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 description that concisely communicates the skill's purpose, specific outputs, process structure, and explicit trigger terms. It uses third-person voice appropriately and provides enough detail to distinguish it from other skills. The only minor improvement could be slightly expanding the trigger terms to include variations like 'PRD' or 'product requirements' as standalone triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and outputs: '7 phase document chain producing product brief, PRD, architecture, epics, and issues' along with details about agent-delegated phases and Codex review gates. | 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 needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: a multi-phase specification generation workflow with specific deliverables (PRD, architecture, epics, issues) and a unique process (agent-delegated phases, Codex review gates). 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 is a highly actionable and well-structured orchestration skill with excellent workflow clarity, explicit validation gates, and clean progressive disclosure to phase-specific documents. Its primary weakness is extreme verbosity — the same information is presented in multiple overlapping formats (architecture diagram, execution flow, agent registry, fork context strategy, timeout protocol, reference tables), and many sections could be consolidated or eliminated without losing any actionable content. The skill would benefit significantly from a 40-50% reduction in length.
Suggestions
Consolidate the Agent Registry, Fork Context Strategy, and Lifecycle Management/Timeout Protocol tables into a single agent configuration section — currently the same agents and their parameters are described three separate times.
Remove the 'Fork Context Strategy' section entirely — the rationale ('all fork_turns: none because pipeline pattern') can be a single sentence in the Agent Registry, and the per-agent explanations are redundant.
Merge the Reference Documents by Phase section into the Execution Flow — each phase already lists its reference files, making the separate reference section duplicative.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Massive amounts of repetition — the agent registry, fork context strategy, lifecycle management, timeout protocol, and reference documents tables all repeat similar information in slightly different formats. The execution flow section restates what the architecture overview already showed. Claude doesn't need explanations of why fork_turns is 'none' repeated for every single agent, or a full error handling table when most entries say 'No | continue with fallback'. | 1 / 3 |
Actionability | Highly actionable with concrete code examples for directory setup, spawn_agent calls with exact parameters, context envelope templates, post-agent validation logic, JSON schemas for spec-config.json, and specific CLI commands. The execution flow provides step-by-step instructions with exact function calls and file paths. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing, explicit validation checkpoints after each agent phase (file existence checks, spec-config.json verification), error recovery cascades (4-step timeout protocol), feedback loops (Phase 6 → 6.5 auto-fix with max 2 iterations), and clear state management via spec-config.json. The readiness check scoring thresholds (>=80% pass, 60-79% review, <60% fail) provide explicit decision gates. | 3 / 3 |
Progressive Disclosure | Well-structured with clear one-level-deep references to phase documents, templates, specs, and profiles organized in tables by phase. The SKILL.md serves as an orchestration overview while delegating detailed phase instructions to dedicated files (phases/01-discovery.md, etc.). Navigation is clear with purpose and timing columns in reference tables. | 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 (564 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
227244f
- 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.