CtrlK
BlogDocsLog inGet started
Tessl Logo

adobe-batch-edit-photos

Apply consistent photo adjustments across a set of images so they look like they were edited together. Use this skill whenever the user says "make my photos look cohesive", "give all these the same style", "apply a warm and golden feel to all of these", "make this cinematic", "match the look across my photos", "edit all my travel photos the same way", "batch edit these", "make these consistent", "fix my phone photos", or uploads a folder of photos and wants a unified, polished result. Also triggers for requests like "apply a preset to all of these", "make these look professional", or "they were shot in mixed lighting — can you fix them all". Outputs direct final image URLs plus an in-chat preview grid and optional Firefly Board link. Access: 🔐 Signed-In required | Gen AI: ❌

71

Quality

88%

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

The canonical home for this skill is adobe-batch-edit-photos in adobe/skills

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A highly actionable, well-sequenced batch pipeline with strong mandatory validation and comprehensive error feedback loops — its main weakness is conciseness, driven by verbatim-repeated fallback routing chains and restated rules across steps that could be consolidated.

Suggestions

Consolidate the repeated source-URL routing chain ('selective_urls[] if Step 5e ran, last preset output from Step 5b if presets ran, otherwise look_adjusted_urls[] from Step 5a') into a single 'Source URL resolution' subsection referenced by Steps 6, 7, and 8 instead of restating it each time.

State the deprecated-tools rule once (e.g., in Hard Constraints) and remove the duplicate restatements in the Look→Parameter Mapping section and Step 5a.

Consider moving the Selective Adaptive Bucket tables and the full Look→Parameter mapping into a short reference block near the Tool Reference, keeping the per-step instructions focused on execution.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but ~660 lines contain verbatim-repeated fallback routing chains ('selective_urls[] if Step 5e ran, last preset output from Step 5b if presets ran, otherwise look_adjusted_urls[] from Step 5a') at Steps 6, 7, and 8, and the deprecated-tools rule restated three times — more than minor tightening opportunity.

3 / 5

Actionability

Fully executable: exact tool names, complete JSON/JS param blocks, specific numeric values (tempA=32, tempB=120, vibrance +15, blurRadius: 12), exact output extraction (results[N].outputUrl), and per-error-code recovery actions covering all common cases.

5 / 5

Workflow Clarity

A clearly sequenced pipeline (Step 0 → 8) with explicit mandatory validation — the Step 2c before/after preview gate that blocks the batch until user confirmation — plus an exhaustive Error Handling table providing feedback loops for recovery, satisfying the batch-operation validation requirement.

5 / 5

Progressive Disclosure

Good section structure with an opening overview and Tool Reference table, and bundle check confirms only non-navigational SVG icons (no references/scripts, no in-body .md links); scored 4 rather than 5 because the 660-line single file inlines heavy reference tables (Look→Parameter mapping, Selective Adaptive buckets) that, while defensible for linear execution, leave minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

96%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.

A strong description: concrete actions, an explicit and exhaustive set of natural trigger phrases, and clear what/when guidance in third-person voice. The only soft spot is mild overlap risk with single-image editing skills on a couple of the more generic photo triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and deliverables — 'Apply consistent photo adjustments across a set of images', 'Outputs direct final image URLs plus an in-chat preview grid and optional Firefly Board link' — giving comprehensive coverage of what the skill does and produces.

5 / 5

Completeness

Explicitly answers both 'what' (consistent photo adjustments for a cohesive set) and 'when' ('Use this skill whenever the user says...' with concrete trigger phrases), matching the model trigger-clause pattern.

5 / 5

Trigger Term Quality

Includes ~13 natural quoted phrases users would actually say ('make my photos look cohesive', 'batch edit these', 'make this cinematic', 'make these look professional', 'fix my phone photos', 'they were shot in mixed lighting') plus the folder-upload scenario, covering synonyms and variations comprehensively.

5 / 5

Distinctiveness Conflict Risk

The batch/cohesion niche and explicit multi-photo triggers are clearly distinct, but a few triggers ('make these look professional', 'fix my phone photos') could overlap with a closely related single-image photo-editing skill.

4 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (687 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
openai/plugins
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.