Autospec Analyze

autospec-analyze

This Agent Skill is generated from autospec.analyze. When the user invokes "$autospec-analyze" or "/autospec.analyze", load and follow these instructions directly. Treat the text after the skill or command name as "$ARGUMENTS". Do not route back through "autospec analyze"; this skill is the prompt for the stage.

Project specs directory: ./specs

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Goal

Identify inconsistencies, duplications, ambiguities, and underspecified items across the core artifacts (spec, plan, tasks) before implementation. This command MUST run only after $autospec-tasks has successfully produced a complete tasks file.

Operating Constraints

STRICTLY READ-ONLY: Do not modify any files. Output a structured analysis YAML file. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).

Constitution Authority: The project constitution (.autospec/constitution.yaml or AGENTS.md, falling back to agent-specific file like CLAUDE.md) is non-negotiable within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks.

Pre-computed Context

The following paths have been pre-computed and are available for use:

• FEATURE_DIR: {{.FeatureDir}}
• FEATURE_SPEC: {{.FeatureSpec}}

Execution Steps

1. Load Artifacts (Progressive Disclosure)

Load only the minimal necessary context from each artifact:

From spec.yaml:

• Overview/Context
• Functional Requirements
• Non-Functional Requirements
• User Stories
• Edge Cases (if present)

From plan.yaml:

• Architecture/stack choices
• Data Model references
• Phases
• Technical constraints

From tasks.yaml:

• Task IDs
• Descriptions
• Phase grouping
• Parallel markers
• Referenced file paths

From constitution:

• Load .autospec/constitution.yaml or AGENTS.md (falling back to agent-specific file like CLAUDE.md) for principle validation

2. Build Semantic Models

Create internal representations (do not include raw artifacts in output):

• Requirements inventory: Each functional + non-functional requirement with a stable key
• User story/action inventory: Discrete user actions with acceptance criteria
• Task coverage mapping: Map each task to one or more requirements or stories
• Constitution rule set: Extract principle names and MUST/SHOULD normative statements

3. Detection Passes (Token-Efficient Analysis)

Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.

A. Duplication Detection

• Identify near-duplicate requirements
• Mark lower-quality phrasing for consolidation

B. Ambiguity Detection

• Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria
• Flag unresolved placeholders (TODO, TKTK, ???, <placeholder>, etc.)

C. Underspecification

• Requirements with verbs but missing object or measurable outcome
• User stories missing acceptance criteria alignment
• Tasks referencing files or components not defined in spec/plan

D. Constitution Alignment

• Any requirement or plan element conflicting with a MUST principle
• Missing mandated sections or quality gates from constitution

E. Coverage Gaps

• Requirements with zero associated tasks
• Tasks with no mapped requirement/story
• Non-functional requirements not reflected in tasks (e.g., performance, security)