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.

Quality

36%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/workflow-execute/SKILL.md

Quality

Content

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 highly actionable with excellent workflow clarity, providing complete executable code for a complex multi-phase pipeline with proper validation checkpoints and error recovery. However, it is severely undermined by its monolithic structure and extreme verbosity—at 600+ lines with all implementation details inlined, it wastes enormous context window budget. The content would be far more effective as a concise overview with implementation details split into referenced files.

Suggestions

Extract the full Phase 3-5 implementation code, CSV helpers, and instruction template into separate referenced files (e.g., PHASE3-CONVERSION.md, PHASE4-EXECUTION.md, CSV-HELPERS.md, INSTRUCTION-TEMPLATE.md) and keep SKILL.md as a concise overview with the pipeline diagram and key rules.

Remove implementation details Claude can derive (CSV parsing, csvEscape, Kahn's BFS algorithm) and replace with brief descriptions of the expected behavior, trusting Claude's competence.

Consolidate the CSV schema documentation—the 21-column table with source/phase metadata is useful but could be a separate SCHEMAS.md reference file.

The ASCII pipeline diagram at the top is valuable as an overview, but the same information is then repeated in exhaustive detail below—keep the diagram and trim redundant prose.

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 the ASCII pipeline diagram all consume enormous token budget. Much of this (CSV parsing, Kahn's BFS, regex escaping) is knowledge Claude already has.	1 / 3
Actionability	The skill provides fully executable JavaScript code for every phase, complete with specific commands, concrete CSV schemas, output JSON schemas for spawn_agents_on_csv, and copy-paste ready implementations. Nothing is left vague or abstract.	3 / 3
Workflow Clarity	The 6-phase pipeline is clearly sequenced with explicit validation checkpoints (Phase 2 validates planning docs, Phase 4 checks dependency failures before execution, Phase 5 reconciles state). Feedback loops exist for dependency cascades (skip dependents on failure), resume support, and error recovery is well-documented in the error handling table.	3 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. The entire implementation—CSV helpers, instruction templates, phase implementations, schemas—is inlined in a single massive document. The CSV schema table, agent instruction template, and helper functions should clearly be in separate referenced files.	1 / 3
	Total	8 / 12 Passed

Description

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 implementation details (JSON files, CSV conversion, specific function names) rather than describing user-facing capabilities and when to use them. The lack of natural trigger terms and a 'Use when...' clause makes it very difficult for Claude to correctly select this skill based on user requests.

Suggestions

Add an explicit 'Use when...' clause describing user-facing scenarios, e.g., 'Use when the user wants to orchestrate multiple parallel agent tasks, run batch workflows, or execute a multi-step task plan across agents.'

Replace internal jargon with natural language trigger terms users would actually say, such as 'parallel task execution', 'batch processing', 'multi-agent orchestration', 'run workflow', or 'distribute tasks'.

Rewrite the 'what' portion to focus on user-facing outcomes rather than pipeline internals, e.g., 'Discovers sessions, validates execution plans, and distributes tasks across multiple agents in waves, 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 explicit trigger guidance. The description reads like internal documentation of a pipeline architecture rather than a skill selection guide. The missing 'Use when...' clause caps this at 2 per the rubric, and the 'what' is also weak, so it scores 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 more likely say things like 'run tasks in parallel', 'batch execution', or 'orchestrate agents'.	1 / 3
Distinctiveness Conflict Risk	The description is fairly niche due to its highly specific technical terminology (CSV wave engine, IMPL-*.json, spawn_agents_on_csv), which reduces conflict risk. However, the opening phrase 'Autonomous workflow execution pipeline' is generic enough to potentially overlap with other orchestration or workflow skills.	2 / 3
	Total	6 / 12 Passed

Validation

72%

Warnings & errors only

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: 07491b0

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.