CtrlK
BlogDocsLog inGet started
Tessl Logo

verify-all-deliverables

Ensure all required output files are created and verified before marking a task complete

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/verify-all-deliverables/SKILL.md
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 content is a strong, actionable checklist skill with concrete commands, clear sequencing, and explicit validation feedback loops for batch file creation. The only real weakness is minor redundancy between the Instructions and the Example Workflow that affects conciseness.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of concepts Claude already knows, but contains redundant emphasis (the "visible text in your output" instruction is repeated) and the Example Workflow restates steps already given in Instructions. It earns its tokens but could be tightened, so it sits at 2 rather than a fully lean 3.

2 / 3

Actionability

Provides fully executable commands — `ls -la [filename]`, a copy-paste `for` loop with `stat -c%s` and `exit 1` on failure, an exact checklist format, and a concrete worked example with real filenames. It is copy-paste ready with specific examples.

3 / 3

Workflow Clarity

Five steps are clearly sequenced with explicit checkpoints ("Do not proceed to Step 2 until this step produces visible output", "Only output `<COMPLETE>` after all files have been verified"). For these batch file operations it includes per-file and final verification with an explicit troubleshoot-before-proceeding feedback loop, satisfying the batch-operations validation requirement.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), and the skill is a self-contained single file organized into clear sections (Purpose, When to Use, Instructions, Common Pitfalls, Example Workflow) with no nested references. It is well-organized and easy to navigate, matching the well-organized-sections anchor for 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 is concise and third-person, clearly stating what the skill does, but it lacks natural trigger terms and an explicit "Use when..." clause. Trigger coverage is the weakest aspect and caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when a task requires creating multiple output files (e.g., spreadsheet + document, report + summary)."

Include natural user-facing keywords such as "multiple files", "deliverables", "all outputs", or "before marking complete" so the description activates on real phrasings.

Tighten the niche phrasing to reference the multi-deliverable scenario explicitly, reducing overlap with generic task-completion skills.

DimensionReasoningScore

Specificity

Names the domain ("output files") and concrete actions ("created and verified", "marking a task complete"), but is not comprehensive — it lists only a couple of actions rather than multiple specific ones. It is more concrete than "Processes PDF files and extracts content" but stops short of the multi-action breadth of a 3.

2 / 3

Completeness

It answers WHAT (ensure files are created and verified before completion) but provides no explicit "Use when..." trigger guidance, which the rubric caps at 2. Per the guideline, a missing trigger clause prevents scoring 3.

2 / 3

Trigger Term Quality

The description uses generic process language ("required output files", "marking a task complete") with no natural keywords a user would actually say when they need this skill. It reads as a capability summary rather than a trigger-rich description like "PDF files, PDFs, forms, document extraction".

1 / 3

Distinctiveness Conflict Risk

The completion-verification niche is reasonably distinct from most skills, but the wording ("task complete", "output files") is generic enough that it could overlap with broad task-completion or file-generation skills, so it does not reach the clear-niche 3.

2 / 3

Total

7

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
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.