CtrlK
BlogDocsLog inGet started
Tessl Logo

quasi-coder

Expert 10x engineer skill for interpreting and implementing code from shorthand, quasi-code, and natural language descriptions. Use when collaborators provide incomplete code snippets, pseudo-code, or descriptions with potential typos or incorrect terminology. Excels at translating non-technical or semi-technical descriptions into production-quality code.

88

1.00x
Quality

Does it follow best practices?

Impact

96%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is highly actionable with executable examples and clear markers, but it is verbose with significant repetition and explains concepts Claude already knows. Its workflows lack an explicit validation checkpoint for the destructive shorthand-replacement step, and a large monolithic file misses the opportunity to split reference material into separate files.

Suggestions

Consolidate the repeated 'remove `()=>` lines' guidance into a single authoritative rule; it currently appears in Shorthand Indicators, Critical Rules, the Shorthand Key, the Common Pitfalls, the Example Workflow, and the Summary.

Add an explicit validation step to the interpretation workflow — e.g., 'After replacing shorthand, verify no `()=>` or marker lines remain and run available tests before saving' — to close the feedback loop for destructive file edits.

Trim general-knowledge padding ('Apply Expert Knowledge: Use computer science principles, design patterns, and industry best practices') and the duplicated architect-sketch metaphor to respect the context-window budget.

DimensionReasoningScore

Conciseness

The ~370-line body is mostly useful but padded with repetition — the rule to remove `()=>` lines is restated at least six times and the architect-sketch metaphor twice — and it explains basics Claude already knows ('Apply Expert Knowledge: Use computer science principles, design patterns'), so it could be tightened rather than being fully lean.

2 / 3

Actionability

It gives concrete, executable guidance — exact markers (`// start-shorthand`, `()=>`), runnable example code (validateUserInput, the list-comprehension translation), comment directives (REMOVE COMMENT/NOTE), and percentage-based expertise thresholds — copy-paste ready rather than abstract.

3 / 3

Workflow Clarity

A clear sequence exists (the 6-step Interpretation Process and the Example Workflow), but for a skill that destructively replaces shorthand lines in files there is no explicit validation checkpoint (e.g., verify no `()=>` remain, run tests before saving), which caps it at 2 per the destructive-operation guideline.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is a single monolithic ~370-line file; sections like Shorthand Key, Variables and Markers, and Advanced Usage are well-organized but inline content that, given the length, could be split into referenced files rather than one wall of text.

2 / 3

Total

9

/

12

Passed

Description

100%

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 well-crafted: third person, concrete actions, an explicit 'Use when' clause with natural trigger terms, and a distinctive niche. Its only minor weakness is reliance on the coined term 'quasi-code', which is not a phrase users naturally say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'interpreting and implementing code from shorthand, quasi-code, and natural language descriptions' and 'translating non-technical or semi-technical descriptions into production-quality code' — matching the score-3 anchor for multiple specific actions.

3 / 3

Completeness

Explicitly answers both what (interpret/implement/translate code from imperfect descriptions) and when ('Use when collaborators provide incomplete code snippets, pseudo-code, or descriptions with potential typos'), matching the score-3 anchor for explicit triggers.

3 / 3

Trigger Term Quality

The 'Use when' clause surfaces natural terms a collaborator would actually say — 'incomplete code snippets', 'pseudo-code', 'descriptions with potential typos', 'incorrect terminology' — giving good coverage, even though 'quasi-code' is more jargon than conversational.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche — recovering production code from shorthand and imperfect descriptions — with triggers (shorthand, pseudo-code, typo-laden descriptions) unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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
github/awesome-copilot
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.