CtrlK
BlogDocsLog inGet started
Tessl Logo

ccwf-cli

Use the `ccwf` CLI (from @cc-wf-studio/cli) to render, validate, preview, export, or run cc-wf-studio workflow JSON files from the terminal. Apply whenever the user mentions viewing, visualizing, checking, executing, or converting a workflow under `.vscode/workflows/` (or any `*workflow*.json`), wants a Mermaid diagram of a workflow, asks to "see" / "preview" / "open" a workflow, or wants to run a workflow as a Claude Code Skill without opening VSCode.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

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

The body is a strong, actionable CLI reference with executable examples and clear navigation, hindered mainly by conceptual framing and a duplicated security note that pad the token budget. Workflow sequencing is clear with validation guidance, though the retry loop is implicit rather than explicit.

Suggestions

Trim conceptual framing (e.g. "a visual AI-agent workflow tool", "This Skill teaches Claude how to recognise when ccwf is the right answer") — Claude can infer these from the subcommand reference.

Deduplicate the UUID/loopback security note: keep it once in Tips & gotchas and remove the inline repetition in the `ccwf preview` section.

Make the validation feedback loop explicit in Core workflow (validate → on failure, fix and re-validate → only then run/export) to lift workflow clarity to a 5.

DimensionReasoningScore

Conciseness

Mostly efficient reference material, but padded with conceptual framing ("a visual AI-agent workflow tool", "This Skill teaches Claude how to recognise..."), a repeated UUID/loopback security note across two sections, and backstory Claude could infer — more than minor over-explanation.

3 / 5

Actionability

Every subcommand has copy-paste-ready bash examples with real flags, plus a concrete --agent output-path table and an .mcp.json snippet — fully executable and covering common cases.

5 / 5

Workflow Clarity

The Core workflow sequences validate → preview → export/run with explicit ordering and a "stop and surface the error" checkpoint, plus a validation-before-execution tip; the fix-and-re-validate feedback loop is only implicit, a minor gap.

4 / 5

Progressive Disclosure

No bundle files exist; the body is well-organized into clear sections and points one level deep to `ccwf <subcommand> --help` and the repo README, with no nested references and easy navigation.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 exemplary: it states concrete capabilities, gives rich natural-language trigger phrases with synonyms and file patterns, and clearly delineates both what the skill does and when to use it. It is tightly scoped to a named CLI, so conflict risk is minimal.

DimensionReasoningScore

Specificity

Lists multiple concrete actions tied to a named tool — "render, validate, preview, export, or run" cc-wf-studio workflow JSON files — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both "what" (render/validate/preview/export/run workflow JSON from the terminal) and "when" ("Apply whenever the user mentions..." with concrete trigger phrases).

5 / 5

Trigger Term Quality

Rich natural-language triggers with synonyms (viewing/visualizing/checking/executing/converting, see/preview/open) plus file patterns (*.vscode/workflows/, *workflow*.json) and a Mermaid trigger, giving comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

Anchored to a specific named CLI (ccwf / @cc-wf-studio/cli) and specific workflow file locations, giving a clear niche with minimal overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
breaking-brake/cc-wf-studio
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.