CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-maple-harness-engineering

Use when the user asks about Simon Maple's AI Native DevCon talk "Welcome to AI Native DevCon" on harness engineering — including questions about agents.md structure, just-in-time guardrails, review personas, shift-right interventions, the three phases of agent context delivery (grounding / messy middle / review & merge), why the speaker avoids shifting left with agents, treating agents as teammates, vibe coding, the foundational constraints (human time, attention, context window), verbatim quotes from the talk, or applying his harness engineering approach to the user's own codebase.

71

Quality

88%

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

The canonical home for this skill is ainativedev/aidevcon-2026-ldn

SKILL.md
Quality
Evals
Security

Quality

Content

77%Scale 1-3

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

This is a well-structured skill for a knowledge-retrieval task grounded in a specific talk transcript. Its greatest strengths are actionability (concrete step-by-step workflows for each use case) and workflow clarity (clear sequencing with validation checkpoints like asking before scoring and marking non-talk content). Its main weakness is repetition — the verbatim quoting rule and the outline.md→transcript.md lookup pattern are restated nearly identically across all six sections, which inflates token cost without adding information.

Suggestions

Consolidate the repeated 'read outline.md → read transcript.md → quote verbatim → cite line numbers' pattern into a single shared procedure section at the top, then reference it from each use-case section to reduce redundancy.

Consider trimming the introductory paragraph summary of the talk — Claude doesn't need a synopsis to follow the instructions, and the grounding rules already constrain behavior to the transcript.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but includes some redundancy — the verbatim quoting instruction is repeated across nearly every section (6+ times), and the 'read outline.md then transcript.md' pattern is restated in almost identical form for each use case. Some consolidation would save tokens without losing clarity.

2 / 3

Actionability

Each section provides concrete, step-by-step procedures with specific actions (read outline.md, locate named frameworks, quote verbatim, cite line numbers, mark non-talk additions with a specific label). The audit workflow specifies exact dimensions (a-g) to check. The guidance is specific and directly executable.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced with numbered steps. The audit workflow includes explicit checkpoints ('If the user hasn't described their state for a dimension, ask before scoring') and the artifact drafting workflow has a validation step (marking anything beyond Maple's prescription). Each workflow has a clear sequence with appropriate guardrails.

3 / 3

Progressive Disclosure

The skill references external files (outline.md, transcript.md, quotes.md) appropriately, creating a good layered structure. However, no bundle files were provided to verify these references exist, and the skill itself is somewhat long with repetitive patterns across sections that could potentially be consolidated into a shared preamble plus shorter per-section specifics.

2 / 3

Total

10

/

12

Passed

Description

100%Scale 1-3

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

This is a strong, well-crafted description that clearly identifies a narrow domain (a specific conference talk) and enumerates the many subtopics a user might ask about. It opens with an explicit 'Use when' clause and provides extensive trigger terms that match natural user queries. The only minor concern is its length, but the specificity justifies the verbosity.

DimensionReasoningScore

Specificity

The description lists many specific concrete concepts and actions: agents.md structure, just-in-time guardrails, review personas, shift-right interventions, three phases of agent context delivery, vibe coding, foundational constraints, verbatim quotes, and applying the approach to the user's codebase.

3 / 3

Completeness

The description explicitly answers both 'what' (answers questions about Simon Maple's talk on harness engineering, including specific topics) and 'when' ('Use when the user asks about Simon Maple's AI Native DevCon talk' with extensive trigger scenarios). The 'Use when...' clause is present and detailed.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a user would say: 'Simon Maple', 'AI Native DevCon', 'harness engineering', 'agents.md', 'guardrails', 'vibe coding', 'shift-right', 'agents as teammates', 'context window'. These are highly specific and match what someone familiar with this talk would naturally reference.

3 / 3

Distinctiveness Conflict Risk

Extremely distinctive — it's scoped to a specific speaker's specific talk at a specific conference. The combination of 'Simon Maple', 'AI Native DevCon', and 'harness engineering' creates a very clear niche that is unlikely to conflict with any other skill.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

9

/

11

Passed

Repository
AINativeDev/aidevcon-2026-ldn
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.