CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deburr-edge-cases

Strip AI-codegen cruft from a branch — defensive checks the type system should make unrepresentable, redundant validation, speculative abstraction, no-op wrappers — while preserving load-bearing seams. Use after a feature lands and before merge, when asked to "simplify", "de-ornament", "remove cruft", "make erroneous states unrepresentable", or "clean up" a diff.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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, behavior-preserving quality pass with a strong sequenced workflow, explicit validation feedback loops, concrete verification commands, and illustrative worked examples. Weakest on conciseness (some prose and a stray generator comment could be trimmed) and the worked examples could be shown as diffs for maximal actionability.

Suggestions

Remove the '<!-- Generated by rust-bucket v0.9.7. DO NOT EDIT BY HAND. -->' comment — it is irrelevant noise in a hand-authored skill and slightly undercuts the 'strip cruft' ethos.

Tighten the opening canonical-example paragraph and the preserve-list rationale; the five ornamentation categories plus 'load-bearing until proven otherwise' already convey the philosophy.

Render at least one worked example as a before/after diff (type signature + the deleted accessor/unwrap_or) instead of prose, so the remedy is copy-paste ready.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence without re-explaining basics, but contains some explanatory prose (e.g. the canonical-example paragraph and preserve-list rationale) that could be tightened; a stray 'Generated by rust-bucket' comment is pure noise.

4 / 5

Actionability

Concrete executable commands are present ('cargo check --all-targets', 'cargo clippy --all-targets --all-features', 'cargo nextest run', 'ratchets check') plus a precise finding-shape spec and worked examples; the examples are described in prose rather than as diffs, leaving minor gaps.

4 / 5

Workflow Clarity

A clear six-step sequence with explicit validation checkpoints ('verify suspicious editor diagnostics against cargo check', 'After each change, verify cargo and review it') and feedback loops ('If removing the "cruft" produces a warning... restore it and report', 'add a characterization test first'), matching the top anchor.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear sections (When to use, What counts, What to PRESERVE, Process, Worked examples, Anti-patterns) and no external references needed; it is not under 50 lines, so it stops just short of the 5-anchor self-contained-simple-skill bar.

4 / 5

Total

17

/

20

Passed

Description

87%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 domain, explicit what-and-when, multiple natural trigger phrases, and a clear niche that distinguishes it from correctness reviews. Voice is appropriately third person. Minor room to expand concrete action coverage and add a couple of common synonyms.

DimensionReasoningScore

Specificity

Names the domain and lists several specific cruft categories ('defensive checks the type system should make unrepresentable, redundant validation, speculative abstraction, no-op wrappers') plus the preserve-seam action, but these are category labels rather than fully enumerated concrete actions, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('Strip AI-codegen cruft from a branch... while preserving load-bearing seams') and when ('Use after a feature lands and before merge, when asked to "simplify"...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Good natural keyword coverage with multiple user-sayable phrases ('simplify', 'de-ornament', 'remove cruft', 'make erroneous states unrepresentable', 'clean up'); a few common synonyms like 'refactor' or 'tighten up' are absent, and 'de-ornament' is less colloquial.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (a quality/de-ornamentation pass distinct from a bug hunt) with distinct triggers and an explicit carve-out that correctness findings route elsewhere, giving minimal conflict risk.

5 / 5

Total

18

/

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

imbue-ai/offload

Path

.agents/skills/deburr-edge-cases/SKILL.md

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.