CtrlK
BlogDocsLog inGet started
Tessl Logo

fallback-file-creation

Fallback pattern for reliable file creation when code execution tools fail

64

Quality

76%

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/fallback-file-creation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with clear, verified workflows and executable examples, but it is a monolithic single file with some redundancy between the two worked examples and the best-practices list. Splitting reusable detail into reference files and de-duplicating examples would improve it.

Suggestions

De-duplicate the PDF and DOCX examples into one parameterized worked example plus a short table of format-specific verification commands (pdfinfo, unzip -l).

Move the Best Practices and Troubleshooting sections into a reference file (e.g., references/TROUBLESHOOTING.md) and link to it, adding one-level-deep progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient and actionable, but the PDF and DOCX examples repeat the same four-step structure and the Best Practices list overlaps the steps, so it could be tightened, matching the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It provides fully executable commands (pwd, heredoc scripts, chmod, pdfinfo, unzip -l) and two complete copy-paste worked examples, matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The five steps are clearly sequenced with an explicit Verify Output checkpoint and an Iterative Debugging feedback loop, matching the 'clear sequence with explicit validation steps; feedback loops' anchor.

3 / 3

Progressive Disclosure

With no bundle files present, the ~150-line skill is a single well-organized monolithic file with no one-level-deep references, matching the 'some structure but content that should be separate is inline' anchor rather than a multi-file overview.

2 / 3

Total

10

/

12

Passed

Description

75%

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 conveys a specific niche (fallback file creation when execution tools fail) and answers both what and when, but its trigger terms lean technical and its enumerated actions are thin. Tightening the natural-language triggers and listing concrete actions would raise it further.

Suggestions

Add natural-language trigger terms users would actually say (e.g., 'when creating PDF, DOCX, or other files fails', 'file creation keeps failing') instead of relying on 'fallback pattern' and 'code execution tools fail'.

Enumerate concrete actions in the description (e.g., 'create and verify PDFs, DOCXs, and other file outputs') rather than the single phrase 'reliable file creation'.

DimensionReasoningScore

Specificity

The description names the domain ('file creation') and one action concept ('reliable file creation') but does not enumerate concrete, multiple actions like creating PDFs or DOCXs, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It explicitly answers both what ('Fallback pattern for reliable file creation') and when ('when code execution tools fail'), providing equivalent explicit trigger guidance, matching the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

'file creation' is a natural term a user might say, but 'fallback pattern' and 'code execution tools fail' are technical jargon and common variations are missing, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The narrow fallback-for-tool-failure niche with a distinct trigger is unlikely to overlap with other skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor.

3 / 3

Total

10

/

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.