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.
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-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.
The description is heavily laden with internal/technical jargon that would be meaningful only to someone already familiar with this specific pipeline architecture. It lacks any user-facing trigger terms and has no explicit 'Use when...' clause, making it very difficult for Claude to know when to select this skill from a pool of alternatives. The core workflow is somewhat discernible but poorly communicated for skill selection purposes.
Suggestions
Add an explicit 'Use when...' clause describing the scenarios that should trigger this skill, e.g., 'Use when the user needs to explore a complex requirement from multiple angles before executing, or when they mention explore-first, multi-agent exploration, or phased task decomposition.'
Replace or supplement jargon like 'spawn_agents_on_csv' and 'E*→T*' with plain-language descriptions of what these mean, e.g., 'delegates exploration tasks to parallel agents' and 'links exploration findings to execution tasks.'
Include natural trigger terms a user might say, such as 'research first then implement', 'explore before building', 'multi-phase task planning', or 'parallel exploration.'
| 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 understood concrete actions. | 2 / 3 |
Completeness | While the 'what' is partially addressed (though in jargon-heavy terms), there is no 'Use when...' clause or any explicit guidance on when Claude should select this skill. The absence of trigger guidance caps this at a low score. | 1 / 3 |
Trigger Term Quality | The description uses highly technical internal jargon like 'spawn_agents_on_csv', 'cross-phase context linking (E*→T*)', and 'wave pipeline' — none of which are natural terms a user would say when requesting this kind of work. There are no user-facing keywords that would naturally trigger selection. | 1 / 3 |
Distinctiveness Conflict Risk | The description is specific enough in its jargon (spawn_agents_on_csv, E*→T* linking) that it wouldn't easily conflict with generic skills, but the lack of clear domain framing means it could overlap with other agent orchestration or task decomposition skills. | 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 is highly actionable with excellent workflow clarity — every phase has concrete code, clear sequencing, mandatory confirmation gates, and comprehensive error handling. However, it is severely over-long and monolithic: ~600+ lines of inline implementation detail with no progressive disclosure or external references. The content would benefit enormously from splitting into a concise overview SKILL.md with references to separate files for CSV schemas, instruction templates, helper functions, and the wave computation algorithm.
Suggestions
Split into multiple files: move CSV schemas to SCHEMAS.md, instruction templates to TEMPLATES.md, helper functions (computeWaves, buildPrevContext, updateMasterCsvRow) to HELPERS.md, and keep SKILL.md as a concise overview with phase summaries and references.
Remove redundant explanations of context_from linking — it's explained in the overview, context flow diagram, CSV schema, Phase 3 implementation, Phase 4 implementation, and core rules. Consolidate to one authoritative location.
Trim the instruction templates (buildExploreInstruction, buildExecuteInstruction) to essential directives only — Claude doesn't need verbose protocol explanations like 'Read references: Parse {hints}' when the hints format is already defined in the CSV schema.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~600+ lines. It includes massive amounts of implementation detail (full JavaScript functions, CSV schemas with every column documented, ASCII diagrams) that could be split into reference files. Many sections repeat information (e.g., context_from linking is explained in overview, context flow diagram, CSV schema, implementation, and core rules). The instruction templates alone consume hundreds of tokens with information Claude could infer. | 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 helper functions like computeWaves and buildPrevContext. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally clear with 5 explicitly numbered phases, mandatory confirmation gates between phases, dependency-failure cascading (skip on failure), wave ordering rules, and explicit validation checkpoints. The error handling table and core rules section provide comprehensive feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files and no references to external documents. The full CSV schemas, implementation code, instruction templates, helper functions, wave computation algorithm, and error handling are all inline. The CSV schemas, instruction templates, and helper functions should be in separate reference files with the SKILL.md serving as an overview. | 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
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.