CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

56

Quality

65%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/wf-composer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill has excellent workflow architecture with clear phase sequencing, checkpoint injection rules, and user confirmation loops. However, it functions primarily as a routing document that delegates all substantive execution logic to external phase files that are not provided in the bundle, significantly limiting its standalone actionability. The content is well-structured but would benefit from inline fallback instructions or at minimum having the referenced bundle files present.

Suggestions

Provide the referenced phase files (phases/01-parse.md through phases/05-persist.md) and spec files in the bundle, or inline the critical execution logic for each phase so the skill is functional standalone.

Add concrete executable examples — e.g., show the exact JSON structure for intent.json, nodes.json, and dag.json so Claude knows the expected output format without needing external schema files.

Include a minimal end-to-end example: a sample natural language input and the resulting template JSON output, so Claude can pattern-match on real data.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient and doesn't over-explain basic concepts, but includes some structural overhead that could be tightened (e.g., the shared constants table and entry router table could be more compact). It respects Claude's intelligence but has moderate verbosity in formatting.

2 / 3

Actionability

The skill provides structured phases with clear objectives and success criteria, but delegates all actual execution logic to external phase files (phases/01-parse.md through phases/05-persist.md) which are not provided. The SKILL.md itself contains no executable code or concrete commands — it's a routing document that says 'Read X and execute' without giving fallback instructions if those files are missing.

2 / 3

Workflow Clarity

The multi-phase workflow is clearly sequenced with explicit phase boundaries, success criteria for each phase, checkpoint injection rules, and a confirmation/edit loop in Phase 4. The resume/edit flow in Phase 0 handles recovery scenarios. The DAG validation in Phase 3 and user confirmation in Phase 4 serve as validation checkpoints.

3 / 3

Progressive Disclosure

The skill references phase files (phases/01-parse.md through phases/05-persist.md) and spec files (specs/node-catalog.md, specs/template-schema.md) for deeper content, which is good progressive disclosure design. However, none of these bundle files are actually provided, meaning the skill is essentially non-functional without them — the references are well-signaled but unverifiable.

2 / 3

Total

9

/

12

Passed

Description

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 DAG composition with concrete actions. However, it relies on command-based triggers rather than natural language keywords users would actually say, and lacks an explicit 'Use when...' clause describing the scenarios that should activate this skill beyond the command prefix.

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, chain tasks together, or build a pipeline of skills and commands.'

Include natural language trigger terms users would say, such as 'workflow', 'pipeline', 'automate steps', 'chain tasks', 'multi-step process', 'task orchestration' alongside the command triggers.

DimensionReasoningScore

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', 'automate', 'pipeline', '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 parses natural language into DAGs of skill/CLI/agent nodes is a very specific niche. The explicit command triggers and unique domain (workflow DAG composition) make conflicts with other skills unlikely.

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.