CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-simplifier

Clean up the changed code for reuse, simplification, efficiency, and altitude, then apply the fixes. Quality only — it does not hunt for correctness bugs (use code-review for that). Use when the user wants to simplify, tidy, refactor, de-duplicate, or clean up their recent changes or working diff.

Quality

90%

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

86%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 tight, well-structured wrapper skill that delegates to a built-in capability and provides a concrete, sensible fallback. The main gaps are minor: an exact command for the merge-base diff variant and a post-edit verification step in the fallback path.

Suggestions

Add the explicit command for the third diff variant, e.g. `git diff $(git merge-base HEAD origin/main)..HEAD`, so all three fallback diff sources are copy-paste ready.

Add a brief verification step after applying edits in the fallback path, e.g. 'confirm behavior is preserved (run relevant tests or re-read the diff) before finishing'.

DimensionReasoningScore

Conciseness

The 18-line body is lean throughout: "Thin wrapper over Claude Code's built-in simplify skill" states the purpose in one line, and the fallback steps give only actionable detail with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching anchor 5.

5 / 5

Actionability

The primary path is directly executable ("Run the built-in simplify skill via the Skill tool, forwarding any arguments") and the fallback gives concrete commands ("git diff, git diff --staged") and specific criteria ("duplicated logic that could reuse an existing helper", "smallest safe edits"). It misses anchor 5 because the third diff variant ("the branch diff vs the merge-base with the default branch") is described but no copy-paste command is given, leaving a minor gap.

4 / 5

Workflow Clarity

The sequence is clear: numbered primary path, then an explicit conditional fallback ("If the built-in simplify skill is unavailable") with ordered sub-steps, matching anchor 4. It falls short of anchor 5 because there is no validation checkpoint after applying edits (e.g., confirming behavior is preserved by running tests), though the edits are not destructive/batch operations so the anchor-3 cap does not apply.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (none exist in the bundle), and is well organized: a one-line purpose statement, a numbered procedure, and a clearly demarcated boundary note ("This is a quality pass only — do not report or fix correctness bugs here"). Per the simple-skill guideline this matches anchor 5.

5 / 5

Total

18

/

20

Passed

Description

91%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 that clearly states what the skill does, when to use it with natural trigger synonyms, and even a boundary clause routing correctness bugs elsewhere. The only weakness is unavoidable trigger overlap with the closely related built-in simplify and code-review skills.

DimensionReasoningScore

Specificity

"Clean up the changed code for reuse, simplification, efficiency, and altitude, then apply the fixes" lists several concrete actions and names the specific quality dimensions; it falls just short of anchor 5's comprehensive coverage because the individual cleanup operations (what 'simplify' or 'de-duplicate' concretely do) are only named, not enumerated. It is clearly above anchor 3, which expects only 1-2 concrete actions.

4 / 5

Completeness

The 'what' is explicit ("Clean up the changed code for reuse, simplification, efficiency, and altitude, then apply the fixes") and the 'when' is explicit with concrete trigger phrases ("Use when the user wants to simplify, tidy, refactor, de-duplicate, or clean up..."). It even adds explicit negative scope ("does not hunt for correctness bugs"), matching the anchor 5 example pattern exactly; anchor 4's weaker 'when' does not apply.

5 / 5

Trigger Term Quality

"simplify, tidy, refactor, de-duplicate, or clean up their recent changes or working diff" provides comprehensive natural-language synonym coverage for the domain, plus "working diff" / "recent changes" as object triggers users would actually say. File extensions don't apply to this task type, so nothing meaningful is missing; anchor 5 fits better than anchor 4's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

It carves a mostly distinct niche and explicitly disambiguates from the closest neighbor ("it does not hunt for correctness bugs (use code-review for that)"), matching anchor 4's 'minor overlap risk with closely related skills'. It stops short of anchor 5 because triggers like 'simplify' and 'refactor' overlap heavily with the built-in simplify/code-review skills it wraps, so conflict risk is not minimal.

4 / 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

BigSimmo/PsychSift

Path

.claude/cloud-profile/skills/code-simplifier/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.