workflow-execute
Autonomous workflow execution pipeline with CSV wave engine. Session discovery → plan validation → IMPL-*.json → CSV conversion → wave execution via spawn_agents_on_csv → results sync. Task JSONs remain the rich data source; CSV is brief + execution state.
36
36%
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/workflow-execute/SKILL.mdQuality
Discovery
17%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 description reads like internal technical documentation rather than a skill selection guide. It focuses on architecture and pipeline stages using jargon that users would never naturally use, and completely lacks explicit trigger guidance ('Use when...'). While the technical specificity provides some distinctiveness, it fails at its primary purpose of helping Claude match user requests to the right skill.
Suggestions
Add an explicit 'Use when...' clause describing user-facing scenarios, e.g., 'Use when the user wants to orchestrate multi-agent task execution, run batch workflows, or distribute work across parallel agents.'
Replace internal jargon with natural trigger terms users would actually say, such as 'parallel task execution', 'batch processing', 'multi-agent orchestration', 'automated workflow', or 'distributed task running'.
Rewrite the 'what' portion to describe user-facing capabilities rather than internal pipeline stages, e.g., 'Orchestrates parallel execution of multiple tasks by converting task plans into waves of agent work, tracking progress and syncing results.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names specific components (CSV wave engine, IMPL-*.json, spawn_agents_on_csv, CSV conversion) and outlines a pipeline sequence, but the actions are described as abstract pipeline stages rather than concrete user-facing capabilities. It's more of an internal architecture description than a list of what the skill actually does for the user. | 2 / 3 |
Completeness | While there is a partial 'what' (autonomous workflow execution pipeline), there is no 'when' clause or any explicit trigger guidance. The description reads like internal documentation of a pipeline architecture rather than guidance for when Claude should select this skill. Missing 'Use when...' clause caps this at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | The terms used are highly technical and internal ('IMPL-*.json', 'spawn_agents_on_csv', 'wave execution', 'results sync'). These are not natural keywords a user would say when requesting this functionality. A user would never ask for 'CSV wave engine' or 'session discovery → plan validation'. | 1 / 3 |
Distinctiveness Conflict Risk | The highly specific technical terms (spawn_agents_on_csv, IMPL-*.json, CSV wave engine) make it unlikely to conflict with other skills, but the opening phrase 'Autonomous workflow execution pipeline' is quite generic and could overlap with other orchestration or automation skills. The niche is somewhat clear but not well-articulated for disambiguation. | 2 / 3 |
Total | 6 / 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.
The skill excels at actionability and workflow clarity with fully executable code and a well-structured 6-phase pipeline with validation checkpoints and error recovery. However, it is severely hampered by its monolithic structure — over 600 lines of inline implementation code, CSV helpers, instruction templates, and detailed schemas that should be split across multiple files. The token cost is extremely high for what could be a concise overview pointing to implementation details.
Suggestions
Extract the full phase implementation code (Phases 1-6) into separate files (e.g., PHASES.md or individual phase files) and keep only the pipeline overview, CSV schemas, and core rules in SKILL.md
Move CSV helper functions (parseCsv, parseCsvLine, updateMasterCsvRow, csvEscape) to a referenced utility file since Claude already knows how to parse CSV
Move the execute instruction template (buildExecuteInstruction) to a separate INSTRUCTION_TEMPLATE.md file — it's ~60 lines of template text that doesn't need to be in the main skill
Remove the detailed 21-column CSV schema table and replace with a brief summary noting that task_json_path provides rich data while CSV tracks execution state — the column definitions are self-documenting from the code
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at 600+ lines, with massive inline code blocks that could be in separate files. The full implementation code for every phase, CSV helpers, instruction templates, and detailed column-by-column schema tables consume enormous token budget. Much of this (CSV parsing, BFS algorithm, regex escaping) is knowledge Claude already has. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code for every phase, complete with specific function implementations, exact CLI flag parsing, CSV schema definitions, spawn_agents_on_csv calls with output_schema, and concrete error handling. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 6-phase pipeline is clearly sequenced with an excellent ASCII diagram overview, explicit validation checkpoints (Phase 2 document validation, Phase 3 user confirmation, Phase 4 dependency cascade checks), feedback loops (skip on failure, re-read CSV before each wave), and clear resume mode entry points. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being 600+ lines. The CSV helpers, instruction template, phase implementations, and schema documentation are all inline when they should be split into separate reference files. No bundle files are provided to offload this content. | 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 (1118 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.