locate-missing-artifacts

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

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/locate-missing-artifacts/SKILL.md

Quality

Content

81%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 content is highly actionable with a well-sequenced, validated workflow and concrete bash examples, but it carries redundant pattern/example sections that restate the core flow and keeps everything inline despite a length that could justify splitting.

Suggestions

Collapse the 'Common Patterns' and 'Example: Complete Recovery Workflow' sections or trim them to non-duplicative edge cases, since they restate the find/cp steps already in the main workflow.

Move the 'Troubleshooting' table and full worked example into a reference file (e.g. references/recovery-examples.md) and link to it, improving progressive disclosure and token efficiency.

Tighten inline comments like '# Common roots to check' and '# Search by filename' that restate the obvious purpose of the commands.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable bash blocks and no over-explanation of basic concepts, but the 'Common Patterns' and full 'Example: Complete Recovery Workflow' sections re-run the same find/cp flow already covered in the steps, which is more than minor padding.	3 / 5
Actionability	Fully executable, copy-paste-ready bash commands (ls, test, find, cp, stat, mkdir) appear throughout, and the three pattern examples plus the complete worked example with real paths and outputs cover the common cases.	5 / 5
Workflow Clarity	A clear five-step sequence (confirm, identify roots, search, copy, validate) is paired with explicit validation checkpoints in Steps 1 and 5 and a troubleshooting table providing feedback loops for error recovery.	5 / 5
Progressive Disclosure	Structure is clean with well-labeled sections and easy header navigation, but at ~140 lines with no external references, content that could live in separate files (patterns, full example, troubleshooting) is inlined, leaving minor organization gaps versus the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description is third-person, specific, and carves a clear niche, but it lacks an explicit 'Use when...' trigger clause and omits common natural phrases like 'file not found', capping completeness and trigger quality at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when a tool reports success but the file is not at its expected path, or you see file-not-found errors in a sandboxed/ephemeral environment.'

Include natural user-facing phrases such as 'file not found', 'missing artifact', and 'expected location' to improve trigger term coverage.

Consider naming a third concrete action (e.g. validating the recovered file) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Recover generated files in sandboxed environments') and two concrete actions ('searching from confirmed roots', 'copying to expected locations'), matching the 1-2 concrete actions anchor; not comprehensive enough for a 4.	3 / 5
Completeness	It clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords like 'generated files', 'sandboxed environments', 'searching', 'copying' are present but common natural trigger phrases users actually say (e.g. 'file not found', 'missing artifact', 'expected location') are missing, so it sits at 'some relevant keywords' rather than 'good coverage'.	3 / 5
Distinctiveness Conflict Risk	The sandboxed-environment file-recovery niche is mostly distinct with specific triggers, carrying only minor overlap risk with general file-management skills, fitting the 'mostly distinct' anchor.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/locate-missing-artifacts/SKILL.md
Commit: 3827781

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.