Claude skill
Context Anchoring
Context Anchoring is a Claude skill in the Lattice plugin. Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development.
What it does
The description in the skill's SKILL.md, which Claude reads to decide when to use it:
Manage per-feature living documents that capture decisions, constraints, and reasoning across AI sessions during active development. Scoped to feature-level work — design, implementation, bugfix, refactor — not for codebase-wide assessments or product-wide specifications (those define their own document lifecycles). Handles creating new context documents, loading existing ones, and enriching them with new decisions. Use when starting a new feature, resuming work, making technical decisions, resolving questions, or when context needs to persist across sessions. Use this skill whenever the user mentions 'load context', 'update context', 'context doc', 'decisions', 'continue where we left off', 'what did we decide', or 'capture this decision'.
The skill's instructions (about 1,603 words) cover:
- Scope
- Config Resolution
- Why Context Anchors Exist
- Document Lifecycle
- Status Lifecycle
- Create Behavior
- Load Behavior
- Enrich Behavior
- Document Discovery
- Output Formats
- Integration with Other Skills
How to use it
- Context Anchoring comes inside the Lattice plugin, so you get it by installing that plugin, along with its 26 other skills. A plugin installs as one unit, with all its skills. The plugin's page has the install steps, and plugins are saved to your Claude account.
- Ask Claude for the task. When your request matches the skill's description, Claude loads it.
- To pick it yourself in Claude chat, type
/or click + and choose context-anchoring. In Claude Code and Cowork, type:/lattice:context-anchoring
Source
- Plugin
- Lattice
- SKILL.md
- View on GitHub
- Repo stars
- 214
- Repo last pushed
- Nov 14, 2026
- Checked
- Nov 16, 2026
More skills in Lattice
- Ddd RefinerFacilitate a structured conversation to define DDD guardrails for domain design within a repository.
- Design BlueprintRun a complete design workflow -- from establishing context through four progressive design levels (Capabilities, Components, Interactions, Contracts) to an approved blueprint.
- Design FirstGuide structured design thinking through 5 progressive levels before any code is written.
- Domain Driven DesignApply DDD tactical patterns when working with domain code, and validate proposed domain models before approval (design mode).
- Knowledge PrimingLoad project-specific context -- tech stack, architecture overview, directory layout, trusted sources, and conventions -- so that all skills operate with awareness of what this project actually is.
- Knowledge Priming RefinerFacilitate a structured conversation to create a project-specific knowledge base document.
- Language Idioms RefinerFacilitate a structured conversation to define language-specific idioms and patterns for a repository.
- Lattice InitGuided setup and upgrade-check experience for Lattice projects -- scans the repository, detects existing configuration and outdated conventions, suggests refiners and available upgrades in priority…
- Learning HarvestManage the operational learnings lifecycle — load prior learnings to inform current work, harvest new patterns worth preserving, and keep the document tight over time.
- Refactor SafelyRestructure existing code safely without changing externally observable behavior.
- Refiners UpdateUpdate existing Lattice standards after a significant change — the update-mode counterpart to lattice-init.
- Requirement ForgeGenerate structured feature specifications through a collaborative product interview.
- Requirement Forge RefinerFacilitate a structured conversation to define requirement standards for a project — epic and feature definitions, scenario structure, AC format, priority notation, status workflow, and naming…
- Requirement QualityApply requirement quality principles when generating or validating feature specifications.
- ReviewPerform a structured code review by composing validation checklists from relevant atoms based on what code changed.
- Review RefinerFacilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging.
- Secure CodingApply security-conscious thinking when generating or modifying code.
- Test QualityApply test quality principles when generating or reviewing test code.
- ArchitectureEnforce architectural rules when generating or modifying code, and validate proposed designs before approval (design mode).
- Architecture CompassArchitectural thinking partner for an existing repository — scans the codebase, conducts a structured interview, agrees on current architectural state and recommended direction, and produces a…
- Architecture RefinerFacilitate a structured conversation to define architecture principles for a repository.
- Bug FixInvestigate, reproduce, and safely fix a bug with regression protection.
- Clean CodeApply clean code principles when generating or modifying implementation code.
- Clean Code RefinerFacilitate a structured conversation to define clean code principles for a repository.