synaptiai/agent-capability-standard/generate
Claude Code and agent skill by synaptiai/agent-capability-standard
- community
Checking that the SKILL.md file is still in the repository.
Create a new artifact (text, code, plan, data) under specified constraints. Use when producing content, writing code, designing solutions, or synthesizing outputs.
Install
npx vskill@latest install synaptiai/agent-capability-standard/generateSKILL.md
Intent
Produce a new artifact that satisfies specified constraints and serves a defined purpose. Generation is creative synthesis bounded by requirements, not mere retrieval or transformation.
Success criteria:
- Artifact satisfies all stated constraints
- Rationale explains design decisions
- Quality signals demonstrate fitness for purpose
- Safety considerations documented
Compatible schemas:
schemas/output_schema.yaml
Inputs
| Parameter | Required | Type | Description | ||
|---|---|---|---|---|---|
specification | Yes | string\ | object | What to generate | |
format | No | string | Output format: markdown, json, yaml, typescript, etc. | ||
constraints | No | object | Requirements the artifact must satisfy |
Inputs not listed here are outside the capability's contract: a workflow step that binds them gets W604 (STANDARD v1.1 §5.5).
Procedure
1) Clarify artifact requirements: Ensure constraints are understood
- Must-have: absolute requirements (format, structure, compatibility)
- Should-have: preferences (style, conventions, optimization)
- Must-not-have: exclusions (patterns to avoid, security constraints)
2) Gather context: Collect relevant reference material
- Read existing code/docs for style consistency
- Identify patterns to follow or avoid
- Understand integration points and dependencies
3) Design approach: Plan the generation strategy
- Outline structure before detailed generation
- Consider multiple approaches if request is complex
- Document key design decisions
4) Generate artifact: Produce the content systematically
- Follow identified patterns and conventions
- Satisfy constraints in priority order
- Document any constraints that conflict
5) Validate constraints: Verify each constraint is satisfied
- Mark each constraint as satisfied/unsatisfied
- Note any compromises or partial satisfaction
6) Assess quality: Evaluate fitness for purpose
- Correctness: Does it work as intended?
- Completeness: Is anything missing?
- Maintainability: Is it understandable and modifiable?
- Safety: Are there security or reliability concerns?
7) Document rationale: Explain why this design
- Key decisions and their reasoning
- Alternatives considered and why rejected
- Known limitations or future considerations
8) Ground claims: Reference sources that informed generation
Output Contract
Return a structured object:
Field Definitions
| Field | Type | Description | ||
|---|---|---|---|---|
content | string\ | object | The generated artifact itself | |
metadata | object | Generation metadata: type (category of content) and format | ||
constraints_used | array | Evaluation of constraint satisfaction | ||
rationale | string | Design decision explanation | ||
alternatives_considered | array | Other approaches that were rejected | ||
quality_signals | array | Quality metrics and assessments | ||
confidence | number | 0.0-1.0 in artifact fitness | ||
evidence_anchors | array[string] | Sources that informed generation | ||
safety_notes | array[string] | Security/reliability concerns | ||
next_actions | array[string] | Recommended follow-up steps |
Examples
Example 1: Generate API Endpoint
Input:
Output:
Evidence pattern: Read existing codebase for patterns, reference library documentation for best practices.
Example 2: Generate Configuration Schema
Input:
Output:
Verification
- [ ] All required constraints marked as satisfied
- [ ] Artifact format matches requested format
- [ ] Quality signals include at least correctness and completeness
- [ ] Rationale explains key design decisions
- [ ] Safety notes address security considerations
Verification tools: Read (for pattern consistency), schema validators, linters
Safety Constraints
mutation: falserequires_checkpoint: falserequires_approval: falserisk: low
Capability-specific rules:
- Generated code must not contain hardcoded secrets or credentials
- Flag any security-sensitive patterns in generated content
- Do not generate content that violates constraints - report conflicts instead
- Include safety_notes for any security-relevant artifact
Composition Patterns
Commonly follows:
compare- Generate solution based on comparison winnerplan- Generate artifacts specified in planidentify- Generate based on identified requirementsdiscover- Generate to address discovered gaps
Commonly precedes:
verify- Generated artifacts should be verifiedact- Generated content may be written to filescritique- Generated plans should be critiqued
Anti-patterns:
- Never generate without constraints (unbounded generation)
- Avoid generate for retrieval (use
searchorretrieve) - Do not use generate for analysis (use
estimate,compare, etc.)
Workflow references:
- See
reference/composition_patterns.md#capability-gap-analysisfor generate-plan usage - See
reference/composition_patterns.md#debug-code-changefor code generation in fixes
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/generate/SKILL.md
Popularity
- 7-day trend score
- 0
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/synaptiai/agent-capability-standard/generate)