CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

talk-lopopolo-harness-engineering

Use when the user asks about Ryan Lopopolo's AI Native DevCon talk on harness engineering, steering coding agents with goals, constraints, context, tool scope, eval loops, and verification systems.

Quality

77%

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-lopopolo-harness-engineering/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 concise, well-organized reference-skill body with sequenced grounding rules, explicit verification and fallback behavior, and sensible source-material safety rules. The critical weakness is progressive disclosure: the body is built almost entirely on three bundle files that are not present in the skill as provided.

Suggestions

Ship `outline.md`, `quote.md`, and `transcript.md` in a `references/` directory and cite them with explicit paths (e.g., `references/outline.md`) so the grounding workflow is actually navigable.

Add one concrete example of a transcript line-ID citation so the 'cite the transcript line IDs' instruction is copy-paste unambiguous.

Merge the bare 'Core Concepts' list into the grounding rules or the intro sentence to remove redundancy with the description.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanation of concepts Claude already knows — the framing sentence, grounding rules, and safety rules all earn their place. The bare-name 'Core Concepts' bullet list slightly duplicates the frontmatter topic enumeration and could be trimmed, keeping it just below anchor 5.

4 / 5

Actionability

Concrete, executable instruction for a reference skill: "Read `outline.md` first", "Use `quote.md` for short supporting excerpts, then verify against `transcript.md`", and "cite the transcript line IDs when available". It falls short of anchor 5 only in lacking concrete examples (e.g., a sample line-ID citation) and any fallback if a referenced file is unavailable.

4 / 5

Workflow Clarity

The numbered grounding rules give a clear sequence with a verification step ("verify against `transcript.md` when precision matters") and an explicit error-recovery rule ("If the transcript does not support a claim, say that the talk does not address it"). Not anchor 5 because the verification checkpoint is conditional ('when precision matters') rather than a hard gate, and the How-To-Help flows have no checkpoints.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep, but the three cited files — `outline.md`, `quote.md`, and `transcript.md` — do not exist in the provided bundle (no references/ directory is present), so navigation cannot actually be completed and the paths lack directory context. Scoring against the actual bundle structure places this at anchor 3: structure present, but discovery is broken.

3 / 5

Total

15

/

20

Passed

Description

73%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 well-targeted description with an explicit 'Use when' trigger and a distinctive proper-noun niche. Its main weakness is that it lists what the talk covers rather than what the skill does, leaving the capability statement implicit.

Suggestions

State the skill's action explicitly, e.g. 'Answers questions about, summarizes, and helps apply Ryan Lopopolo's AI Native DevCon talk...' so the 'what' is as explicit as the 'when'.

Add a few natural trigger variations such as 'agent harness', 'Lopopolo', or 'DevCon talk notes' to broaden keyword coverage.

DimensionReasoningScore

Specificity

The description enumerates concrete domain topics ("harness engineering, steering coding agents with goals, constraints, context, tool scope, eval loops, and verification systems") but never states an action the skill performs (no 'answers', 'summarizes', or 'cites' verbs). It is more concrete than anchor 2's bare 'Processes PDF files' domain naming, but lacks the concrete actions that anchors 3-4 reward.

3 / 5

Completeness

The 'when' is explicit ("Use when the user asks about Ryan Lopopolo's AI Native DevCon talk..."), so the missing-trigger cap at 3 does not apply, but the 'what' is only implied by the topic enumeration — the description never states what the skill does with the talk content. This sits between anchor 3 (clear what, weak when) and anchor 5 (both fully explicit).

4 / 5

Trigger Term Quality

Natural trigger phrases are well covered: "Ryan Lopopolo", "AI Native DevCon talk", "harness engineering", "steering coding agents" — terms a user asking about this talk would plausibly say. A few natural variations are missing (e.g., "agent harness", "Lopopolo", "talk notes/summary"), keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The trigger is anchored to a proper-noun niche — a specific speaker ("Ryan Lopopolo") and a specific event ("AI Native DevCon talk") — making false triggers from unrelated skills extremely unlikely.

5 / 5

Total

16

/

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-lopopolo-harness-engineering/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.