📦
content-creator
88Create Brand-Consistent Marketing Content
Marketing teams need content that stays consistent across channels. This skill helps plan, write, analyze, and optimize content for brand voice and SEO.
Writing & Content View
Skills context-compression
📦
context-compression
Content revision r2 Safe ⚙️ External commands
Compress Agent Context Without Losing Critical Details
Long agent sessions can lose critical decisions, file changes, and error details when history is compressed. This skill provides structured compression and probe-based evaluation methods that preserve useful context while reducing repeated exploration.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "context-compression" from https://skillstore.io/skills/sickn33-context-compression.md and its manifest at https://skillstore.io/api/skills/sickn33-context-compression/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "context-compression". Compress a debugging session involving an HTTP 401 error, a stale Redis connection, three modified files, and two failing tests.
Expected outcome:
Session Intent: resolve valid login requests returning HTTP 401. Root Cause: stale Redis session connection. Files Modified: Redis configuration, session service, and authentication tests. Current State: fourteen tests pass and two fail. Next Steps: repair mocks, run all tests, and validate staging.
Using "context-compression". Recommend a compression method for a long coding agent session where file tracking and readable summaries are essential.
Expected outcome:
Recommendation: anchored iterative summarization. Preserve dedicated sections for files, decisions, current state, and next steps. Merge only newly truncated history into the existing summary. Validate retention with artifact and continuation probes.
Security Audit
Safev5 • 7/23/2026 Open versioned report
All three external-command findings are Markdown fence markers, not executable Ruby or shell syntax. The reconnaissance findings are technical examples, and no prompt injection or malicious intent appears in SKILL.md.
1
Files scanned
271
Lines analyzed
0
Review items
0
False positives ignored
Risk Factors
⚙️ External commands (3)
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-context-compression/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-context-compression?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-context-compression?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-context-compression/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-context-compression.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). context-compression security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-context-compression/audits/5BibTeX citation
@techreport{sickn33-sickn33-context-compression-2026,
author = {sickn33},
title = {context-compression security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-context-compression/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "context-compression security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-context-compression/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-context-compression:audit:5"
description: "Skillstore immutable audit report identifier"
Compare variants
3 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
muratcankoylan Recommended
muratcankoylan-context-compression
Skillstore Score 81
Evidence Confidence High
Skillstore usage 48
Updated
2026-08-21
chakshugautam-context-compression
Skillstore Score 80
Evidence Confidence High
Skillstore usage 93
Updated
2026-08-21
sickn33 Current
sickn33-context-compression
Skillstore Score 78
Evidence Confidence High
Skillstore usage 31
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance
What You Can Build
Preserve Long Coding Sessions
Create durable summaries that preserve modified files, decisions, errors, test results, and next actions during long coding sessions.
Plan Context Window Management
Select trigger thresholds and compression methods for agents operating near model context limits.
Evaluate Compression Quality
Build recall, artifact, continuation, and decision probes that measure whether compressed context supports task completion.
Try These Prompts
Create a Structured Summary
Compress the provided session into Session Intent, Files Modified, Decisions Made, Current State, and Next Steps. Preserve exact file paths, errors, and test results.
Choose a Compression Strategy
Compare anchored iterative, opaque, and regenerative compression for this workload. Recommend one approach using context size, interpretability, and refetching costs.
Design Functional Probes
Create recall, artifact, continuation, and decision probes for the supplied compressed session. Include expected answers and explain what each probe measures.
Build a Tokens-Per-Task Experiment
Design a tokens-per-task experiment comparing two compression strategies across repeated compression cycles. Measure token savings, refetching, factual accuracy, artifact retention, and completion quality.
Best Practices
- Preserve exact file paths, errors, decisions, and test status in dedicated sections
- Merge newly truncated content into an anchored summary instead of regenerating everything
- Evaluate tokens per completed task, including refetching and repeated exploration
Avoid
- Optimize only for the smallest possible summary
- Regenerate the entire summary without checking for information drift
- Trust a high compression ratio without functional retention probes
Frequently Asked Questions
What compression approach does this skill prefer?
It generally favors anchored iterative summarization when file tracking, readability, and long-session continuity matter.
Does this skill execute compression automatically?
No. It provides design guidance, summary structures, evaluation dimensions, and example workflows.
Why measure tokens per task?
A smaller request can still waste tokens when missing details force repeated searches, tool calls, or reasoning.
When should compression begin?
The guidance suggests testing thresholds near 70 to 80 percent context utilization, then adapting them to workload behavior.
How can teams test summary quality?
Use factual recall, artifact tracking, continuation, and decision probes with expected answers.
Can compression preserve every file detail?
No. Artifact tracking remains difficult and may require a separate file-state index.
Developer Details
Author
sickn33License
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Repository
https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/context-compressionRef
f9e2c34b4f19c7f3e6b0a1e93227b5f77cc12526
Maintenance freshness
7/26/2026
Usage
20 downloads · 160 views
File structure
📄 SKILL.md
More from sickn33
View all📦
prompt-engineering-patterns
85Improve LLM Prompts With Proven Patterns
Inconsistent prompts waste time and make AI outputs hard to trust. This skill guides prompt design with reusable patterns, examples, evaluation steps, and optimization workflows.
Productivity View
📦
senior-fullstack
82Build Fullstack Apps with Senior Patterns
Teams need consistent setup, architecture, and review guidance for modern web applications. This skill provides scaffolders, workflow references, and quality prompts for React, Next.js, Node.js, GraphQL, and PostgreSQL projects.
Coding & Development View
📦
senior-architect
81Design Scalable Software Architectures
Architecture decisions are hard to compare across web, mobile, backend, and cloud systems. This skill provides structured guides and local scaffold scripts for reports, dependency review, and trade-off documentation.
Coding & Development View
📦
prompt-engineer
81Optimize AI Prompts With Prompt Engineer
Writing clear prompts is hard when goals are vague or complex. This skill turns rough requests into structured prompts using proven prompt frameworks.
Productivity View
📦
product-manager-toolkit
80Prioritize Product Work With Research Insights
Product teams need faster ways to rank features, synthesize interviews, and document decisions. This skill provides RICE scoring, interview analysis, and PRD templates for structured planning.
Productivity View
Related Skills
View all📦
context-optimization
80Optimize AI Context Windows
by ChakshuGautam
Long AI sessions can waste tokens, slow responses, and lose important context. This skill gives Claude, Codex, and Claude Code practical patterns for compacting, masking, caching, and budgeting context.
Productivity View
📦
summarize
78Summarize URLs, Files, and Media
by steipete
Long sources make key information difficult to review. This skill uses the Summarize CLI to extract or condense URLs, documents, transcripts, audio, and video.
Productivity View
📦
caveman-learn
77Reduce Agent Token Usage
by juliusbrussee
Large configuration files and repeated context increase token usage. This skill reviews Caveman reports and applies measured changes with individual approval.
Productivity View
📦
error-memory
75Track Project Error Lessons
by Aceek
Teams lose time when agents repeat the same project mistakes. This skill records concise error lessons in a shared project file.
Productivity View
📦
handoff
75Create a Clear Agent Handoff
by mattpocock
Long conversations make session changes difficult and can expose sensitive details. This skill creates a concise, redacted handoff that references existing artifacts.
Productivity View
📦
self-improving-agent
70Improve Skills From Validated Feedback
by charon-fan
Repeated workflow lessons can be lost or applied without enough evidence. This skill captures structured experiences and creates traceable proposals before durable guidance changes.
Productivity View