unslopify

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

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Infrastructure/references/deferred-skill-context/agent-ops-unslopify/SKILL.md

Quality

Content

77%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 content is a strong, well-structured runbook with explicit validation gates, fail-fast feedback loops, and clean progressive disclosure to verified reference files. Its main weakness is moderate redundancy across the safety/failure/baseline sections rather than verbosity from over-explaining known concepts.

Suggestions

Consolidate the repeated fail-fast statement and resolver/handles validation commands into a single canonical section, referencing it from the other locations to trim tokens.

Add one concrete example command per discovery lane (or a short table) so Lane 1-8 guidance is as executable as the Phase 1 examples.

De-duplicate the 'Invocation and Visibility Proof Requirements' list with the 'Baseline validation to confirm first' list, since several commands appear in both.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient runbook prose, but the fail-fast directive and the resolver/handles validation commands are repeated across 'Failure mode', 'Invocation and Visibility Proof Requirements', and 'Baseline validation to confirm first', which could be consolidated.	3 / 5
Actionability	Provides concrete copy-paste commands (e.g., './bin/ask skills resolve unslopify --json', 'rg', 'fd'), a decision matrix, and ordered batch guidance, but the eight discovery lanes are described at a high level without per-lane exact commands, leaving minor gaps.	4 / 5
Workflow Clarity	Six phases are clearly sequenced with explicit validation checkpoints, fail-fast feedback loops ('stop at the first failed gate ... rerun the failed gate only after the blocker is fixed'), and a decision-matrix checklist; validation is ample so the batch/destructive cap does not apply.	5 / 5
Progressive Disclosure	A dedicated 'Progressive Disclosure' section clearly signals one-level-deep references to real files (references/contract.yaml, references/evals.yaml, references/task-profile.json), and machine-readable artifacts are appropriately externalized while the operational workflow stays inline.	5 / 5
	Total	17 / 20 Passed

Description

62%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.

The description is well-structured with an explicit 'Use when...' trigger and a clear, multi-part 'what', but it loses points for second-person voice and for missing the most natural user trigger terms (dead/unused code). It is distinct but overlaps slightly with adjacent cleanup/review skills.

Suggestions

Rewrite in third person (e.g., 'Performs focused cleanup audits... Use when the user requests...') to avoid the specificity penalty and improve trigger naturalness.

Add concrete trigger terms users actually say, such as 'dead code', 'unused exports', 'stale dependencies', and 'refactor cleanup', to broaden trigger-term coverage.

Make the 'when' clause name external user signals rather than restating the skill's own activities (e.g., 'Use when the user mentions dead code, stale exports, or brittle fallback paths in an owned scope').

Dimension	Reasoning	Score
Specificity	Names several concrete activities ('focused cleanup audits, safe removals, scoped quality-risk reductions, and evidence-backed cleanup plans') which would anchor at 4, but the second-person phrasing ('Use when you need') triggers the mandated specificity penalty of -1.	3 / 5
Completeness	Explicitly answers both what (the four cleanup activities) and when ('Use when you need ... before touching code'), but the 'when' trigger is somewhat self-referential rather than naming concrete user-mentionable signals, so it does not reach the 5 anchor.	4 / 5
Trigger Term Quality	Relevant keywords like 'cleanup', 'safe removals', and 'cleanup plans' are present, but common natural variations users actually say ('dead code', 'unused', 'refactor', 'stale exports') are missing from the description.	3 / 5
Distinctiveness Conflict Risk	The evidence-first, scoped, 'before touching code' framing carves a distinct cleanup niche, but it has minor overlap risk with closely related skills like [[simplify]] and verification skills referenced in See Also.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Infrastructure/references/deferred-skill-context/agent-ops-unslopify/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.