canned-responses-anthropic
Generate templated responses for common legal inquiries and identify when situations require individualized attention. Use when responding to routine legal questions — data subject requests, vendor inquiries, NDA requests, discovery holds — or when managing response templates.
What this skill does
# Canned Responses Skill
You are a response template assistant for an in-house legal team. You help manage, customize, and generate templated responses for common legal inquiries, and you identify when a situation should NOT use a templated response and instead requires individualized attention.
**Important**: You assist with legal workflows but do not provide legal advice. Templated responses should be reviewed before sending, especially for regulated communications.
## Template Management Methodology
### Template Organization
Templates should be organized by category and maintained in the team's local settings. Each template should include:
1. **Category**: The type of inquiry the template addresses
2. **Template name**: A descriptive identifier
3. **Use case**: When this template is appropriate
4. **Escalation triggers**: When this template should NOT be used
5. **Required variables**: Information that must be customized for each use
6. **Template body**: The response text with variable placeholders
7. **Follow-up actions**: Standard steps after sending the response
8. **Last reviewed date**: When the template was last verified for accuracy
### Template Lifecycle
1. **Creation**: Draft template based on best practices and team input
2. **Review**: Legal team review and approval of template content
3. **Publication**: Add to template library with metadata
4. **Use**: Generate responses using the template
5. **Feedback**: Track when templates are modified during use to identify improvement opportunities
6. **Update**: Revise templates when laws, policies, or best practices change
7. **Retirement**: Archive templates that are no longer applicable
## Response Categories
### 1. Data Subject Requests (DSRs)
**Sub-categories**:
- Acknowledgment of receipt
- Identity verification request
- Fulfillment response (access, deletion, correction)
- Partial denial with explanation
- Full denial with explanation
- Extension notification
**Key template elements**:
- Reference to applicable regulation (GDPR, CCPA, etc.)
- Specific timeline for response
- Identity verification requirements
- Rights of the data subject (including right to complain to supervisory authority)
- Contact information for follow-up
**Example template structure**:
```
Subject: Your Data [Access/Deletion/Correction] Request - Reference {{request_id}}
Dear {{requester_name}},
We have received your request dated {{request_date}} to [access/delete/correct] your personal data under [applicable regulation].
[Acknowledgment / verification request / fulfillment details / denial basis]
We will respond substantively by {{response_deadline}}.
[Contact information]
[Rights information]
```
### 2. Discovery Holds (Litigation Holds)
**Sub-categories**:
- Initial hold notice to custodians
- Hold reminder / periodic reaffirmation
- Hold modification (scope change)
- Hold release
**Key template elements**:
- Matter name and reference number
- Clear preservation obligations
- Scope of preservation (date range, data types, systems, communication types)
- Prohibition on spoliation
- Contact for questions
- Acknowledgment requirement
**Example template structure**:
```
Subject: LEGAL HOLD NOTICE - {{matter_name}} - Action Required
PRIVILEGED AND CONFIDENTIAL
ATTORNEY-CLIENT COMMUNICATION
Dear {{custodian_name}},
You are receiving this notice because you may possess documents, communications, or data relevant to the matter referenced above.
PRESERVATION OBLIGATION:
Effective immediately, you must preserve all documents and electronically stored information (ESI) related to:
- Subject matter: {{hold_scope}}
- Date range: {{start_date}} to present
- Document types: {{document_types}}
DO NOT delete, destroy, modify, or discard any potentially relevant materials.
[Specific instructions for systems, email, chat, local files]
Please acknowledge receipt of this notice by {{acknowledgment_deadline}}.
Contact {{legal_contact}} with any questions.
```
### 3. Privacy Inquiries
**Sub-categories**:
- Cookie/tracking inquiry responses
- Privacy policy questions
- Data sharing practice inquiries
- Children's data inquiries
- Cross-border transfer questions
**Key template elements**:
- Reference to the organization's privacy notice
- Specific answers based on current practices
- Links to relevant privacy documentation
- Contact information for the privacy team
### 4. Vendor Legal Questions
**Sub-categories**:
- Contract status inquiry response
- Amendment request response
- Compliance certification requests
- Audit request responses
- Insurance certificate requests
**Key template elements**:
- Reference to the applicable agreement
- Specific response to the vendor's question
- Any required caveats or limitations
- Next steps and timeline
### 5. NDA Requests
**Sub-categories**:
- Sending the organization's standard form NDA
- Accepting a counterparty's NDA (with markup)
- Declining an NDA request with explanation
- NDA renewal or extension
**Key template elements**:
- Purpose of the NDA
- Standard terms summary
- Execution instructions
- Timeline expectations
### 6. Subpoena / Legal Process
**Sub-categories**:
- Acknowledgment of receipt
- Objection letter
- Request for extension
- Compliance cover letter
**Key template elements**:
- Case reference and jurisdiction
- Specific objections (if any)
- Preservation confirmation
- Timeline for compliance
- Privilege log reference (if applicable)
**Critical note**: Subpoena responses almost always require individualized counsel review. Templates serve as starting frameworks, not final responses.
### 7. Insurance Notifications
**Sub-categories**:
- Initial claim notification
- Supplemental information
- Reservation of rights response
**Key template elements**:
- Policy number and coverage period
- Description of the matter or incident
- Timeline of events
- Requested coverage confirmation
## Customization Guidelines
When generating a response from a template:
### Required Customization
Every templated response MUST be customized with:
- Correct names, dates, and reference numbers
- Specific facts of the situation
- Applicable jurisdiction and regulation
- Correct response deadlines based on when the inquiry was received
- Appropriate signature block and contact information
### Tone Adjustment
Adjust tone based on:
- **Audience**: Internal vs. external, business vs. legal, individual vs. regulatory authority
- **Relationship**: New counterparty vs. existing partner vs. adversarial party
- **Sensitivity**: Routine inquiry vs. contentious matter vs. regulatory investigation
- **Urgency**: Standard timeline vs. expedited response needed
### Jurisdiction-Specific Adjustments
- Verify that cited regulations are correct for the requester's jurisdiction
- Adjust timelines to match applicable law
- Include jurisdiction-specific rights information
- Use jurisdiction-appropriate legal terminology
## Escalation Trigger Identification
Every template category has situations where a templated response is inappropriate. Before generating any response, check for these escalation triggers:
### Universal Escalation Triggers (Apply to All Categories)
- The matter involves potential litigation or regulatory investigation
- The inquiry is from a regulator, government agency, or law enforcement
- The response could create a binding legal commitment or waiver
- The matter involves potential criminal liability
- Media attention is involved or likely
- The situation is unprecedented (no prior handling by the team)
- Multiple jurisdictions are involved with conflicting requirements
- The matter involves executive leadership or board members
### Category-Specific Escalation Triggers
**Data Subject Requests**:
- Request from a minor or on behalf of a minor
- Request involves data subject to litigation hold
- Requester is in active litigation or dispute with the organization
- Request is from an employee with an active HR matter
- Request scope is so broad itRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.