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.
40
41%
Does it follow best practices?
Impact
—
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 but written in implementation jargon rather than user-facing language, making it poor for skill selection. It lacks a 'Use when...' clause entirely, and the trigger terms are internal technical concepts rather than natural phrases a user would employ. While the specific actions are concrete, they are expressed in a way that would be difficult for Claude to match against typical user requests.
Suggestions
Add an explicit 'Use when...' clause describing user-facing scenarios, e.g., 'Use when the user wants to break down a complex requirement into parallelizable tasks and execute them in dependency order.'
Replace technical jargon with natural trigger terms users would say, such as 'break down tasks', 'parallel execution', 'dependency planning', 'multi-step workflow', 'batch processing'.
Clarify the domain context—what kind of requirements and CSV tasks are involved—so Claude can distinguish this from general task planning or CSV file manipulation skills.
| 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 (decomposes requirements, computes waves, runs tasks) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also obscured by jargon, bringing it to 1. | 1 / 3 |
Trigger Term Quality | Uses highly technical jargon like 'wave-based CSV execution pipeline', 'spawn_agents_on_csv', 'cross-wave context propagation' that users would never naturally say. Missing natural trigger terms a user might use like 'plan tasks', 'break down requirements', or 'parallel execution'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'spawn_agents_on_csv' and 'wave-based' execution is fairly specific and niche, but the 'requirement planning' framing is broad enough to potentially overlap with general task planning or project management 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 exceptionally thorough and actionable, providing complete executable implementations for a complex wave-based execution pipeline. However, it severely violates conciseness — at 600+ lines it consumes enormous context window space, with utility functions, templates, and optional features (handoff intake) that should be in separate bundle files. The lack of any progressive disclosure structure means Claude must load the entire document even for simple operations.
Suggestions
Extract CSV utility functions (parseCsv, parseCsvLine, csvEscape, updateMasterCsvRow) into a referenced UTILS.md or utils.js bundle file
Move the instruction template builder and handoff intake logic into separate bundle files (e.g., INSTRUCTION_TEMPLATE.md and HANDOFF.md), referenced from the main skill
Move the Phase 3 context.md generation template into a separate REPORT_TEMPLATE.md file
Condense the main SKILL.md to a high-level overview (~100-150 lines) covering the workflow phases, CSV schema summary, key rules, and pointers to detailed implementation files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Includes extensive implementation code (CSV parsers, full instruction templates, handoff intake logic, context.md generation) that could be in separate files. Much of this is boilerplate that Claude could generate from a concise specification. The handoff intake section alone is ~40 lines of code for an optional feature. | 1 / 3 |
Actionability | Highly actionable with complete, executable JavaScript code for every phase — session initialization, wave computation (Kahn's algorithm), CSV generation, wave execution loop, result merging, and report generation. The CSV schema is fully specified with concrete examples, and the instruction template is copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear phase separation (Decompose → Execute → Aggregate), explicit validation checkpoints (user approval gate, dependency failure skipping, circular dependency detection), and feedback loops (retry failed tasks, re-validate). The wave execution loop has clear error handling with skip-on-failure propagation and cleanup steps. | 3 / 3 |
Progressive Disclosure | Monolithic wall of content with no bundle files to offload detail. The CSV utility functions, instruction template builder, handoff intake logic, context.md generation, and Phase 3 reporting could all be in separate referenced files. Everything is inlined into a single massive SKILL.md with no progressive structure. | 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 (961 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
5ff5e86
- 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.