CtrlK
BlogDocsLog inGet started
Tessl Logo

finalize-zip-deliverable

Ensures codebase deliverables are properly archived into a ZIP file before marking task complete

55

Quality

61%

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/finalize-zip-deliverable/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete, copy-paste-ready ZIP commands and verification steps, and it is appropriately organized as a self-contained skill. Its main weaknesses are redundant restating of the iteration-urgency rule and a workflow sequence whose step numbering is broken and contradictory (duplicate step 4, out-of-order step 0, two checklists).

Suggestions

Fix the workflow numbering: resolve the duplicate step 4 ('Declare Completion' vs 'Mandatory Pre-Completion Checklist'), move 'Monitor Iteration Count (ONGOING)' to its correct position, and merge the duplicate end-of-file '## Checklist' into the pre-completion checklist.

Collapse the repeated iteration-urgency rules (CRITICAL FAILURE, FAILURE CONSEQUENCE, ITERATION OVERRIDE RULE, ITERATION-AWARE PRIORITY, ITERATION STATUS CHECK) into a single clearly marked section to reduce redundancy.

Keep the actionable command blocks as-is; they are the strongest part of the skill.

DimensionReasoningScore

Conciseness

The skill provides concrete commands without explaining concepts Claude already knows, but it restates the iteration-limit/ZIP-urgency rule many times ('CRITICAL FAILURE', 'FAILURE CONSEQUENCE', 'ITERATION OVERRIDE RULE', 'ITERATION-AWARE PRIORITY', 'ITERATION STATUS CHECK'), which is unnecessary padding that could be tightened.

2 / 3

Actionability

Provides fully executable bash commands with concrete examples ('zip -r project_fallback.zip ./project/', 'ls -lh', 'unzip -l') that are copy-paste ready, satisfying the score-3 anchor rather than the pseudocode of score 2.

3 / 3

Workflow Clarity

Verification checkpoints exist (file existence, non-zero size, contents inspection) and a checklist is present, but the sequence is muddled: '### 0. Monitor Iteration Count' appears after step 1, '### 4. Declare Completion' is an empty header immediately followed by a second '## 4. Mandatory Pre-Completion Checklist', and a redundant duplicate '## Checklist' appears at the end.

2 / 3

Progressive Disclosure

The skill is a self-contained single SKILL.md with no bundle files and is organized into clearly headed sections (Early Warning System, Minimum Viable ZIP Fallback, Workflow Steps, Common Pitfalls, Checklist), meeting the bar for well-organized section-based disclosure without external references.

3 / 3

Total

10

/

12

Passed

Description

50%

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 clear and reasonably specific about a single action (archiving deliverables into a ZIP before completion), but it omits explicit 'Use when...' trigger guidance and lacks broad coverage of natural trigger terms. This caps both completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit 'Use when...' clause stating the natural trigger conditions, e.g. 'Use when delivering a codebase as a single downloadable ZIP artifact or when a task requires a packaged deliverable.'

Broaden trigger-term coverage with common phrasings users would actually say, such as 'zip up', 'package', 'compress', or 'bundle the project'.

Clarify the niche to reduce overlap, e.g. by contrasting against general file-management or build skills.

DimensionReasoningScore

Specificity

Names the domain ('codebase deliverables') and a concrete action ('archived into a ZIP file before marking task complete'), but lists only a single action rather than multiple specific concrete actions as the score-3 anchor requires.

2 / 3

Completeness

Clearly states what the skill does but provides no 'when should Claude use it' trigger guidance; per the judging guidelines, a missing 'Use when...' clause caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant keywords ('ZIP file', 'archived', 'codebase deliverables', 'task complete') but lacks common natural variations users might say ('zip up', 'package', 'compress', 'bundle') and has no 'Use when' phrasing.

2 / 3

Distinctiveness Conflict Risk

The ZIP-archive niche is somewhat specific, but the 'before marking task complete' framing is generic and could overlap with any completion-related skill, so it does not reach the clear-distinct-trigger bar of 3.

2 / 3

Total

8

/

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.