task-verification-checkpoints

Verify output format, file coverage, and task alignment before completing

Quality

60%

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 ./benchmarks/gdpval/skills/task-verification-checkpoints/SKILL.md

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 well-structured and highly actionable, with executable validation code and an explicit validation-gated completion workflow. The main weakness is mild redundancy between the checkpoints, the failure-modes table, and the quick reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of Claude-known concept explanations, but the failure-modes table and repeated Question/Actions framing restate the checkpoints, so it could be tightened to earn a 3.	2 / 3
Actionability	Provides fully executable Python validation functions with real logic (extension checks, set-difference coverage, verb-subset matching) plus concrete step lists, meeting the copy-paste-ready bar.	3 / 3
Workflow Clarity	A clear three-checkpoint sequence feeds a pre-completion checklist with an explicit validation gate and a fail-then-fix feedback loop ('If ANY box unchecked -> Do NOT complete, fix first').	3 / 3
Progressive Disclosure	A self-contained single-file skill with no bundle files, organized into clear sections (Overview, Checkpoints, Checklist, When to Apply, Failure Modes, Quick Reference); per the simple-skills note, well-organized sections alone earn a 3.	3 / 3
	Total	11 / 12 Passed

Description

35%

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 clearly states what the skill does but omits natural trigger terms and explicit 'when to use' guidance, capping completeness and trigger-term quality. Adding a 'Use when...' clause with user-facing keywords would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating deliverables from reference files, when a task specifies an output format, or before declaring any task complete.'

Replace process jargon ('file coverage,' 'task alignment') with natural user-facing terms ('process all input files,' 'revising vs. creating a report').

Tie the description to concrete, distinctive contexts (e.g. format mismatches like PDF vs PPTX) to reduce overlap with generic verification skills.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('Verify output format, file coverage, and task alignment') but 'task alignment' is abstract and the set is not comprehensive, matching the score-2 anchor rather than the multiple-specific-actions bar of 3.	2 / 3
Completeness	States the 'what' clearly but the 'when' is only the bare 'before completing' with no explicit 'Use when...' trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	Contains no natural user-facing trigger terms; 'output format,' 'file coverage,' and 'task alignment' are process jargon with no 'Use when...' phrasing a user would naturally say.	1 / 3
Distinctiveness Conflict Risk	Verification phrasing is somewhat specific but generic enough to overlap with other QA/verification skills, and without distinct triggers it does not reach the clear-niche bar of 3.	2 / 3
	Total	7 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/task-verification-checkpoints/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.