agent-specification
Agent skill for specification - invoke with $agent-specification
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-specification31
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
46%
15%Payment Processing Service Requirements
Requirements document structure and YAML requirement formatting
FR YAML format
0%
0%
FR ID scheme
28%
0%
FR acceptance criteria
0%
33%
FR priority field
0%
0%
NFR YAML format
0%
0%
NFR ID scheme
28%
0%
NFR category field
0%
0%
NFR measurement field
0%
37%
SRS Introduction section
100%
100%
Definitions subsection
42%
100%
SRS section numbering
0%
100%
No vague qualifiers
100%
100%
Measurable performance NFR
100%
100%
Without context: $0.3689 · 2m 14s · 12 turns · 18 in / 7,573 out tokens
With context: $0.5693 · 2m 50s · 20 turns · 271 in / 9,509 out tokens
54%
30%Appointment Booking Feature Specification
Use case definition and Gherkin acceptance criteria
Use case YAML format
0%
0%
UC ID field
0%
57%
UC actor field
0%
12%
UC preconditions field
0%
12%
UC numbered flow
0%
14%
UC postconditions field
0%
12%
UC exceptions field
0%
12%
Gherkin format
33%
100%
Happy path scenario
66%
100%
Failure scenario
66%
100%
Constraints three categories
100%
100%
Constraint YAML structure
0%
100%
Without context: $0.2964 · 1m 57s · 13 turns · 20 in / 6,421 out tokens
With context: $0.6127 · 3m · 21 turns · 184 in / 10,368 out tokens
55%
10%Team Collaboration Tool Technical Specification
Data model, API specification, and constraint analysis
Data model YAML format
0%
0%
Entity attributes with types
44%
77%
Primary key annotation
100%
100%
Entity relationships
44%
100%
Foreign key annotation
100%
100%
OpenAPI version declaration
0%
0%
OpenAPI info block
0%
0%
OpenAPI paths block
0%
0%
Request body schema
0%
0%
Multiple response codes
75%
100%
Validation checklist present
66%
77%
Checklist covers key areas
100%
90%
Without context: $0.2071 · 1m 13s · 8 turns · 13 in / 5,024 out tokens
With context: $0.6061 · 2m 24s · 23 turns · 31 in / 9,709 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.