ppt-reliable-creation

Robust PowerPoint generation with shell_agent primary and python-pptx fallback, including directory verification and error debugging

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/ppt-workflow-location-enhanced-72b4a5/SKILL.md

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 content is a strongly actionable, well-sequenced workflow with clear validation and error-recovery loops. Its main weaknesses are length/redundancy across multiple debugging-style sections and a monolithic single-file structure with no progressive disclosure to reference files.

Suggestions

Consolidate the Debugging Commands, Common Pitfalls, Troubleshooting Table, and Best Practices sections, which repeat the same find/2>&1/verify guidance, to cut length and redundancy.

Move the reference-style material (debugging commands, troubleshooting tables) into a references/ file and link to it from SKILL.md to add one-level-deep progressive disclosure.

Fix the flagship python-pptx example by adding 'import os' before os.path.abspath so the script is copy-paste runnable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, actionable command/code rather than concept explanation, but at ~290 lines it repeats the same guidance across Debugging Commands, Common Pitfalls, Troubleshooting Table, and Best Practices (find-before-assuming, 2>&1, verify file size), so it 'could be tightened' rather than earning the lean anchor-3.	2 / 3
Actionability	It provides concrete, executable shell commands (pwd, find, stat, file, cp, tee) and a near-complete python-pptx script with copy-paste-ready examples and a decision tree, matching 'fully executable code/commands; specific examples'.	3 / 3
Workflow Clarity	Steps 0-5 are clearly sequenced with explicit validation checkpoints (pre-check pwd, verify directory match, verify file size/type) and a feedback loop ('After 2 failures switch to Fallback'), matching 'clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	The skill is well-sectioned but is a single ~290-line file with no bundle files (references/scripts/assets absent) and all detail inline; the >50-line exception means sections alone do not earn 3, and content like the debugging/troubleshooting material could be offloaded to references.	2 / 3
	Total	10 / 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 names concrete tools and several actions but lacks an explicit 'Use when' trigger clause and relies on technical jargon over natural user terms. It is a competent but generic statement of capability rather than a trigger-rich, distinctive pitch.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating PowerPoint presentations, especially if shell_agent fails or output files land in unexpected directories.'

Surface natural user terms ('presentations', 'slides', '.pptx') alongside the technical tool names so users' phrasing matches the description.

Drop the filler adjective 'Robust' and replace it with a concrete capability to tighten specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (PowerPoint generation) and several actions ('directory verification', 'error debugging') plus concrete tools (shell_agent, python-pptx), but the action verbs are more abstract than the anchor-3 granular list and 'Robust' is filler, so it sits at 'names domain and some actions, not comprehensive' rather than multiple concrete actions.	2 / 3
Completeness	It states what the skill does, but there is no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	'PowerPoint' is a natural user term, but the description leans on technical jargon ('shell_agent', 'python-pptx') and omits common variations users would say ('presentations', 'slides', '.pptx', 'pptx files'), matching 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	PowerPoint generation with a fallback mechanism is a fairly narrow niche, but without explicit triggers and with the technical-jargon framing it could still overlap with a general presentation skill, fitting 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 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/ppt-workflow-location-enhanced-72b4a5/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.