ffmpeg-graceful-degradation

Graceful degradation workflow for ffmpeg encoding failures with progressive fallback strategies

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/ffmpeg-graceful-degradation/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 body is highly actionable with a clear, validated fallback workflow, but it is verbose due to redundant restatements of the fallback chain and a monolithic structure that exceeds the simple-skill threshold. Consolidating the recap/diagram and splitting the reference material would improve efficiency.

Suggestions

Remove redundancy: keep the fallback chain in one place (either Step 3 prose or the Step 4 function) and drop the 'Key Principles' recap and/or the ASCII Decision Flow, which restate the same steps.

Move the full 'safe_video_encode' implementation and the 'Common Error Patterns' table into a separate reference file (e.g. references/fallbacks.md) referenced one level deep, keeping SKILL.md as a lean overview.

Tighten the Overview so it does not re-list every step that the numbered sections immediately restate.

Dimension	Reasoning	Score
Conciseness	Content is accurate and avoids explaining concepts Claude already knows, but the fallback chain is restated three times (Step 3 prose, Step 4 implementation code, and the Decision Flow + Key Principles recap), and the ASCII diagram adds tokens beyond what is needed.	2 / 3
Actionability	Provides concrete executable commands ('ffmpeg -encoders \| grep ...'), real ffmpeg flags, a complete copy-paste 'safe_video_encode' Python function, and working moviepy code.	3 / 3
Workflow Clarity	A clearly sequenced Step 1-4 workflow with an explicit validation checkpoint (test on a short clip before batch) and a fallback retry loop on failure, satisfying the feedback-loop requirement for batch operations.	3 / 3
Progressive Disclosure	The file is well-organized into sections but is a ~190-line monolithic document with the full implementation function, error-pattern table, and decision diagram all inline; content that could live in separate reference files is not split out.	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 correctly identifies a specific ffmpeg domain and approach, but omits an explicit usage trigger and concrete action list. Adding a 'Use when...' clause and naming specific actions would lift the weakest dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when ffmpeg encoding fails due to missing codecs, library mismatches, or container issues, or when batch video processing must not fail partway.'

Enumerate concrete fallback actions (probe encoders, try copy mode, fall back to mpeg4, use bundled moviepy) instead of the generic 'progressive fallback strategies'.

Include natural user phrasing like 'video encoding', 'video conversion failed', or 'ffmpeg error' alongside 'ffmpeg'.

Dimension	Reasoning	Score
Specificity	Names the domain ('ffmpeg encoding failures') and approach ('Graceful degradation workflow', 'progressive fallback strategies') but does not list multiple concrete actions as the score-3 anchor requires.	2 / 3
Completeness	Clearly states what the skill does, but provides no explicit 'Use when...' trigger guidance for when Claude should invoke it, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	'ffmpeg' is a strong natural keyword, but common variations users would say (e.g. 'video encoding', 'video processing', 'conversion failed') are missing.	2 / 3
Distinctiveness Conflict Risk	The ffmpeg niche is reasonably distinct, but the 'graceful degradation / progressive fallback' framing reads as a generic pattern that could overlap with other fallback-style skills.	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/ffmpeg-graceful-degradation/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.