CtrlK
BlogDocsLog inGet started
Tessl Logo

workflow-skill-creator

Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

A well-structured, highly actionable meta-skill with clear phased sequencing and validation checkpoints. The main gaps are mild verbosity from over-explaining concepts Claude already knows and a monolithic body that could offload the question bank and rules into reference files.

Suggestions

Trim explanations of concepts Claude already knows (e.g., why stdout truncates, why file output is token-efficient, why API response bodies are actionable) — keep only the directive.

Move the Round 1–5 brainstorming question bank and/or the implementation Rules into separate reference files (e.g., references/brainstorming_questions.md, references/implementation_rules.md) and link to them from SKILL.md to improve progressive disclosure.

In the conciseness-sensitive sections, replace multi-bullet justifications with a single imperative sentence so every token earns its place.

DimensionReasoningScore

Conciseness

The body is mostly actionable procedural guidance, but it pads several points with explanations Claude already knows (e.g., "API responses can be very large and will truncate in terminal output", "API response bodies contain actionable details"), so it could be tightened.

2 / 3

Actionability

Provides concrete, executable guidance — specific rules (uv run, urllib, time.monotonic(), RateLimitError, --output required, exit code 1, json.dump indent=2), a copy-paste SKILL.md structure template, and a real template file at references/cli_script_template.py.

3 / 3

Workflow Clarity

Phases 1–4 are clearly sequenced with explicit validation checkpoints: a Brainstorming Completion Criteria checklist, "Wait for explicit user approval before proceeding to Phase 3", and a Phase 4 validation feedback loop (test → verify output matches expectations).

3 / 3

Progressive Disclosure

There is one clearly-signaled, one-level-deep reference (references/cli_script_template.py, verified to exist), but the large brainstorming question bank and the implementation rules are kept inline in a ~270-line monolithic SKILL.md rather than split into separate reference files.

2 / 3

Total

10

/

12

Passed

Description

90%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with explicit trigger guidance and clear disambiguation from generic skill-creators. Its only weakness is specificity: it distills to a single action rather than enumerating multiple concrete capabilities.

DimensionReasoningScore

Specificity

Names the domain and a concrete action ("Distills a completed user workflow or interaction into a reusable agent skill") but offers a single distilled action rather than a list of multiple specific concrete actions, so it stops short of the top anchor.

2 / 3

Completeness

Explicitly answers both what ("Distills…into a reusable agent skill") and when ("Use when the user asks…") with explicit positive triggers plus a negative "Do not use for…" clause.

3 / 3

Trigger Term Quality

Covers natural phrases users would actually say — "make this a skill", "create a skill from what we just did", "package this workflow", "turn their workflow…into a skill" — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The niche is clear (distilling an *existing* workflow into a skill) and the explicit "Do not use for creating skills from scratch… use a generic skill-creator" disambiguates it from sibling skills, making wrong-skill triggering unlikely.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google-deepmind/science-skills
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.