Why your LLM ignores what you asked for

camjampng1 pts0 comments

GitHub - CamjamPNG/skills: An agent skill that stops AI models from drowning complex tasks in words · GitHub

/" data-turbo-transient="true" />

Skip to content

Type / to search

Sign in<br>Sign upAppearance settings

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

CamjamPNG

skills

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>9 Commits<br>9 Commits

evals

evals

README.md

README.md

SKILL.md

SKILL.md

View all files

Repository files navigation

efficient-semantic-thinking

An agent skill that stops AI models from drowning complex tasks in words — it thinks in compact meaning, not prose, and only talks normally when it needs to.

Who it's for: anyone building or running agents that handle multi-step planning, comparing options, or juggling lots of constraints.

Why it exists: natural language is verbose. When an agent restates requirements as prose over and over, it burns tokens, repeats itself, and drifts. This skill gives the model a compressed "mental workspace" — the same information, less overhead.

Install

npx skills add CamjamPNG/skills

What the skill does

When active, the model:

Extracts the real goal, entities, hard requirements, preferences, conditions, and uncertainty from the task

Represents them compactly — e.g. PRICE, RAM>=16GB, BEST=B

Reasons over that compressed state instead of restating prose

Preserves specificity — never swaps a specific fact for a generic label

Expands back into natural language when it talks to you

The point is not fewer words. The point is more meaning per word — a representation that stays compact, precise, and reversible, and that never loses information to sound shorter.

Example

A user asks to compare three laptops. The model internally works with:

=16GB, STORAGE>=512GB<br>PREF: PERFORMANCE > BATTERY<br>VALID: A, B REJECT: C (RAMREQ: PRICE=16GB, STORAGE>=512GB<br>PREF: PERFORMANCE > BATTERY<br>VALID: A, B REJECT: C (RAM

...then answers in plain English: "I'd pick B — it meets every requirement and has 32GB RAM and 1TB storage."

Repository structure

efficient-semantic-thinking/<br>└── SKILL.md

About<br>An agent skill that stops AI models from drowning complex tasks in words<br>Topics<br>agentagent-skillagent-skillsaiai-agentai-agentsai-skillskillskill-md<br>Resources<br>Readme<br>Activity<br>Stars<br>0 stars<br>Watchers<br>0 watching<br>Forks<br>0 forks<br>Report repository

Releases

Packages

Contributors

You can’t perform that action at this time.

skill skills agent from words camjampng

Related Articles