context-compression SKILL.md skillA
context-compression from amey-thakur/ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add amey-thakur/ai-skills/context-compression@git:20260728.fe84bd4Pins git:20260728.fe84bd4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- amey-thakur/ai-skills
- Path
skills/ai-memory-rag/context-compression/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260728.fe84bd4, committed Jul 28, 2026
- Size
- 1,917 bytes
- Repository stars
- 13
- License
- MIT
Reduce retrieved material to what the model needs, through filtering, extraction, and summarisation, before it reaches the prompt. Use when retrieved context is large, mostly irrelevant, or crowding out reasoning.
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
# Context compression Retrieval returns passages that are relevant to the query; much of each passage is not relevant to the answer. Compression removes the excess before it consumes context, which improves both cost and the model's attention on what matters. ## Method 1. **Filter before compressing.** Dropping a passage that should not have been retrieved is cheaper and safer than summarising it (see retrieval-reranking). 2. **Extract the relevant spans.** Pulling the sentences that bear on the question preserves exact wording, which matters for citation and for faithfulness (see citation-grounding). 3. **Prefer extraction to summarisation.** Summarising introduces a paraphrase step that can distort, while extraction cannot invent. 4. **Compress per passage, not across them.** Merging passages loses provenance and blends sources that should stay distinguishable. 5. **Keep the structure that carries meaning.** Headings, dates, and identifiers are small and disproportionately useful for the model's reasoning. 6. **Budget explicitly.** Decide how much context the answer step gets and compress to fit, rather than sending everything and letting the …
Read the whole file at its exact version.
How to install
mdr add amey-thakur/ai-skills/context-compression@sha256:79ecfe67f5758199The line at the top of this page pins the label git:20260728.fe84bd4, 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_rvrtybdoo4hzaxli)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 28, 2026.
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 (1917 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
amey-thakur/ai-skills · 13 stars · license MIT · pushed 2026-09-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rvrtybdoo4hzaxli GET https://markdownregistry.com/api/v1/resolve?ref=amey-thakur/ai-skills/context-compression GET https://markdownregistry.com/api/v1/blob/79ecfe67f57581994b9d1ffd3e51f1f94d206cda4bfa630acc13e27cef15b3c3
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.
More from amey-thakur/ai-skills
Every file in amey-thakur/ai-skills