CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-anything-kdenlive

Command-line interface for Kdenlive - A stateful command-line interface for video editing, following the same patterns as the Blender CLI ...

Quality

56%

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 ./kdenlive/agent-harness/cli_anything/kdenlive/skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 body is a well-organized command catalog with mostly executable examples, but it reads as generated CLI documentation rather than a skill: no end-to-end editing workflow is sequenced, validation for destructive operations is missing, one export example is factually wrong, and all detail lives inline with no bundle references. It lands just below the midpoint on workflow clarity and actionability.

Suggestions

Add a sequenced end-to-end workflow example (project new → import → add-track/add-clip → trim/split → export xml) with explicit verification checkpoints, e.g. check the JSON output and confirm the XML file exists after export, since the skill includes destructive operations (remove-clip, --overwrite) that currently lack validation steps.

Fix the invalid export example: 'export render output.pdf --overwrite' uses a nonexistent 'render' subcommand (the Export group only lists 'xml' and 'presets') and names a .pdf output, which a video tool cannot produce; replace it with the actual export command and its real arguments.

Show full command syntax (arguments and flags) for the core timeline/filter commands instead of name-plus-one-line tables, and move the duplicated project-new and REPL examples into a single section — or push the full command catalog to a references/ file, keeping SKILL.md as a lean overview with clearly signaled links.

DimensionReasoningScore

Conciseness

The command tables are mostly lean, but examples repeat (project new and the REPL invocation each appear twice), comments over-explain the obvious ('# Show help'), and time-sensitive version info ('## Version 1.0.0') is stated outside any deprecated/old-patterns section. This fits the 'mostly efficient but could be tightened' anchor rather than 4, where only minor trimming would be needed.

3 / 5

Actionability

There are concrete, executable invocations ('cli-anything-kdenlive --json project info -p project.json'), but the export example is invalid — 'cli-anything-kdenlive --project myproject.json export render output.pdf --overwrite' references a 'render' subcommand that does not exist in the Export group (only 'xml' and 'presets' are listed) and outputs a .pdf from a video editor — and the command tables omit the arguments/flags needed to actually run most commands (e.g. what 'add-clip' or 'trim' take). Not the 4 anchor because the gaps go beyond minor: the core editing workflow has no complete executable example.

3 / 5

Workflow Clarity

No multi-step process is ever sequenced — examples are isolated single commands and the command-group ordering (Project → Bin → Timeline → … → Export) only implies a rough editing sequence. Validation is essentially absent beyond one agent bullet ('Verify outputs exist after export operations') despite destructive/batch operations (remove-clip, remove-track, --overwrite), which caps this dimension; it sits at the 'rough sequence, many gaps, validation absent' anchor rather than 3 because no explicit step list exists at all.

2 / 5

Progressive Disclosure

Sections are well organized with clear headers, but the full command catalog (~150 lines of tables) is inlined rather than split into a reference file, and the only pointers ('See README.md in the package', 'See HARNESS.md in the cli-anything-plugin') reference files outside the skill bundle (no references/ directory exists) and are not navigable links. Matches 'some structure; references present but not clearly signaled; content that should be separate is inline' rather than 4.

3 / 5

Total

11

/

20

Passed

Description

48%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 identifies a distinct, well-targeted niche (Kdenlive/melt via a stateful CLI) but tells what the tool is rather than what a user can do with it, and it never says when the skill should be invoked. Specific capabilities and a 'Use when…' trigger clause are the main gaps.

Suggestions

Add an explicit 'Use when…' trigger clause, e.g. 'Use when editing video with Kdenlive, building or trimming timelines, applying effects, or generating MLT XML for melt rendering', to answer the 'when should this be used' question directly.

Replace the generic 'A stateful command-line interface for video editing' with concrete capabilities: create/edit projects, import clips, trim/split/move clips on timelines, apply filters and transitions, and export/render — mirroring the command groups the body already documents.

Cut the redundant restatement ('Command-line interface for Kdenlive - A stateful command-line interface…') and the 'following the same patterns as the Blender CLI harness' comparison, which adds no capability or trigger information for users unfamiliar with that harness.

DimensionReasoningScore

Specificity

It names the domain ('Kdenlive', 'video editing', 'MLT XML generation for Kdenlive/melt') but the capability claims are minimal and generic: 'A stateful command-line interface for video editing' describes the interface style rather than concrete actions, and no editing capabilities (clips, timelines, filters, transitions, rendering) are listed. Fits 'names the domain but actions are minimal or generic' better than 3, whose anchor requires 1-2 genuinely concrete capability actions.

2 / 5

Completeness

The 'what' is reasonably clear ('A stateful command-line interface for video editing … Uses a JSON project format with MLT XML generation'), but the 'when' is entirely missing — there is no 'Use when…' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the when-clause is absent, not merely imprecise.

3 / 5

Trigger Term Quality

Natural terms users would say are present — 'Kdenlive', 'video editing', 'melt' — but common variations and synonyms are missing ('edit video', 'render video', 'timeline', 'clips', '.kdenlive', '.mlt'), matching 'some relevant keywords but missing common variations or synonyms'. Not 4 because a user asking to render or cut footage would not naturally hit these triggers.

3 / 5

Distinctiveness Conflict Risk

'Command-line interface for Kdenlive' plus 'MLT XML generation for Kdenlive/melt' carves a clear niche with distinct tool-name triggers and minimal conflict risk. It falls short of 5 because the broad phrase 'video editing' and the reference to 'the Blender CLI harness' create minor overlap with general video-editing or other CLI-harness skills.

4 / 5

Total

12

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

HKUDS/CLI-Anything

Path

kdenlive/agent-harness/cli_anything/kdenlive/skills/SKILL.md

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.