spec-generator
Specification generator - 7 phase document chain producing product brief, PRD, architecture, epics, and issues. Agent-delegated heavy phases (2-5, 6.5) with Codex review gates. Triggers on "generate spec", "create specification", "spec generator", "workflow:spec".
86
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that concisely communicates a complex multi-phase specification generation workflow. It names specific outputs (product brief, PRD, architecture, epics, issues), describes the execution model (agent-delegated phases with review gates), and provides explicit trigger terms. The description uses third-person voice appropriately and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and outputs: '7 phase document chain producing product brief, PRD, architecture, epics, and issues.' Also mentions agent-delegated phases and Codex review gates, which are concrete implementation details. | 3 / 3 |
Completeness | Clearly answers both 'what' (7-phase document chain producing specific deliverables with agent delegation and review gates) and 'when' (explicit triggers listed). The 'Triggers on' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Includes explicit natural trigger terms: 'generate spec', 'create specification', 'spec generator', 'workflow:spec'. These cover common variations a user would naturally say when requesting specification generation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: specification generation through a specific multi-phase workflow. The combination of 'spec generator', specific deliverables (PRD, architecture, epics), and the phased workflow approach makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability, workflow clarity, and progressive disclosure — it provides a comprehensive, well-structured orchestration guide with concrete code, clear phase sequencing, validation gates, and well-organized references to detailed phase documents. However, it is severely over-verbose for a SKILL.md file; the agent registry, fork context strategy tables with rationale, full lifecycle management protocols, and detailed error handling tables should be extracted into referenced specification files rather than occupying the main skill body. The content is accurate and thorough but consumes far more tokens than necessary for the orchestrator overview role it serves.
Suggestions
Extract the Agent Registry, Fork Context Strategy, Lifecycle Management, and Timeout Protocol sections into a separate file (e.g., specs/agent-protocols.md) and reference it from SKILL.md — these are operational details that don't need to be in the main context.
Move the detailed Error Handling table to a separate file (e.g., specs/error-handling.md) and keep only a brief summary of the fallback chain in SKILL.md.
Consolidate the Reference Documents by Phase section — the phase file references are already embedded in the Execution Flow; having them repeated in a separate section is redundant.
Remove the Fork Context Strategy rationale column and the explanatory paragraph ('Why all fork_context: false') — Claude doesn't need justification for design decisions, only the configuration values.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Contains extensive tables, diagrams, and protocol details that could be split into referenced files. Much of this (agent registry, fork context strategy rationale, lifecycle management, timeout tables) is operational detail that should live in separate phase/spec files rather than the main SKILL.md. The skill explains architecture decisions and rationale that Claude doesn't need inline. | 1 / 3 |
Actionability | Highly actionable with concrete code snippets for spawn_agent calls, context envelope templates, validation logic, directory setup, state management JSON schemas, and specific CLI commands. The execution flow is detailed with exact file paths, timeout values, and error handling procedures. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (Phase 0 through 7), explicit validation checkpoints after each agent phase (file existence checks, spec-config.json verification), feedback loops (Phase 6 -> 6.5 auto-fix with max 2 iterations), timeout protocols with escalation paths, and error recovery for every phase. The readiness check scoring thresholds (>=80% pass, 60-79% review, <60% fail) provide clear decision gates. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to phase-specific documents (phases/01-discovery.md through phases/07-issue-export.md), template files, and spec documents. All references are one level deep with organized tables showing document, purpose, and when to use. The main file serves as an orchestration overview pointing to detailed phase docs. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (522 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
0f8e801
- Reviewed
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.