reverseclabs/spikee/target-implementation
Claude Code and agent skill by reverseclabs/spikee
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Guide for implementing Spikee target modules
Install
npx vskill@latest install reverseclabs/spikee/target-implementationSKILL.md
Spikee Target Implementation Skill
This skill guides users through implementing a Spikee target module.
Domain
Creating Spikee target modules for testing LLMs, LLM applications, and guardrails.
Capabilities
This skill guides users through implementing a Spikee Target module by:
- Determining target type (LLM vs Guardrail vs Multi-turn)
- Selecting appropriate base class (Target, SimpleMultiTarget, or MultiTarget)
- Implementing required methods (get_description, get_available_option_values, process_input)
- Configuring authentication patterns (API keys, OAuth2, Managed Identity, GCP ADC, etc.)
- Handling guardrail triggers and response parsing
- Configuring proxy and TLS options
User Interaction
The skill helps users:
- Gather target system information (HTTP request/response samples, authentication details)
- Answer a decision tree to select the correct base class
- Match their authentication/transport pattern to Spikee templates
- Implement the target with all required error handling
Common Use Cases
- Creating targets for custom LLM APIs (OpenAI-compatible and native SDKs)
- Implementing multi-turn chatbot targets with session management
- Building guardrail targets that return bool (True=bypassed, False=blocked)
- Adding authentication handlers (API keys, bearer tokens, OAuth2, Azure IMDS, GCP ADC)
Dependencies
- Requires Spikee installed with target templates
- Follows spikee.templates module conventions
Available Base Classes
| Scenario | Base Class | Import | |
|---|---|---|---|
| Single-turn LLM or guardrail | Target | from spikee.templates.target import Target | |
| Multi-turn, spikee-managed history | SimpleMultiTarget | from spikee.templates.simple_multi_target import SimpleMultiTarget | |
| Multi-turn, custom state | MultiTarget | from spikee.templates.multi_target import MultiTarget |
Authentication Patterns Supported
- Static API Key / Bearer Token
- Static Session Cookie
- Username / Password (Form Login)
- Azure Managed Identity (IMDS)
- GCP Application Default Credentials
- Auth0 / OAuth2 Refresh Token
- Internal JWT (Self-Fetched)
Response Handling
- LLM targets: Return string (LLM reply), raise GuardrailTrigger for blocks
- Guardrail targets: Return bool (True=bypassed, False=blocked)
Output Format
Generated file: {application}_{feature}.py in workspace/targets/
Related Resources
- .github/skills/target-implementation/target-instructions.md (source documentation)
- spikee/templates/target.py (base class template)
- spikee/templates/simple_multi_target.py (multi-turn template)
- spikee/templates/multi_target.py (complex multi-turn template)
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.github/skills/target-implementation/SKILL.md
Popularity
- Repository stars
- 230
- Repository forks
- 43
- 7-day trend score
- 27
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/reverseclabs/spikee/target-implementation)