wf-player
Workflow template player — load a JSON template produced by wf-composer, bind context variables, execute nodes in DAG order (serial/parallel), persist state at checkpoints, support resume from any checkpoint. Uses ccw-coordinator serial-blocking for CLI nodes and team-coordinate worker pattern for parallel agent nodes. Triggers on "wf-player " or "/wf-player".
77
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/wf-player/SKILL.mdQuality
Discovery
85%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 excels at specificity and distinctiveness, providing detailed technical actions and a clear niche. The completeness is good with explicit trigger terms. The main weakness is that trigger terms are very technical and command-based rather than natural language, which could cause the skill to be missed when users describe their needs in plain language.
Suggestions
Add natural language trigger terms beyond command syntax, e.g., 'Use when the user wants to run a workflow, execute a template pipeline, or resume a paused workflow execution'
Include common user phrasings like 'run workflow', 'execute pipeline', 'resume from checkpoint' alongside the slash-command triggers
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: load JSON templates, bind context variables, execute nodes in DAG order (serial/parallel), persist state at checkpoints, support resume from any checkpoint. Very detailed about what it does. | 3 / 3 |
Completeness | Clearly answers both 'what' (load JSON template, bind variables, execute DAG nodes, persist/resume checkpoints) and 'when' (triggers on 'wf-player' or '/wf-player'). The trigger clause is explicit even if narrow. | 3 / 3 |
Trigger Term Quality | Includes some trigger terms like 'wf-player', '/wf-player', and domain terms like 'workflow template', 'DAG', 'checkpoint'. However, these are highly technical and may not match natural user language — users might say 'run workflow', 'execute template', 'resume workflow' which are not explicitly covered. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific references to wf-composer JSON templates, DAG execution, ccw-coordinator serial-blocking, and team-coordinate worker patterns. Very unlikely to conflict with other skills due to its narrow, well-defined niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured workflow skill with clear sequencing, good error handling, and appropriate use of progressive disclosure patterns. Its main weaknesses are the lack of executable code examples (phases delegate entirely to external files that aren't provided) and some redundancy between the architecture diagram and the phase descriptions. The skill would benefit from including at least minimal inline actionable content for each phase rather than fully deferring to external files.
Suggestions
Add inline executable snippets or concrete pseudo-commands for each phase (e.g., show the actual Skill() call syntax for a skill node, the ccw cli invocation pattern for CLI nodes) rather than just saying 'Read phases/0X.md and execute'.
Include at least a minimal example of a template JSON structure so Claude knows what it's parsing in Phase 1, or reference a concrete example template file.
Remove or condense the architecture ASCII block since it largely duplicates the phase-by-phase descriptions that follow — a single-line summary per phase in the architecture section would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient and avoids explaining basic concepts Claude would know. However, the architecture ASCII diagram and some table structures could be tightened — the architecture block largely duplicates what's described in the phase sections below it. | 2 / 3 |
Actionability | The skill provides structured guidance with tables, phases, and error handling, but lacks executable code examples. Key phases (1-4) delegate to external files ('Read phases/01-load.md and execute') without providing inline concrete steps, making the SKILL.md itself incomplete for execution. The handleList example output is helpful but is display-only, not executable. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases, a well-defined entry router, resume/checkpoint logic, and a comprehensive error handling table with specific resolution strategies per failure mode. The critical CLI node blocking warning is a valuable validation checkpoint. The resume flow includes resetting interrupted nodes back to pending, which is a proper feedback loop. | 3 / 3 |
Progressive Disclosure | The skill references external phase files (phases/01-load.md through 04-complete.md) and spec files (specs/node-executor.md, specs/state-schema.md), which is good progressive disclosure structure. However, no bundle files were provided, meaning these references are unverifiable. The phase sections in SKILL.md are too thin — they just say 'Read X and execute' with minimal inline context about what each phase actually does, making the overview insufficient on its own. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
227244f
- 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.