expression-compiler

Compile a caller-provided expression into a Python code object

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./evals/skills/command-injection/eval-execution/SKILL.md

Quality

Content

51%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 maximally lean but nearly empty of actionable guidance: it describes a helper file rather than instructing any workflow, and its only reference (calculate.py) is broken with no bundle directories present. It reads as a placeholder rather than a usable skill body.

Suggestions

Fix or remove the broken reference: either include the calculate.py bundle file or replace the link with inline executable guidance.

Add a concrete usage example (e.g. a short code snippet or command showing how an expression is compiled and what is returned) to lift actionability.

State the single action unambiguously (input format, compilation step, output) so the simple-skill exception can apply to workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is two sentences with no padding and no explanation of concepts Claude already knows, matching 'lean and efficient; assumes Claude's competence'. It cannot exceed 5, and it is not a 4 because there is no over-explanation to trim.	5 / 5
Actionability	The body only describes ("intentionally demonstrates dynamic compilation of caller input") with no code, commands, or steps, and its single concrete pointer — [calculate.py](calculate.py) — is a broken link to a nonexistent file. This sits between the purely vague anchor 1 and the minimal-hint anchor 2: a specific artifact is named, but it provides no executable guidance.	2 / 5
Workflow Clarity	No sequence or action is articulated at all; the body never instructs what to do with an expression. The simple-skill exception does not apply because the single action is not unambiguous from the body, so this lands at 'many gaps; steps poorly defined' rather than 1 only because the text is coherent and names a helper file.	2 / 5
Progressive Disclosure	The tiny body is trivially organized and its one reference is clearly signaled as a markdown link, but the link targets calculate.py, which does not exist in any bundle directory. That fits 'some structure but could be better organized; references present but not clearly (or validly) connected', keeping it below 4's 'minor organization gaps' since the skill's sole navigation element is broken.	3 / 5
	Total	12 / 20 Passed

Description

53%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 states a clear, third-person 'what' but omits any 'when to use' guidance, which both caps completeness and weakens trigger coverage. Keywords are relevant but lack natural synonyms and variations users would actually say.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to compile, evaluate, or transform an expression into executable Python code."

Include natural trigger terms and synonyms such as "expression evaluation", "code generation", or "eval" to improve trigger_term_quality.

Mention companion capabilities (e.g. compiling to code objects vs. AST, handling constraints) to broaden specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	"Compile a caller-provided expression into a Python code object" names the domain (expression compilation) and one concrete action (compiling to a Python code object), matching the '1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because no related actions or variants are covered, and not a 2 because the single action is specific rather than generic.	3 / 5
Completeness	The 'what' is clear (compile a caller-provided expression into a Python code object) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It does not reach 4 because 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	Relevant keywords like "compile", "expression", and "Python code object" exist, but natural variations users would say ("evaluate an expression", "expression evaluator", "code generation") are missing. It fits 'some relevant keywords but missing common variations or synonyms', below level 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	Compiling expressions into Python code objects is a fairly narrow niche with distinct triggers, giving minor overlap risk only with closely related code-generation skills. It is not a 5 because terms like 'compile' and 'Python code' could still collide with general code-execution or generation skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: cisco-ai-defense/skill-scanner
Path: evals/skills/command-injection/eval-execution/SKILL.md
Commit: c3d7fd9

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.