated file-structure section, but none of these files exist in the bundle — no references/, scripts/, or assets/ directories are present. Every reference dangles, making navigation to the actual content impossible; the failure is missing files rather than organization, fitting anchor 2 rather than 3.

2 / 5

Total

14

/

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 description with an explicit what/when structure, rich natural trigger terms, and a highly distinct niche. The only soft spot is that the action verbs are somewhat generic relative to the top specificity anchor.

DimensionReasoningScore

Specificity

"Answers questions about, summarizes, and applies" names the domain plus three concrete actions, matching the several-specific-actions anchor. It falls short of 5 because the verbs are generic and what "applies" the talk means is left vague.

4 / 5

Completeness

It explicitly answers both: what ("Answers questions about, summarizes, and applies May Walter's AI Native DevCon talk...") and when ("Use when the user asks about...") with concrete trigger phrases, matching the top anchor exactly; the 'when' is explicit and specific, so not 4.

5 / 5

Trigger Term Quality

The "Use when" clause enumerates natural phrases users would actually say — "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" — comprehensive coverage including synonyms and niche terms.

5 / 5

Distinctiveness Conflict Risk

It targets a single named talk by a named speaker with product-specific terms (Hud's runtime code sensor), giving it a clear niche with minimal conflict risk against any plausible sibling skill.

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.

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-walter-runtime-intelligence-agents/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.