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.

80

1.00x
Quality

70%

Does it follow best practices?

Impact

96%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/quasi-coder/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 genuinely actionable — precise marker syntax, explicit directives, and worked input/output examples — and the interpretation workflow is clearly sequenced. Its main weakness is redundancy: the same shorthand rules are repeated across five sections and the persona material adds padding, making the file roughly twice as long as its content warrants with no reference files to offload detail.

Suggestions

Collapse the shorthand rules currently spread across 'Shorthand Interpretation', 'Shorthand Key', 'Critical Rules', 'Variables and Markers', and 'Summary' into one canonical section; the 'ALWAYS remove ()=> lines' rule alone is stated five times.

Trim the Role section's persona bullet points ('Expert 10x Software Engineer', 'Creative Problem Solver') to a single sentence — they describe attitudes Claude already has rather than adding instructions.

Move the marker grammar specification and the advanced examples (mixed-language pseudo-code, non-code actions) into a references/ file, keeping SKILL.md as a concise overview with clearly signaled one-level-deep pointers.

DimensionReasoningScore

Conciseness

The ~365-line body is noticeably verbose for a single-purpose skill: the 'ALWAYS remove ()=> lines' rule is stated at least five times (Shorthand Indicators, Critical Rules, Summary, Pitfalls, Example Workflow), the Role section pads with persona flourishes ('Expert 10x Software Engineer', 'Creative Problem Solver') that assume no competence, and the 'Shorthand Key' and 'Variables and Markers' sections restate the same marker specification twice. This matches the 'several unnecessary explanations or padded sections' anchor rather than the mostly-efficient 3 anchor.

2 / 5

Actionability

Concrete, executable guidance dominates: exact marker syntax with per-language examples ('// start-shorthand', '# start-shorthand', '<!-- start-shorthand -->'), explicit directives ('REMOVE COMMENT', 'NOTE'), a full input-to-output example workflow with runnable JavaScript, and a mixed-language Python translation example. Minor gaps (e.g., the 'Complex Multi-Step Logic' section says only 'Convert to proper TypeScript' without showing output) keep it below fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

The 'Interpretation Process' gives a clear six-step sequence (read context → identify goal → assess accuracy → choose approach → replace shorthand → apply syntax), reinforced by a worked example with steps, a troubleshooting table, and 'ask clarifying questions before implementing' for ambiguity. Checkpoints are mostly present but mostly advisory rather than explicit validation gates, so it sits between the 3 and 5 anchors, above the midpoint.

4 / 5

Progressive Disclosure

The skill has no bundle files (no references/, scripts/, or assets/), so everything lives inline in a long single file. Section headers are clear and consistent, but content that would naturally be split out — the shorthand grammar specification, the worked examples, and the advanced/non-code-action cases — is inlined in one monolithic document, matching the 'some structure but could be better organized; content that should be separate is inline' anchor. It avoids the 2 anchor because the file is well-sectioned rather than an unstructured wall of text.

3 / 5

Total

13

/

20

Passed

Description

83%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.

A strong description: concrete capabilities, an explicit 'Use when...' clause with realistic trigger phrases, third-person voice, and a recognizable niche. Minor weaknesses are the 'Expert 10x engineer' hype phrase and the coined term 'quasi-code', which slightly dilute specificity and trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ('shorthand, quasi-code, and natural language descriptions') and several concrete actions — 'interpreting and implementing code', 'translating non-technical or semi-technical descriptions into production-quality code'. It falls just short of the 5 anchor's comprehensive multi-action coverage, and the 'Expert 10x engineer' framing is mild buzzword padding rather than a concrete capability.

4 / 5

Completeness

It explicitly answers both questions: what ('interpreting and implementing code from shorthand, quasi-code, and natural language descriptions... translating... into production-quality code') and when ('Use when collaborators provide incomplete code snippets, pseudo-code, or descriptions with potential typos or incorrect terminology') with concrete trigger phrases. It matches the 5 anchor's pattern directly; the 4 anchor applies only when the 'when' is weaker than here.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'code snippets, pseudo-code', 'shorthand', 'descriptions with potential typos or incorrect terminology' map well to what a user would actually say. A few plausible variations (e.g., 'sloppy pseudocode', 'rough code sketch') are missing, and 'quasi-code' is a coined term users are unlikely to say, so it sits between the 3 and 5 anchors but noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

The niche (salvaging intent from imperfect/incomplete descriptions) is mostly distinct, with specialized markers like 'start-shorthand'. However, 'implementing code from... natural language descriptions' has minor overlap risk with general code-generation skills, keeping it below the 5 anchor's minimal-conflict bar but clearly above the 3 anchor.

4 / 5

Total

17

/

20

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.

Validation — 16 / 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.