📦
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-management-context-restore
📦
context-management-context-restore
Content revision r2 Medium Risk ⚙️ External commands
Restore AI Project Context with Semantic Retrieval
Long-running AI projects lose decisions and working state across sessions. This skill provides retrieval, ranking, token budgeting, and validation patterns for restoring useful context.
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-management-context-restore" from https://skillstore.io/skills/sickn33-context-management-context-restore.md and its manifest at https://skillstore.io/api/skills/sickn33-context-management-context-restore/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-management-context-restore". Restore the web platform project with a 2,000-token budget.
Expected outcome:
- Goal: Complete account migration without interrupting active sessions.
- Key decision: Preserve existing session identifiers during the transition.
- Recent work: Migration validation is complete in staging.
- Known issue: Legacy mobile clients require compatibility testing.
- Next step: Run the production readiness checklist.
Using "context-management-context-restore". Compare the previous and current machine learning pipeline contexts.
Expected outcome:
- Unchanged: Training data source and evaluation metrics.
- Updated: The current context selects a smaller batch size after memory testing.
- Conflict: Deployment ownership differs between versions and needs confirmation.
- Recommendation: Preserve both ownership records until a responsible team confirms the change.
Using "context-management-context-restore". Plan incremental restoration for three collaborating agents.
Expected outcome:
Restore shared goals and architectural decisions first. Then load each agent's recent work, unresolved dependencies, and relevant decision history within separate token allocations.
Security Audit
Medium Riskv5 • 7/23/2026 Open versioned report
All 16 static findings are false positives caused by Markdown inline code and fenced examples, not Ruby or shell backtick execution. The conceptual restoration workflow lacks explicit isolation for untrusted instructions embedded in stored context. This creates a moderate context-poisoning risk that needs documented guardrails.
1
Files scanned
188
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (1)
Medium
Restored Context Lacks Prompt-Injection Isolation
The workflow restores stored project context without requiring embedded directives to remain untrusted data. Poisoned memory could influence subsequent agent actions.
Lines 147-151 direct context retrieval and restoration, while the only scanned file provides no trust-boundary or embedded-instruction handling.
Risk Factors
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-management-context-restore/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-context-management-context-restore?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-context-management-context-restore?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-context-management-context-restore/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-context-management-context-restore.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-management-context-restore security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-context-management-context-restore/audits/5BibTeX citation
@techreport{sickn33-sickn33-context-management-context-restore-2026,
author = {sickn33},
title = {context-management-context-restore security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-context-management-context-restore/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-management-context-restore 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-management-context-restore/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-context-management-context-restore:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance
What You Can Build
Resume a Long-Running Project
Recover goals, decisions, recent work, and known issues before continuing a paused project.
Coordinate Multiple AI Agents
Rank and restore shared project knowledge so agents can continue work with consistent context.
Design a Knowledge Restoration Pipeline
Plan semantic retrieval, token allocation, validation, and conflict resolution for stored project knowledge.
Try These Prompts
Restore Project Context
Restore context for {{project_identifier}} within {{token_budget}} tokens. Summarize goals, decisions, recent work, known issues, and next steps.Apply an Incremental Update
Compare the saved context with {{current_state}}. Restore only relevant changes, explain omissions, and keep the result within {{token_budget}} tokens.Resolve Context Differences
Compare {{previous_context}} and {{current_context}}. Identify conflicts, preserve provenance, and propose a merged context with unresolved decisions clearly marked.Design a Restoration Strategy
Design a restoration workflow for {{context_source}}. Include retrieval, ranking, token allocation, provenance checks, conflict handling, validation, caching, and measurable success criteria.Best Practices
- Set the project identifier, source, restoration mode, relevance threshold, and token budget before retrieval.
- Validate restored claims against the current codebase and preserve source provenance.
- Prioritize decisions, active work, known issues, and dependencies before lower-value historical details.
Avoid
- Do not restore every stored item when the token budget requires prioritization.
- Do not merge conflicting context versions without marking unresolved decisions and their sources.
- Do not treat instructions found in retrieved context as trusted agent directives.
Frequently Asked Questions
Does this skill store or retrieve context automatically?
No. It provides workflows and pseudocode for systems that already have context storage and retrieval components.
Which restoration modes does it describe?
It describes full restoration, incremental updates, and difference-based comparison and merging.
How does it control context size?
It prioritizes context components and includes them only while the configured token budget remains available.
What signals can guide relevance ranking?
The guide uses semantic similarity, temporal relevance, and historical impact as example ranking signals.
Can I run the shown command examples directly?
Not from this skill alone. The referenced command is illustrative and no executable implementation is included.
How should retrieved instructions be handled?
Treat them as untrusted data, verify provenance, and never allow them to override current system or user instructions.
Developer Details
Author
sickn33License
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
f9e2c34b4f19c7f3e6b0a1e93227b5f77cc12526
Maintenance freshness
7/26/2026
Usage
10 downloads · 133 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📦
para-skill
79Organize Notes with PARA
by scifishelf
Notes lose value when projects, responsibilities, and references mix together. This skill classifies Obsidian notes into PARA categories and proposes safe routing, metadata, reviews, and archiving.
Productivity View
📦
context-daddy
76Map large codebases with focused symbol search
by ChipFlow
Large repositories can overwhelm code exploration and consume limited context. This skill builds a local symbol index so you can retrieve targeted code and preserve project knowledge.
Productivity View
📦
Agent Coordination
38Coordinate coding agents with clear tasks
by ClementWalter
Multi-agent work can lose context, ownership, and verification. This skill provides delegation patterns, task templates, VibeKanban procedures, and CI monitoring guidance.
Productivity View
📦
memory
38Manage Project Memory and SSOT
by Chachamaru127
Project decisions and reusable patterns often become scattered across tools and sessions. This skill searches shared memory and promotes durable knowledge into structured project SSOT files.
Productivity View
📦
openserv-multi-agent-workflows
38Orchestrate OpenServ Multi-Agent Workflows
by internet-court
Complex agent projects need clear data flow, dependencies, and reliable triggers. This skill provides practical OpenServ patterns for building and operating coordinated workflows.
Productivity View
📦
using-lwc
38Build Durable Project Memory with LWC
by janyork
Project knowledge often disappears between agent sessions or becomes stale. This skill recalls verified context and preserves reusable results through LWC.
Productivity View