CtrlK
BlogDocsLog inGet started
Tessl Logo

talk-wotherspoon-humans-vs-slop

Explains Jack Wotherspoon's Humans vs Slop talk and helps create quality gates for AI-heavy software work: review-cost analysis, slop detection heuristics, durable-value metrics, and human-judgment checkpoints. Use when the user asks about AI-generated maintenance burden, review economics, or preserving taste in agentic development.

65

Quality

79%

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-wotherspoon-humans-vs-slop/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 well-organized reference skill body with lean, actionable workflows and templates. Its main defect is that every referenced bundle file (outline.md, quote.md, transcript.md) is absent, which undermines both navigation and execution.

Suggestions

Ship the referenced bundle files (outline.md, quote.md, transcript.md) under references/ so the Read Order actually resolves; without them the skill cannot deliver its stated outputs.

Add a brief fallback line for when a referenced file is missing, so Claude degrades gracefully instead of citing a non-existent excerpt.

Tighten the thematic opener sentence or fold it into the outline to lift conciseness from 4 to 5.

DimensionReasoningScore

Conciseness

The body is lean — numbered workflows, bulleted outputs, and short templates assume Claude's competence and avoid explaining concepts Claude already knows; the thematic opener ('Cheap generation can create expensive review burden...') is minor padding that keeps it at 4 rather than 5.

4 / 5

Actionability

Guidance is concrete and executable — a named Read Order, numbered steps, and specific template fields (Goal, Boundaries, Review points, Evidence) — but the referenced bundle files do not exist, which leaves minor execution gaps; this fits the 4 anchor (mostly executable, minor gaps) better than 5.

4 / 5

Workflow Clarity

Two clearly sequenced numbered workflows are present with light checkpoints ('State when the bundle does not cover a requested detail', redaction guardrails), matching the 4 anchor; it is not 5 because there are no explicit validate→fix→retry feedback loops, and not 3 because the sequences are well defined.

4 / 5

Progressive Disclosure

The Read Order signals one-level-deep references (outline.md, quote.md, transcript.md) clearly, but those bundle files are not present in references/, scripts/, or assets/, so navigation is broken; the missing materials drop it to the 3 anchor rather than the 4/5 the structure would otherwise earn.

3 / 5

Total

15

/

20

Passed

Description

87%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, third-person description that clearly conveys both capability and trigger conditions with concrete actions and natural keywords. The main limitation is slightly less than comprehensive keyword/synonym coverage.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions — 'review-cost analysis, slop detection heuristics, durable-value metrics, and human-judgment checkpoints' — but stops short of fully comprehensive coverage, so the 4 anchor (several specific actions, minor gaps) fits better than 5.

4 / 5

Completeness

It explicitly states both what the skill does ('Explains... talk and helps create quality gates...') and when to use it ('Use when the user asks about...') with concrete trigger phrases, matching the 5 anchor exactly; it is not merely a weak 4 because both halves are concrete and explicit.

5 / 5

Trigger Term Quality

The 'Use when' clause surfaces natural phrases users would say — 'AI-generated maintenance burden', 'review economics', 'preserving taste in agentic development' — giving good coverage, but it misses common synonyms and variations that would push it to 5.

4 / 5

Distinctiveness Conflict Risk

The named talk ('Jack Wotherspoon's Humans vs Slop') and specialized triggers carve a clear niche with minimal overlap risk against other skills, matching the 5 anchor; it is not a 4 because the subject matter is highly distinctive rather than merely 'mostly distinct'.

5 / 5

Total

18

/

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.