CtrlK
BlogDocsLog inGet started
Tessl Logo

locate-missing-artifacts

Recover generated files in sandboxed environments by searching from confirmed roots and copying to expected locations

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/locate-missing-artifacts/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 a clear, validated workflow, but carries redundant content (a full re-run example and repeated patterns) that could be tightened or moved to a reference file for better token economy and progressive disclosure.

Suggestions

Trim the 'Example: Complete Recovery Workflow' or fold it into the steps, since it duplicates the Step 1-5 sequence verbatim.

Consolidate 'Common Patterns' into the search step as brief variants rather than restating find/cp commands separately.

If the skill grows further, move the patterns and worked example into a references/ file and link to it one level deep from the overview.

DimensionReasoningScore

Conciseness

Largely lean code-driven content with no conceptual padding, but the full 'Complete Recovery Workflow' example and the 'Common Patterns' section re-run find/cp/validate commands already shown in the steps, adding redundant tokens.

2 / 3

Actionability

Fully executable bash commands (ls, test, find, cp, stat, mkdir) throughout, with concrete copy-paste-ready examples and a worked end-to-end example showing expected output.

3 / 3

Workflow Clarity

A clear five-step sequence with explicit validation checkpoints in Step 1 and Step 5, plus a troubleshooting table providing feedback loops (no results, multiple matches, empty file).

3 / 3

Progressive Disclosure

Well-sectioned with no nested references, but at ~140 lines it exceeds the simple-skill (<50 lines) carve-out and keeps inline content (full worked example, repeated patterns) that a leaner overview could offload to a reference file.

2 / 3

Total

10

/

12

Passed

Description

57%

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 specific and occupies a clear niche, but lacks an explicit 'Use when' trigger clause and natural trigger terms that users would actually say, capping completeness and trigger quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a tool reports success but its output files are missing or a file-not-found error appears in a sandboxed/ephemeral environment.'

Add natural trigger terms users would say such as 'missing files', 'file not found', or 'tool didn't create the file' alongside the procedural phrasing.

Optionally enumerate a couple more concrete actions (e.g. 'verify file accessibility') to lift specificity from some-actions to multiple-specific-actions.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('searching from confirmed roots', 'copying to expected locations'), but does not list a comprehensive set of multiple specific actions.

2 / 3

Completeness

Clearly answers what the skill does, but 'when' is only implied via 'in sandboxed environments' with no explicit 'Use when...' trigger clause, which caps completeness at 2.

2 / 3

Trigger Term Quality

Has relevant terms like 'sandboxed environments' and 'generated files', but leans procedural ('searching from confirmed roots') and misses common natural variations users would say such as 'missing files' or 'file not found'.

2 / 3

Distinctiveness Conflict Risk

The sandboxed-environment artifact-recovery niche is distinctive and unlikely to conflict with unrelated skills, despite the generic 'copying' action.

3 / 3

Total

9

/

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.