semantic-compress SKILL.md skillA
semantic-compress from bjcoombs/ai-native-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add bjcoombs/ai-native-toolkit/semantic-compress@git:20260604.2d1f4c7Pins git:20260604.2d1f4c7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- bjcoombs/ai-native-toolkit
- Path
skills/semantic-compress/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260604.2d1f4c7, committed Jun 4, 2026
- First version recorded
- Jun 3, 2026
- Size
- 23,631 bytes
- Repository stars
- 32
- License
- Apache-2.0
Make an LLM-directed document smaller while preserving what it does. Two modes: a local span-level core->pointer pass, and an A/B-validated distill loop that produces the smallest document that behaves the same as the original. Point at core knowledge the model already holds (a concept name activates it); keep project-specific detail explicit and verbatim. TRIGGER when asked to compress, tighten, shorten, or strip a prompt / instruction / system message meant for an LLM; to distill a skill; to…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Semantic Compress Make a document written **for an LLM reader** smaller while preserving what it *does*. The essence of an LLM-directed document is **behavioural**, not textual - the behaviour it induces in the reading model across the tasks it handles. Compression splits content into two kinds and treats each correctly: - **Core knowledge** - anything in the model's training (named concepts, standard definitions, common-domain background). Replace the explanation with a **pointer**: the bare concept name or a short cue that activates the right knowledge. A pointer costs a few tokens and reliably switches on the model's existing understanding; a full explanation is wasted tokens, and *deleting the concept entirely* gambles that it is already active in the model's reasoning - often it is not, and disambiguation suffers. - **Project / bespoke knowledge** - anything the model cannot know from training: specific facts, local decisions, constraints, and non-standard twists on a known concept. Keep these **explicit and verbatim**. The model has no other source for them. …
Read the whole file at its exact version.
How to install
mdr add bjcoombs/ai-native-toolkit/semantic-compress@sha256:6af22bf230a5c465The line at the top of this page pins the label git:20260604.2d1f4c7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_wad3wuproao5db65)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 3, 2026 and Jun 4, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260604.2d1f4c7 latest | 2026-06-04 | 2d1f4c7 | 23,631 B | A | view · diff |
| git:20260603.2be704a | 2026-06-03 | 2be704a | 24,272 B | A | view · diff |
| git:20260603.c479e6f | 2026-06-03 | c479e6f | 24,309 B | A | view · diff |
| git:20260603.4d98a33 | 2026-06-03 | 4d98a33 | 16,480 B | A | view · diff |
| git:20260603.17e8bfa | 2026-06-03 | 17e8bfa | 16,531 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (23631 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
bjcoombs/ai-native-toolkit · 32 stars · license Apache-2.0 · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wad3wuproao5db65 GET https://markdownregistry.com/api/v1/resolve?ref=bjcoombs/ai-native-toolkit/semantic-compress GET https://markdownregistry.com/api/v1/blob/6af22bf230a5c4657e34e33421408ff37f98ac952760ef904607ce0d90c24f98
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.