workflow-lite-plan
Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution tasks with cross-phase context linking (E*→T*), then wave-executes via spawn_agents_on_csv.
46
36%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/workflow-lite-planex/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 is heavily laden with internal jargon and implementation details (spawn_agents_on_csv, E*→T* linking) that would be opaque to most users and even to Claude when selecting among skills. It completely lacks a 'Use when...' clause, making it very difficult to know when this skill should be triggered. The description prioritizes how the pipeline works internally over what problem it solves for the user.
Suggestions
Add an explicit 'Use when...' clause describing the scenarios that should trigger this skill, e.g., 'Use when the user asks to research a topic before executing, or when a complex task requires exploration before implementation.'
Replace internal jargon like 'spawn_agents_on_csv' and 'E*→T*' with user-facing language describing the benefit, e.g., 'Breaks complex requirements into research phases, explores multiple angles in parallel, then synthesizes findings into actionable tasks executed in parallel.'
Include natural trigger terms a user might say, such as 'explore first', 'research then execute', 'multi-phase task', 'parallel exploration', or 'complex requirement breakdown'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names specific actions like 'decomposes requirement into exploration angles', 'runs wave exploration', 'synthesizes findings into execution tasks', and 'wave-executes', but these are described in domain-specific jargon (e.g., 'cross-phase context linking (E*→T*)') rather than universally concrete terms. It names a domain and some actions but is not comprehensible without prior knowledge of the pipeline. | 2 / 3 |
Completeness | The description explains 'what' in technical terms but completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent trigger guidance, and per the rubric this should cap completeness at 2, but the 'what' is also unclear enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | The description uses highly technical jargon like 'wave pipeline', 'spawn_agents_on_csv', 'cross-phase context linking (E*→T*)' that no user would naturally say. There are no natural keywords a user would use to invoke this skill, such as 'explore', 'research', 'plan and execute', or 'multi-step task'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'spawn_agents_on_csv' and 'E*→T* context linking' makes it somewhat distinctive from generic skills, but the overall framing as an 'explore-first' pipeline could overlap with other planning/execution or agent orchestration skills. Without clear trigger boundaries, conflict risk remains moderate. | 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.
This skill is highly actionable with excellent workflow clarity — every phase is precisely defined with executable code, validation gates, and error handling. However, it is severely over-long and monolithic, cramming ~600+ lines of implementation detail into a single file with no progressive disclosure. The content would be dramatically improved by extracting implementation details (helper functions, instruction templates, CSV schemas) into referenced files while keeping the SKILL.md as a concise overview with navigation.
Suggestions
Extract helper functions (computeWaves, buildPrevContext, updateMasterCsvRow, parseCsvLine) into a separate HELPERS.md or reference file, linking from the main skill
Move the full instruction templates (buildExploreInstruction, buildExecuteInstruction) into separate EXPLORE_TEMPLATE.md and EXECUTE_TEMPLATE.md files
Move detailed CSV schema tables into a SCHEMAS.md reference file, keeping only a brief summary (column names + one-line descriptions) in the main skill
Consolidate the main SKILL.md to ~150 lines: overview diagram, phase summaries with key code snippets, core rules, and links to detailed reference files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~600+ lines. It includes extensive implementation details (full JavaScript functions, CSV parsing helpers, Kahn's algorithm implementation) that could be in separate reference files. Many sections repeat information (e.g., CSV schemas are shown multiple times in different contexts). The instruction templates are fully inlined rather than referenced. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code for every phase, complete CSV schemas with examples, concrete spawn_agents_on_csv calls with output schemas, instruction templates with placeholder variables, and specific helper functions like computeWaves and buildPrevContext. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally clear with a 5-phase pipeline, explicit mandatory confirmation gates between phases, dependency cascade handling (skip on failure), wave ordering rules, and validation checkpoints. The ASCII diagram provides a complete overview, and each phase has explicit success criteria. Error handling table covers all failure modes with resolutions. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The full implementation of every helper function, instruction template, CSV schema, wave computation algorithm, and error handling table is inlined. The CSV schemas, instruction templates, and utility functions (computeWaves, updateMasterCsvRow, buildPrevContext) should be in separate reference files with clear links from the main skill. | 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 (1145 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.