code-completion-semantic-constraints

Automatically complete partial code snippets while satisfying semantic constraints including variable types, invariants, pre/post-conditions, interface contracts, and expected input/output behavior. Use when users provide incomplete code with specific requirements like "complete this function that takes a list and returns sorted unique elements" or "fill in this method body that must maintain the invariant that x stays positive" or "implement this interface method with these type constraints." Produces compilable, executable code with tests and a constraint satisfaction report.

1.02x

Quality

78%

Does it follow best practices?

Impact

95%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/code-completion-semantic-constraints/SKILL.md

Quality

Content

60%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.

A well-structured, clearly sequenced workflow with concrete example inputs, but it is held back by Workflow/Output Format redundancy, generic guidance, and example outputs described in prose rather than shown as real completed code.

Suggestions

Show at least one fully completed executable code example (not just the TODO stub and a prose description of the output) so the expected result is unambiguous and copy-pasteable.

Collapse the Output Format section into the Workflow or remove the redundancy with Steps 3–5, and drop generic bullets like "Follows language idioms and best practices" that Claude already knows.

Add an explicit feedback loop after generating verification tests (run tests → if failing, fix the code → re-run) to turn Step 4 into a true validation checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the Output Format section restates Workflow steps 3–5 (completed code, tests, report) and several bullets state concepts Claude already knows ("Follows language idioms and best practices"), so it could be tightened.	3 / 5
Actionability	Example inputs and constraints are concrete, but every example output is described in prose ("Completed function with sorting logic, tests...") rather than shown as actual executable completed code, leaving a key gap for a code skill.	3 / 5
Workflow Clarity	Five clearly sequenced steps with a clarification checkpoint in Step 2 and verification tests in Step 4; validation is present, though no explicit validate→fix→retry feedback loop is stated.	4 / 5
Progressive Disclosure	Self-contained file with clear section structure (Overview, Workflow, Examples, Output Format, Language Support) and no bundle files; at ~130 lines it is over the simple-skill threshold but remains well-organized, with only minor externalization potential for the examples.	4 / 5
	Total	14 / 20 Passed

Description

96%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, specific description that clearly states capabilities and gives concrete, natural trigger phrases with synonyms. The only soft spot is distinctiveness, since general code-writing skills cover overlapping territory.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — completing partial code, satisfying typed constraints (variable types, invariants, pre/post-conditions, interface contracts), and producing compilable code with tests and a constraint satisfaction report — giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	Explicitly answers both what (code completion plus compilable code, tests, and report) and when ("Use when users provide incomplete code with specific requirements like...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides three natural, varied trigger phrases with synonyms ("complete this function", "fill in this method body", "implement this interface method") that users would plausibly say when needing this skill.	5 / 5
Distinctiveness Conflict Risk	The semantic-constraint framing (types, invariants, contracts) is a distinct niche, but code completion broadly overlaps with general write-code skills, leaving minor conflict risk rather than minimal.	4 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ArabelaTso/Skills-4-SE
Path: skills/code-completion-semantic-constraints/SKILL.md
Commit: 4f38503

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.