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

Humans vs Slop

Cheap generation can create expensive review and maintenance burden, so teams need quality gates that reward durable value.

Read Order

  1. Use outline.md for the talk thesis, concept map, and safe application boundaries.
  2. Use quote.md when the answer needs a short supporting excerpt.
  3. Use transcript.md only to confirm what remained after safety redaction.
  4. If the user asks for omitted mechanics, say that the bundle is redacted and answer with the safe design principle.

What This Skill Produces

  • slop-risk checklist
  • review-cost model
  • quality-gate rubric
  • durable-value metrics

Core Workflow

When answering a factual question:

  1. Identify the relevant concept from outline.md.
  2. Answer in 2-5 sentences.
  3. Add one short excerpt from quote.md only if it strengthens the answer.
  4. State when the bundle does not cover a requested detail.

When applying the talk to the user's work:

  1. Identify what generated work someone must own later.
  2. Separate visible output volume from maintained value.
  3. Add review gates for correctness, readability, and fit.
  4. Define when humans must make taste or architecture calls.
  5. Prefer small durable changes over large unreviewable batches.

When the user asks for operational mechanics, commands, credentials, mutable-source processing, or direct system actions, do not provide them from this bundle. Give the design-level alternative instead.

Output Templates

Summary

  • Thesis:
  • Key concepts: <3-5 bullets>
  • Practical takeaway:

Design Artifact

  • Goal:
  • Boundaries: <what the agent/system must not do>
  • Review points:
  • Evidence:
  • Open questions:

Redacted Request

  • State that the requested mechanics are not available in the redacted bundle.
  • Explain the risk in neutral terms.
  • Provide a safe checklist or conceptual design instead.

Examples

User: How do we avoid slop? Response shape: Give a rubric covering ownership, clarity, tests, reversibility, and product fit.

User: Can you review current contributions? Response shape: Decline mutable-source processing and offer a static rubric.

Repository
jscraik/Agent-Skills
Last updated
First committed

Also appears in

ainativedev/latest-aidevcon-speakers-london-2026
Modified

on Jun 18, 2026

ainativedev/aidevcon-2026-ldn
Modified

on Jun 22, 2026

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.