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

66%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 delivers a clear, well-validated workflow with strong checkpoint sequencing and feedback loops, but its code examples are not fully executable due to undefined helpers and the body carries redundant restatements of the same three checks. Progressive disclosure is solid for a self-contained single-file skill.

Suggestions

Replace undefined helper functions (extract_format_requirement, extract_action_verbs, get_accessed_files, get_output_summary) with concrete implementations or simpler inline checks so the code is executable.

Remove redundancy: the 'Common Failure Modes' table and 'Quick Reference' restate the three checkpoints — collapse into one condensed reference to tighten conciseness.

Trim the Overview section, which re-explains failure modes already covered later, to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes unnecessary explanation (the Overview restating failure modes) and redundancy between the 'Common Failure Modes' table and the 'Quick Reference', which could be tightened; not 4 due to more than minor padding and not 2 because it is not severely verbose.	3 / 5
Actionability	Concrete Python functions are provided for each checkpoint, but they rely on undefined helpers (extract_format_requirement, extract_action_verbs, get_accessed_files, get_output_summary), making them pseudocode rather than copy-paste executable; fits the some-concrete-guidance-but-incomplete anchor.	3 / 5
Workflow Clarity	The three checkpoints are sequenced in pre_completion_verification with explicit pass/fail validation, feedback messages on failure ('Do not mark complete'), a 'fix first' recovery loop, and a checklist, matching the anchor for clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	The single-file skill has well-organized sections (Overview, Checkpoints, Checklist, When to Apply, Failure Modes, Quick Reference) and needs no external references, but the redundancy across sections keeps it from the cleanest split; good structure with minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

55%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 clearly states three concrete verification actions but lacks an explicit "Use when..." trigger clause and relies on internal process terms rather than natural user phrases. It is adequately specific but capped on completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use before marking a task complete, when delivering files in a required format, or when multiple reference files must all be processed') to raise completeness and trigger term quality.

Include natural user-facing keywords and synonyms (e.g., 'deliverable', 'done', 'finished', 'file format', 'reference files') instead of only internal terms like 'task alignment'.

Sharpen distinctiveness by naming the distinctive trigger (pre-<COMPLETE> verification) so it is less likely to collide with generic quality-check skills.

Dimension	Reasoning	Score
Specificity	"Verify output format, file coverage, and task alignment" lists three concrete verification actions, matching the anchor that lists several specific actions with minor gaps; not 5 because coverage is not comprehensive and not 3 because more than 1-2 actions are named.	4 / 5
Completeness	The "what" is clear (verify format, coverage, alignment) but the only "when" is the weakly implied "before completing" with no explicit "Use when..." clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "output format", "file coverage", and "task alignment" are relevant but lean toward internal process jargon rather than natural phrases a user would say; missing common synonyms, so it sits at the some-relevant-keywords anchor rather than good coverage.	3 / 5
Distinctiveness Conflict Risk	The pre-completion verification niche is somewhat specific but the description could still overlap with generic quality-check or "verify your work" skills, fitting the somewhat-specific anchor rather than mostly distinct.	3 / 5
	Total	13 / 20 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: 3827781

Reviewed: 5 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.