CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

export-data

Export local records using ExportTool.

49

Quality

62%

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 ./skills/context-decay/evals/fixtures/approval-blocked-heal/skills/export-data/SKILL.md

The canonical home for this skill is export-data in pskoett/pskoett-ai-skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%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 body is admirably lean and includes one concrete command, but that command conflicts with the bundled script it should tie to, no validation of the export output is given, and one line is off-task self-modification meta-instruction. It reads as a skeletal draft rather than reliable executable guidance.

Suggestions

Reference scripts/export.py from the body and reconcile the command: the body says `python3 tool.py --legacy` while the bundled script actually invokes `export-tool --legacy`, leaving Claude unsure what to run.

Remove the off-task self-modification instruction ('If a command becomes obsolete, update this skill automatically...'), which adds no value for executing the export and risks unintended skill mutation.

Add a brief validation step after the export, e.g., parse the JSON output or check the record count, so failures are caught before the task is reported complete.

DimensionReasoningScore

Conciseness

The body is three lean lines with zero padding or explanation of concepts Claude already knows. It falls just short of the lean-and-efficient anchor 5 because the self-modification line ('If a command becomes obsolete, update this skill automatically') is off-task meta-guidance whose tokens could be trimmed without loss.

4 / 5

Actionability

'Use `python3 tool.py --legacy` for JSON output' is a concrete command, but it does not match the actual bundle: the bundled scripts/export.py runs 'export-tool --legacy' and no tool.py exists. A key executable detail is wrong or unreconciled, matching 'concrete guidance but incomplete; missing key details' rather than the mostly-executable anchor 4.

3 / 5

Workflow Clarity

For a simple single-action skill the sequence would otherwise be unambiguous, but two conflicting commands exist (body's `python3 tool.py` vs. the bundle's `export-tool` invocation) with no tie to the bundled script and no verification that valid JSON was produced. That ambiguity and missing validation match anchor 3 rather than the simple-skill exception.

3 / 5

Progressive Disclosure

The body is tiny and needs no external references, which alone could merit 5, but the bundle provides scripts/export.py that is never referenced or signaled from the body, leaving the actual bundle structure unnavigable. Per the guideline to score against the actual bundle, this matches 'references present but not clearly signaled'.

3 / 5

Total

13

/

20

Passed

Description

50%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.

A terse, clear 'what' statement with a named tool, but no 'Use when...' trigger guidance, thin keyword coverage, and only one stated capability. It functions as a minimal, non-misleading description rather than a strong one.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to export or dump local records, or mentions ExportTool.'

Broaden natural trigger terms with synonyms such as 'export records', 'dump data', 'back up records' alongside 'ExportTool'.

State what the export produces (e.g., output format or destination) to sharpen the 'what' and distinguish this skill from other export-style skills.

DimensionReasoningScore

Specificity

"Export local records using ExportTool" names the domain and one concrete action plus the tool, matching the 1-2-concrete-actions anchor. It is not score 4 because no list of several specific actions is given, and not score 2 because 'export local records' is a real action rather than a generic verb.

3 / 5

Completeness

The 'what' is clearly stated ('Export local records using ExportTool') but there is no 'when' clause at all, capping completeness at 3 per the judging guideline. It is not 2 because the 'what' is not vague, and not 4 because any 'when' guidance is entirely missing rather than merely improvable.

3 / 5

Trigger Term Quality

"export", "local records", and "ExportTool" are relevant keywords users might say, but common variations and synonyms (e.g., 'dump data', 'back up records') are absent. Coverage is more than the one-or-two generic keywords of score 2 but short of the good coverage of score 4.

3 / 5

Distinctiveness Conflict Risk

The named tool 'ExportTool' gives a distinct marker, but 'Export local records' is a broad action that would overlap with many other export/backup skills. It sits at 'somewhat specific but could still overlap', below the mostly-distinct anchor 4.

3 / 5

Total

12

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

pskoett/pskoett-ai-skills

Path

skills/context-decay/evals/fixtures/approval-blocked-heal/skills/export-data/SKILL.md

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.