Spec
Write a comprehensive product or engineering specification before implementation. Use when the user asks for `/spec`, PRDs, feature specs, API specs, refactor specs, acceptance criteria, user stories, edge cases, or open decision tracking before code is written.
Install
$ agentstack add skill-eigent-ai-agent-skills-spec ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-eigent-ai-agent-skills-spec) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Spec
Overview
Use this skill to turn a feature, API, refactor, or product idea into a clear specification that can feed planning and implementation. The output should reduce ambiguity before code is written.
Workflow
- Identify the problem, goal, users, constraints, and non-goals.
- Capture the current behavior or system context when relevant.
- Define user stories or use cases with acceptance criteria.
- Specify functional requirements, edge cases, error states, permissions, and data handling.
- Include API, UI, migration, observability, performance, or rollout requirements when applicable.
- List open decisions and assumptions explicitly.
- Keep the spec implementation-aware but avoid over-prescribing internal code structure unless required.
Output Pattern
Use this structure by default:
- Summary.
- Problem statement.
- Goals and non-goals.
- Users and use cases.
- Requirements.
- Acceptance criteria.
- Edge cases and risks.
- Observability, rollout, and rollback notes.
- Open questions.
Example Prompts
/spec - Build a CSV export feature for our analytics dashboard. Users need to export filtered data with custom date ranges. Support up to 100k rows./spec - Design a public webhooks API for our platform. Third-party apps need to subscribe to user events and receive payloads reliably with retry logic./spec - Refactor our authentication flow to support SSO. We need to keep existing email/password working and add Google and GitHub OAuth without breaking current sessions.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: eigent-ai
- Source: eigent-ai/agent-skills
- License: Apache-2.0
- Homepage: https://www.eigent.ai/skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.