wf-composer
Semantic workflow composer — parse natural language workflow description into a DAG of skill/CLI/agent nodes, auto-inject checkpoint save nodes, confirm with user, persist as reusable JSON template. Triggers on "wf-composer " or "/wf-composer".
73
68%
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-composer/SKILL.mdQuality
Discovery
67%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 excels at specificity and distinctiveness, clearly articulating a unique capability around workflow composition with concrete actions like DAG parsing, checkpoint injection, and JSON template persistence. However, it relies on command-based triggers rather than natural language keywords users might use, and lacks an explicit 'Use when...' clause that would help Claude select this skill in conversational contexts beyond the slash command.
Suggestions
Add a 'Use when...' clause describing natural scenarios, e.g., 'Use when the user wants to create, design, or automate a multi-step workflow, pipeline, or task chain.'
Include natural language trigger terms users might say, such as 'workflow', 'pipeline', 'automate steps', 'chain tasks', 'multi-step process', 'task orchestration'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: parse natural language into a DAG, auto-inject checkpoint save nodes, confirm with user, persist as reusable JSON template. These are detailed, concrete capabilities. | 3 / 3 |
Completeness | The 'what' is well-covered with specific actions. The 'when' is limited to command triggers ('wf-composer' or '/wf-composer') rather than describing natural use cases or scenarios. There's no 'Use when...' clause describing situations like 'when the user wants to create a multi-step workflow' or 'when chaining multiple skills together'. | 2 / 3 |
Trigger Term Quality | Includes the command triggers 'wf-composer' and '/wf-composer', but lacks natural language keywords users would say like 'workflow', 'pipeline', 'automate', 'chain tasks', 'DAG'. The triggers are command-based rather than natural language terms. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the concept of a semantic workflow composer that builds DAGs of skill/CLI/agent nodes is a very specific niche. The explicit command triggers and unique domain (workflow composition into JSON templates) make it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at workflow organization and progressive disclosure, providing a clear high-level routing document with well-defined phases, success criteria, and references to detailed sub-files. Its main weakness is actionability — the SKILL.md itself contains no executable code or concrete commands, fully delegating to external phase files that may or may not exist. The conciseness is adequate but could be tightened by removing the redundant architecture diagram.
Suggestions
Include at least minimal inline executable examples for key operations (e.g., the JSON structure for intent.json, nodes.json, or dag.json) so the skill is partially actionable even without the phase files.
Consider removing or condensing the Architecture section since the phase-by-phase breakdown already conveys the same pipeline sequence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy — the architecture diagram repeats what the phase sections describe, and some tables (like shared constants) could be tighter. However, it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | The skill delegates all actual execution to external phase files (phases/01-parse.md through phases/05-persist.md) rather than providing inline executable guidance. The main file describes what each phase should accomplish but doesn't give concrete code, commands, or copy-paste-ready instructions — it's essentially a routing document that says 'read X and execute.' | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced across 6 phases (0-5) with explicit success criteria for each phase, checkpoint injection rules, a well-defined entry router with branching conditions, and a confirm-before-persist validation step (Phase 4) that includes user approval and edit loops before final save. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure — the SKILL.md serves as a clear overview/router with well-signaled one-level-deep references to phase files (phases/01-parse.md through phases/05-persist.md) and spec files (specs/node-catalog.md, specs/template-schema.md). Navigation is intuitive and content is appropriately split. | 3 / 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
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.