csv-wave-pipeline
Requirement planning to wave-based CSV execution pipeline. Decomposes requirement into dependency-sorted CSV tasks, computes execution waves, runs wave-by-wave via spawn_agents_on_csv with cross-wave context propagation.
50
41%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/csv-wave-pipeline/SKILL.mdQuality
Discovery
27%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is technically detailed and lists specific actions, but it reads like internal implementation documentation rather than a skill description meant for selection. It lacks natural trigger terms a user would use and has no explicit 'Use when...' guidance, making it difficult for Claude to know when to select this skill from a list.
Suggestions
Add a 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to break down a complex requirement into parallel executable tasks, mentions task planning, parallel execution, or wave-based workflows.'
Replace technical jargon with user-facing language — e.g., instead of 'spawn_agents_on_csv with cross-wave context propagation', say 'orchestrates parallel agent execution across task waves, passing results between phases'.
Include natural keywords users might say such as 'break down tasks', 'parallel execution', 'task dependencies', 'multi-step plan', or 'orchestrate agents'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: decomposes requirements into dependency-sorted CSV tasks, computes execution waves, runs wave-by-wave via spawn_agents_on_csv, and propagates cross-wave context. | 3 / 3 |
Completeness | Describes what it does but completely lacks any 'Use when...' clause or equivalent trigger guidance, and the rubric caps completeness at 2 for missing that clause. The 'what' is also described in such technical terms that it's hard to understand the actual use case, pushing this to a 1. | 1 / 3 |
Trigger Term Quality | Uses highly technical jargon like 'wave-based CSV execution pipeline', 'dependency-sorted CSV tasks', 'spawn_agents_on_csv', and 'cross-wave context propagation' — terms a user would almost never naturally say when requesting this capability. | 1 / 3 |
Distinctiveness Conflict Risk | The highly specific technical terminology (wave-based, spawn_agents_on_csv) makes it unlikely to conflict with most skills, but the mention of 'requirement planning' is broad enough to potentially overlap with other planning or task decomposition skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely thorough and actionable, providing a complete implementation of a wave-based CSV execution pipeline with excellent workflow clarity and error handling. However, it is severely over-engineered for a SKILL.md file — at 500+ lines it wastes enormous context window space by including full implementations of basic algorithms (CSV parsing, topological sort) and utility functions that Claude can easily write. The content desperately needs to be split across multiple files with the SKILL.md serving as an overview.
Suggestions
Extract the full implementation code (CSV utilities, wave computation, phase implementations) into separate referenced files (e.g., IMPLEMENTATION.md or .js files), keeping only the architecture overview and key decision points in SKILL.md
Remove basic utility code that Claude can write independently (CSV parsing, string escaping, topological sort) — instead just specify the algorithm name and expected behavior
Move the instruction template builder content to a separate AGENT_TEMPLATE.md file and reference it from the main skill
Reduce the CSV schema section to just the column table and one brief example row, moving the full multi-row examples to a separate EXAMPLES.md
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Includes full implementation code for CSV parsing, session initialization, wave computation, result aggregation, instruction templates, and report generation. Much of this (CSV parsing, topological sort, string escaping) is basic programming Claude already knows. The skill could be reduced to ~30% of its size by describing the architecture and key decisions without spelling out every line of code. | 1 / 3 |
Actionability | Highly actionable with complete, executable JavaScript code for every phase, concrete CSV schemas with full example rows, specific column definitions, exact file paths, and copy-paste ready instruction templates. Every step is fully specified with working code. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (Decompose → Compute Waves → Execute → Aggregate), explicit validation checkpoints (user approval gate, wave-order enforcement, dependency failure → skip dependents), error recovery (retry failed tasks, continue mode), and feedback loops throughout. The error handling table and rules section reinforce the workflow constraints. | 3 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files. Everything is inline — CSV schemas, full implementation code, instruction templates, error handling tables, best practices — all in a single massive document. The instruction template alone is ~60 lines that could be in a separate file. The CSV schema examples and utility functions could easily be split out. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (900 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 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.