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".
66
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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.
The description is technically thorough and highly specific about its capabilities, clearly defining what it does and when to trigger it. Its main weakness is that the trigger terms are internal command names rather than natural language a user might use, which could cause it to be missed when users describe their needs in plain language. The description is well-structured but leans heavily on domain-specific jargon.
Suggestions
Add natural language trigger terms alongside the command triggers, e.g., 'Use when the user wants to run a workflow, execute a template, or resume a paused workflow execution'
Include common variations users might say such as 'run workflow', 'execute pipeline', 'resume from checkpoint', or 'workflow automation'
| 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 templates, bind variables, execute DAG nodes, persist/resume checkpoints) and 'when' (triggers on 'wf-player' or '/wf-player'). The trigger clause is explicit, though narrow. | 3 / 3 |
Trigger Term Quality | Includes some trigger terms like 'wf-player' and '/wf-player', but these are highly technical/internal command names. Missing natural language terms a user might say like 'run workflow', 'execute template', 'resume workflow', or 'workflow execution'. The terms are jargon-heavy rather than natural user language. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — specifically about playing/executing workflow templates from wf-composer in DAG order with checkpoint support. The specific trigger commands and references to ccw-coordinator and team-coordinate patterns make it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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 orchestration skill with excellent organization, clear phase sequencing, and comprehensive error handling. Its main weakness is that actionable details are almost entirely delegated to external phase and spec files that aren't provided in the bundle, making the SKILL.md itself more of an architectural overview than a self-contained executable guide. The conciseness and workflow clarity are strong points.
Suggestions
Include at least minimal executable examples inline for the most critical operations (e.g., how to parse session-state.json, how to invoke ccw cli in background mode) rather than deferring everything to phase files.
Provide the referenced bundle files (phases/*.md, specs/*.md) or include key content inline so the skill is actionable without external dependencies.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It uses tables, ASCII diagrams, and terse descriptions without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary exposition. | 3 / 3 |
Actionability | The skill provides structured guidance with clear phases, error handling tables, and routing logic, but delegates actual execution details to external phase files (phases/01-load.md, etc.) and spec files. The main SKILL.md itself contains no executable code or concrete commands beyond the display format example. Key details like how to actually parse arguments, create session files, or execute nodes are deferred. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases, validation checkpoints, error handling with feedback loops (retry/skip/abort), and resume capability. The CLI node blocking pattern is called out as CRITICAL with explicit instructions. The resume flow includes reconciliation steps for interrupted nodes. | 3 / 3 |
Progressive Disclosure | The skill references external files (phases/01-load.md through phases/04-complete.md, specs/node-executor.md, specs/state-schema.md) with clear signaling, which is good progressive disclosure structure. However, no bundle files were provided, so we cannot verify these references exist. The main file provides a good overview but the phase descriptions are quite thin — just objective and success criteria — making the reader entirely dependent on files that may not exist. | 2 / 3 |
Total | 10 / 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
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.