CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

68

Quality

83%

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

73%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 content is a thorough, well-sequenced eval-and-iterate workflow with strong actionability and clear feedback loops. Its main weaknesses are conversational padding that bloats token use and several referenced bundle files (agents/*.md, eval-viewer/generate_review.py) that do not actually exist.

Suggestions

Trim conversational asides (e.g. "Cool? Cool.", the plumbers/grandparents tangent, the "billions in economic value" line, and the all-caps apology) to tighten token efficiency.

Add the missing `agents/grader.md`, `agents/comparator.md`, and `agents/analyzer.md` files the body depends on, or remove the references to them.

Resolve the `eval-viewer/generate_review.py` path — either create that script in the bundle or correct the path to point at the existing viewer-generation code.

DimensionReasoningScore

Conciseness

The body is mostly actionable but carries several padded conversational passages ("Cool? Cool.", the plumbers-and-grandparents tangent, "we are trying to create billions a year in economic value here!", "Sorry in advance but I'm gonna go all caps here") that could be trimmed without losing clarity, fitting the 3 anchor better than the 4 which expects only minor over-explanation.

3 / 5

Actionability

Concrete, copy-paste-ready commands and JSON schemas are plentiful (e.g. `python -m scripts.aggregate_benchmark`, eval_metadata.json, timing.json), but key referenced files like `eval-viewer/generate_review.py` and `agents/grader.md` do not exist in the bundle, creating execution gaps that keep it below the fully-executable 5 anchor.

4 / 5

Workflow Clarity

The create → test → review → improve cycle is laid out as explicit numbered steps (Step 1–5 for running evals, the iteration loop, the description-optimization Steps 1–4) with a real feedback loop (grade assertions → user reviews feedback.json → improve → rerun), matching the 5 anchor for clear sequencing with feedback loops.

5 / 5

Progressive Disclosure

Structure is good with clear section headers and one-level-deep pointers to `references/schemas.md`, `assets/eval_review.html`, and `scripts.*` that resolve, but the body also repeatedly points to `agents/grader.md`, `agents/comparator.md`, `agents/analyzer.md`, and `eval-viewer/generate_review.py` which are absent from the bundle, leaving organization gaps that fit the 4 anchor rather than the 5.

4 / 5

Total

16

/

20

Passed

Description

92%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 specific, complete, and clearly distinctive, covering the create/edit/eval/benchmark/optimize lifecycle with an explicit "Use when" trigger clause. It falls just short of perfect trigger-term coverage by omitting a few natural synonyms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions spanning the full skill lifecycle — "Create new skills, modify and improve existing skills, and measure skill performance" plus "run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description," matching the comprehensive-coverage anchor rather than the 4 anchor which implies minor gaps.

5 / 5

Completeness

It explicitly states what the skill does ("Create new skills, modify and improve existing skills, and measure skill performance") and gives an explicit "Use when..." clause with concrete trigger phrases, satisfying both halves of the 5 anchor.

5 / 5

Trigger Term Quality

Natural user phrases like "create a skill from scratch," "edit, or optimize an existing skill," and "run evals to test a skill" give good keyword coverage, but a few common variations (e.g. "build a skill," "improve a skill") are absent, so it stops short of the comprehensive synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Skill authoring, eval running, benchmarking, and description optimization form a clear niche with distinct triggers and minimal overlap with unrelated skills, matching the 5 anchor.

5 / 5

Total

19

/

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

skill_md_line_count

SKILL.md is long (511 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
coinbase/cds
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.