x-verify

Use when a long-running skill needs to check "am I done?" — runs the canonical completion cascade with mandatory fallback to prevent silent success claims

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/x-verify/SKILL.md

Quality

Content

82%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 body is a tight, well-structured verifier skill that practices progressive disclosure by pointing to a canonical cascade file rather than duplicating it. The main weakness is that its core actionable and validation detail resides in external files outside the bundle that cannot be verified.

Suggestions

Surface a one-line summary of each cascade stage's validation checkpoint inline so the workflow is self-contained without opening the external file.

Convert the buried prose reference to feedback_xreview_compliance.md into a clearly signaled link or move it to a references/ file.

If ../x-shared/completion-cascade.md is a stable dependency, note its existence/role explicitly so readers can locate it even when the sibling skill is absent.

Dimension	Reasoning	Score
Conciseness	The body is lean and pointer-based ('Do not re-document the cascade here', 'See ... for the full cascade specification'), assumes Claude's competence, and avoids explaining concepts Claude already knows; the inline YAML output templates earn their place as a concrete contract.	5 / 5
Actionability	Provides concrete executable dispatch ('call Agent tool with subagent_type: "oh-my-claudecode:code-reviewer"', fallback with no subagent_type) and concrete output verdicts, but the core cascade execution detail is delegated to an external file, leaving minor gaps.	4 / 5
Workflow Clarity	Clear sequenced cascade (SCOPE GATE -> ABORT -> EXPLICIT FAILURE -> VERIFICATION -> MANDATORY FALLBACK -> HUMAN-APPROVAL) with checkpoints (fallback, human-approval), but the explicit validation detail lives in the external canonical file rather than being fully visible here.	4 / 5
Progressive Disclosure	Good section structure and a clearly signaled one-level-deep pointer to the canonical file ('single source of truth'), but the referenced file lives outside this skill's bundle (../x-shared/) and cannot be verified, and feedback_xreview_compliance.md is a buried prose reference rather than navigable.	4 / 5
	Total	17 / 20 Passed

Description

75%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 cleanly answers both what and when with a memorable concrete trigger ('am I done?') and low conflict risk. It is slightly held back by abstract action language and limited synonym coverage in the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('runs the canonical completion cascade with mandatory fallback to prevent silent success claims') but the actions are somewhat abstract rather than a comprehensive list of specific capabilities, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly answers both what ('runs the canonical completion cascade with mandatory fallback') and when ('Use when a long-running skill needs to check "am I done?"') with a concrete trigger phrase, matching the top anchor.	5 / 5
Trigger Term Quality	Includes the natural phrase 'am I done?' as a trigger plus 'long-running skill' and 'completion cascade', but misses common synonyms/variations like 'verify', 'finished', or 'complete', fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (completion verification for long-running skills) with a distinct trigger unlikely to fire for unrelated skills, matching the 'clear niche with minimal conflict risk' anchor.	5 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Path: skills/x-verify/SKILL.md
Commit: f17a69e

Reviewed: 6 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.