CtrlK
BlogDocsLog inGet started
Tessl Logo

unslopify

Use when you need focused cleanup audits, safe removals, scoped quality-risk reductions, and evidence-backed cleanup plans before touching code.

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 a clearly sequenced, validation-gated workflow and clean one-level reference structure, though it carries redundant gating lists and repeated fail-fast directives that inflate length.

Suggestions

Merge the overlapping command lists in "Invocation and Visibility Proof Requirements" and "Baseline validation to confirm first" into a single gated-checklist section to remove duplication.

State the fail-fast rule once in a canonical location and reference it elsewhere instead of repeating it verbatim three times.

DimensionReasoningScore

Conciseness

The body is directive and avoids explaining concepts Claude already knows, but it repeats itself: the "Invocation and Visibility Proof Requirements" and "Baseline validation to confirm first" sections duplicate the same ./bin/ask gating commands, and the fail-fast directive is stated three times, so it could be tightened rather than earning the lean-every-token-earns-its-place anchor at 3.

2 / 3

Actionability

Provides concrete, copy-pasteable commands ("./bin/ask skills resolve unslopify --json", "./bin/ask repo validate --ephemeral", "rg", "fd") plus a decision matrix and ordered implementation batches, matching the fully-executable-guidance anchor rather than the pseudocode/incomplete anchor at 2.

3 / 3

Workflow Clarity

Six numbered phases are clearly sequenced with explicit validation checkpoints ("Re-run relevant validation after each batch", baseline validation, fail-fast gates) and feedback loops (validate -> fix -> rerun the failed gate), matching the clear-sequence-with-validation anchor; it is not the 2 anchor because checkpoints are explicit, not implicit.

3 / 3

Progressive Disclosure

A dedicated "Progressive Disclosure" section signals one-level-deep references to references/contract.yaml, references/evals.yaml, and references/task-profile.json, all verified to exist as real files, with no nested-reference chains; this matches the clear-overview-with-well-signaled-references anchor rather than the weakly-signaled anchor at 2.

3 / 3

Total

11

/

12

Passed

Description

85%

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 specific, complete, and distinctive with an explicit trigger clause, but its trigger phrasing is more polished-internal than the natural terms a user would actually say.

Suggestions

Add colloquial trigger terms users would naturally say (e.g. "dead code", "remove unused", "tidy up", "stale dependencies") alongside the synthesized phrasing.

Consider a plainer restatement of "scoped quality-risk reductions" and "evidence-backed cleanup plans" so the trigger reads more like a user request.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("focused cleanup audits", "safe removals", "scoped quality-risk reductions", "evidence-backed cleanup plans"), matching the multiple-specific-actions anchor rather than the partial-coverage anchor at 2.

3 / 3

Completeness

Explicitly answers both what (the named cleanup actions) and when (an explicit "Use when you need..." clause), satisfying the both-what-and-when anchor; it is not the 2 anchor because the trigger is stated, not merely implied.

3 / 3

Trigger Term Quality

Contains relevant terms ("cleanup audits", "safe removals", "cleanup plans") but leans toward synthesized/internal phrasing ("scoped quality-risk reductions", "evidence-backed cleanup plans") and omits common colloquial variations like "dead code" or "remove unused", so it stops at some-relevant-keywords rather than full natural coverage.

2 / 3

Distinctiveness Conflict Risk

The scoped, reversible, evidence-backed cleanup niche with the "before touching code" qualifier is a distinct trigger unlikely to overlap with broad refactor skills, matching the clear-niche anchor rather than the still-could-overlap anchor at 2.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
jscraik/Agent-Skills
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.