Stats
Actions
Tags
From skills-for-humanity
Applies lossy vs lossless compression thinking to trim representations, summaries, and communications while preserving what matters. Use when asked to cut, remove, or find the essential.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skills-for-humanity:s4h-information-compressionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Every representation is a compression of reality. A report compresses events. A model compresses a domain. An explanation compresses understanding. A decision brief compresses weeks of analysis. The question is never whether to compress — it's whether the compression preserves what matters.
Every representation is a compression of reality. A report compresses events. A model compresses a domain. An explanation compresses understanding. A decision brief compresses weeks of analysis. The question is never whether to compress — it's whether the compression preserves what matters.
Claude Shannon proved that there is a theoretical lower bound on how far any lossless compression can go: you cannot compress below the entropy of the source without discarding information. This is the source coding theorem. Applied practically: there is always a floor. A message with genuine information content cannot be shortened indefinitely without loss — and often the thing being shortened to below-floor is not actually long; it's precise. The problem is usually the reverse: sources that are padded, redundant, or poorly structured can be dramatically shortened without any loss, because they weren't near the floor to begin with.
The critical distinction is lossy vs. lossless. Lossless compression preserves every bit of the original — the compression is reversible. Lossy compression discards some information permanently, in exchange for a representation that is smaller or more usable. Both are legitimate; the choice depends entirely on what the information is for, who will use it, and what the cost of loss is. An executive summary is lossy by design. A legal contract is lossless by necessity. The skill is making the trade-off explicit — and knowing what you are throwing away.
James Gleick's The Information notes that compression is cognition: the brain is fundamentally a compression engine. Understanding is compression. This is why the best explanations are short: not because they're simpler, but because they've found the structure that allows reconstruction from minimal representation. Teaching someone a principle rather than a list of cases is compression.
Step 1: Identify What the Representation Is For Before deciding what to cut, establish the purpose of the compressed form. Who is it for? What decision or action does it need to enable? What understanding must be present in the receiver after they've processed the compressed version? The appropriate compression strategy is entirely downstream of this answer.
Framing check: Confirm the representation, its purpose, and the audience before continuing. State what you've identified in one sentence, then use AskUserQuestion:
Step 2: Classify Information as Essential, Reconstructable, or Discardable Work through the full source material and classify every component:
Before proceeding: Present your classification to the user for review. Use AskUserQuestion:
Step 3: Decide Lossy vs. Lossless Explicitly declare the compression mode for each component:
Step 4: Apply the Compression Produce the compressed representation. When compression is lossy, mark clearly — in the output or in a note — what has been dropped and what the receiver would need to know if they required the uncompressed form.
Step 5: Test Against the Purpose Ask: given only the compressed form, can the intended receiver accomplish the intended purpose? Run through the specific decision or action the representation is meant to support. If not, the compression is below the entropy floor — you have compressed past the point of usability.
Before proceeding, use the AskUserQuestion tool. State your interpretation of the situation in 1–2 sentences — what is being compressed, what must be preserved, and what the tension is — then ask:
Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.
Compression Brief
Classification
| Element | Classification | Rationale |
|---|---|---|
| [element] | Essential / Reconstructable / Discardable | [why] |
What is being dropped (lossy elements): [explicit statement of what information will not be recoverable from the compressed form, and why this is acceptable given the purpose]
Compressed Output:
[The compressed representation itself — the actual deliverable]
Reconstruction Note: [What a receiver would need to access if they required the full, uncompressed version]
Compression analysis is most powerful when the receiver and purpose are precisely defined — because what is "reconstructable" and "discardable" depends entirely on the receiver's prior knowledge and the purpose the representation serves. Vague audiences produce over-cautious compression (nothing gets cut because "someone might need it") or reckless compression (things get cut that a specific receiver needed badly).
The nearest-neighbour trap is conflating compression with simplification. Compression is about representation efficiency — minimising form while preserving function. Simplification is about reducing cognitive load. A simplified explanation may actually be longer than the original if it adds scaffolding the receiver needs. Use /s4h-communication-clarity-audit when the goal is readability rather than efficiency, and /s4h-information-redundancy when the question is specifically about repetition.
After delivering this output, use AskUserQuestion to offer the next move:
/s4h-information-redundancy — Examine whether the remaining redundancy is load-bearing or wasteful/s4h-communication-clarity-audit — Audit the compressed form for clarity and receiver fit/s4h-information-signal-noise — Check whether the compression preserved the signal or accidentally compressed it outnpx claudepluginhub human-avatar/skills-for-humanityApplies information theory to problems of signal, noise, compression, redundancy, and uncertainty. Routes to the right analysis tool based on your situation.
Distills verbose text to its concentrated essence without losing meaning or nuance. Triggers on 'distill', 'condense', 'tighten', 'shorten' requests for text or files.