CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-anything-gimp

Command-line interface for Gimp - A stateful command-line interface for image editing, built on Pillow. Designed for AI agents and pow...

Quality

64%

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

Quality

Content

63%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, executable command reference with genuinely useful agent guidance (dual human/JSON output modes, render-time semantics of draw ops, verification of rendered output rather than project state). Its main weaknesses are duplicated quick-start/examples sections, missing example invocations for most command groups, and a ~250-line monolith that should be split into a lean overview plus a reference file.

Suggestions

Move the per-command group tables into a references/COMMANDS.md (one level deep, clearly signaled) and keep only a quick-start, one full workflow example, and the agent guidance in SKILL.md; this also removes the current duplication between Usage, Examples, and Output Formats.

Add at least one example invocation for the highest-risk command groups (filter add/set with parameters, canvas resize vs. scale, export render presets) so an agent doesn't have to guess flag names or consult the external README.

Fold the validation checkpoints ('verify outputs exist', 'review the rendered image', 'parse stderr on non-zero exit') directly into the workflow examples as numbered steps, creating an explicit render→verify→fix loop instead of a separate tips list.

DimensionReasoningScore

Conciseness

The command tables are dense, useful reference material with almost no explanation of concepts Claude already knows, but there is noticeable duplication: 'project new -o' appears in Usage, Examples, and again near Output Formats; the --json invocation is shown three times; and the REPL section is explained twice. This fits anchor 3 ('mostly efficient but includes some... padding that could be tightened') better than anchor 4, since several sections could be collapsed.

3 / 5

Actionability

Commands are concrete and copy-paste ready (e.g. 'cli-anything-gimp --project poster.gimp-cli.json draw text --layer 0 --text "Launch Night" --x 96 --y 120 --size 72 --color "#f6f1e8"'), and the Layered Composition Workflow example shows realistic full syntax including negative offsets. It stops short of 5 because most command groups (filter add, canvas resize, media probe) have only one-line table descriptions with no example invocation or flag reference — full syntax is deferred to an external README.

4 / 5

Workflow Clarity

The Layered Composition Workflow gives a clear create→set offsets→draw→export sequence, and the 'For AI Agents' checklist supplies validation checkpoints ('Check return codes', 'Parse stderr for error messages on failure', 'Verify outputs exist after export operations', 'Review rendered outputs after offset, draw, blend-mode, or filter changes'), so the render path is not a blind trust-the-JSON flow. It is 4 rather than 5 because these checkpoints live in a separate tips section instead of being embedded as explicit steps in each workflow, and there is no fix-and-retry loop for a failed render.

4 / 5

Progressive Disclosure

The body has good section structure but inlines roughly 150 lines of command-group reference tables that clearly belong in a separate reference file, and its pointers ('Full documentation: See README.md in the package', 'See TEST.md', 'HARNESS.md in the cli-anything-plugin') reference package files that are not part of this bundle (references/, scripts/, assets/ are absent), so navigation targets cannot be verified. This matches anchor 3 ('content that should be separate is inline; references present but not clearly signaled').

3 / 5

Total

14

/

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 communicates the tool's identity (stateful, Pillow-based, agent-oriented CLI for image editing) but is generic about capabilities, lacks any 'Use when...' trigger clause, is literally truncated mid-word ('pow...'), and omits the natural vocabulary (layers, filters, resize, export, .png) that would let a user's request match it. It is serviceable but below the bar of the good examples.

Suggestions

Add an explicit 'Use when...' clause with concrete triggers, e.g. 'Use when creating or editing images (layers, filters, resize/crop, text overlay, export to PNG) without a GUI, or when the user mentions Gimp, image editing, or batch image generation.'

Replace the generic 'image editing' with the specific capabilities the CLI actually exposes: layer management, filters, canvas resize/scale/crop, draw text/rect, histogram analysis, and export/render — the SKILL.md body already enumerates these.

Fix the truncation: the frontmatter description ends mid-word at 'pow...' — restore the full sentence and include natural synonyms and file extensions (.png, .jpg, .xcf) to improve trigger matching.

DimensionReasoningScore

Specificity

The description only states "A stateful command-line interface for image editing, built on Pillow" and "create and manipulate images without a GUI" — it names the domain but the actions are minimal and generic; no concrete capabilities (layers, filters, resize, crop, export) are listed. This matches anchor 2 ('Names the domain but actions are minimal or generic', e.g. 'Processes PDF files') better than anchor 3, which requires 1-2 concrete actions like 'extracts content'.

2 / 5

Completeness

The 'what' is reasonably clear ("stateful command-line interface for image editing, built on Pillow"), but the 'when' is only weakly implied via the audience clause "Designed for AI agents and pow..." — there is no 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 because the 'when' is not explicit, and not 2 because the 'what' is clear rather than vague. The description is also literally truncated mid-word ('pow...'), further weakening it.

3 / 5

Trigger Term Quality

Relevant keywords are present ("Gimp", "image editing", "Pillow", "command-line interface", "AI agents") but common natural variations users would say are missing — no 'layers', 'resize', 'crop', 'filters', 'export images', or file extensions like .png/.xcf. This sits at anchor 3 ('Some relevant keywords but missing common variations or synonyms') and below anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

Naming "Gimp" and "Pillow" plus the stateful-CLI framing carves a fairly distinct niche (analogous to 'Works with PDF and Word document files'), so this is mostly distinct with only minor overlap risk against other general image-manipulation skills. It does not reach 5 because 'image editing' is broad enough that other image skills could compete for the same triggers.

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

gimp/agent-harness/cli_anything/gimp/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.