SKILLEMALL.ai
GitHub ↗ RU Sign in

CD qwen-mm-plugins-video-edit

Editing-director skill that OWNS every video task built from EXISTING REAL FOOTAGE the user supplies (vlog, montage, intro, recap, eating/travel/family edits, style replication, compositing, subtitles, voiceover, B-roll). When footage files are the input, use THIS skill first — not the generic hyperframes entry and not the general-video workflow: it contributes footage judgment (selection, pacing, beat-sync, sound, looks, per-scene design) and then hands the designed composition to the HyperFrames pipeline for assembly and rendering, so the two are complementary rather than alternatives. It enforces the taste contract, scene-loop assembly with a Scene Ledger, and evidence-based independent review via its own plan-gate and review-gate scripts. Only tasks with NO real footage at all (a motion graphic or promo invented from a brief) go straight to hyperframes. Governance scales by mode instead of confirming every step.

QwenLM/Qwen-MM-Plugins Agent Skills author: QwenLM 80 files · 3 scripts body ≈ 3 383 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Editing-director skill that OWNS every video task built from EXISTING REAL FOOTAGE the user supplies (vlog, montage, intro, recap, eating/travel/family edits…

As a process D 38/100 · Unfinished process — References files that are not bundled: scripts/plan_gate.sh, scripts/loudness_check.sh, scripts/scene_gate.sh

GeneratorMedia and videotype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
69
Run on models
none yet
Process rating
D
38/100
Unfinished process
References files that are not bundled: scripts/plan_gate.sh, scripts/loudness_check.sh, scripts/scene_gate.sh
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/plan_gate.sh
  • warning missing-ref reference to a missing file: scripts/loudness_check.sh
  • warning missing-ref reference to a missing file: scripts/scene_gate.sh
  • warning missing-ref reference to a missing file: scripts/review_gate.sh
  • warning missing-ref reference to a missing file: scripts/README.md

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: scripts/plan_gate.sh, scripts/loudness_check.sh, scripts/scene_gate.sh
  • 0Tools and files. 5 referenced file(s) missing: scripts/plan_gate.sh, scripts/loudness_check.sh, scripts/scene_gate.sh
  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 3 mutating operations with no state check
  • 40Consistency. Frontmatter name (qwen-mm-plugins-video-edit) differs from the folder (skill)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 22 steps
  • 100Execution cost. Instruction body is 3383 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (9 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 929: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 22 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.