CtrlK
BlogDocsLog inGet started
Tessl Logo

shell-doc-gen-and-locate

Generate documents via shell commands and locate nested outputs using find.

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/shell-doc-gen-and-locate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is a lean, well-structured workflow with explicit verification and error-recovery steps, scoring well on conciseness, workflow clarity, and progressive disclosure; its only weak spot is actionability, where the generation step lacks a concrete example script.

Suggestions

Add a minimal example generation script body (e.g., a short python-pptx script) so the generation step is copy-paste ready rather than described.

Replace the placeholder "cp /path/to/nested/file.pptx ./" with a find-driven pipeline (e.g., cp $(find . -type f -name "*.pptx" | head -1) ./) to make retrieval directly executable.

Tighten the error-recovery hint into an explicit validate->retry loop (re-run find, fall back to stderr inspection, then re-copy).

DimensionReasoningScore

Conciseness

The body is lean and does not pad with concepts Claude already knows (no "what is a PDF" exposition); each section (Objective, When to Use, Procedure, Best Practices) earns its place and assumes Claude's competence.

3 / 3

Actionability

The locate/retrieve steps give executable, copy-paste-ready commands (find . -type f -name "*.pptx", find ... -mmin -10), but the core generation step only says to "write a script" with no example script body, and the cp example uses a placeholder path, leaving guidance incomplete.

2 / 3

Workflow Clarity

A clear four-step sequence (Attempt Generation -> Locate -> Retrieve -> Verification) with explicit checkpoints ("verify the file exists and is non-zero size", "Confirm the file opens correctly") and an error-recovery path (check stderr if not found); validation is present so no destructive-operation cap applies.

3 / 3

Progressive Disclosure

At ~50 lines with no bundle files and no need for external references, the well-organized sections satisfy the rubric's allowance for simple skills to score 3 on progressive disclosure.

3 / 3

Total

11

/

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 uses third person and names concrete actions with specific tools, but it is missing an explicit "Use when..." trigger clause and lacks natural file-type keywords, leaving every dimension at the middle level.

Suggestions

Add an explicit trigger clause, e.g. "Use when standard document-generation tools fail or the generated file lands in an unexpected nested directory."

Name concrete file types users would mention (PowerPoint/.pptx, PDF/.pdf) instead of the generic "documents".

Include natural phrasings like "create a slide deck" or "find the generated file" so the trigger terms match what a user would actually say.

DimensionReasoningScore

Specificity

It names two concrete actions ("Generate documents via shell commands", "locate nested outputs using find") with named tools (shell, find), but the object "documents" is generic and no file types are enumerated, so it is not the comprehensive multi-action list of the top anchor.

2 / 3

Completeness

It clearly answers "what" (generate via shell + locate via find) but has no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Relevant keywords like "documents" and "find" appear, but natural file-type triggers a user would say (e.g., PowerPoint, .pptx, PDF, "create a slide deck") are missing, and "nested outputs" / "shell commands" lean technical rather than conversational.

2 / 3

Distinctiveness Conflict Risk

The "locate nested outputs using find" niche is somewhat distinct, but "generate documents" overlaps with other document-creation skills and there are no distinct file-type triggers to disambiguate it.

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.