adobe-retouch-portraits

Bulk-retouch a folder of portrait photos using Adobe tools — designed for wedding photographers and event photographers who need fast, walk-away batch processing. Use this skill when the user says "retouch my photos", "batch process these portraits", "process my wedding photos", "clean up this folder of images", "run my headshots through Adobe", or uploads/selects a folder of photos and wants them polished and ready to review. Automatically applies auto-straighten, auto-tone, and auto-light to every image. Outputs a preview grid and download folder. Access: 🔐 Signed-In required | Gen AI: ❌ by default — optional background-only cleanup only where the surface permits generative AI (e.g. Codex); none on Claude

Quality

86%

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

Quality

Content

77%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 thorough, highly actionable batch pipeline with strong sequencing and a mandatory validation gate. Its weaknesses are redundant restatements of the generative-AI policy and a monolithic structure that keeps reference-worthy detail inline.

Suggestions

Consolidate the Generative AI Policy: state it once in its section and reference it from the Hard Constraints and frontmatter instead of repeating the full policy three times.

Move the Preset Plan buckets and mood→preset guidance into a references/ file (e.g. PRESETS.md), keeping SKILL.md as an overview that signals where the detail lives — this would also lift progressive_disclosure.

Extract the Error Handling table into a references/ERRORS.md and reference it from each step, reducing repetition of the no-widget fallback and failure-handling patterns.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational detail that earns its place, but the Generative AI Policy is restated three times (frontmatter, dedicated section, Hard Constraints) and no-widget fallback patterns repeat across steps, so it could be tightened; not verbose enough to drop to 2.	3 / 5
Actionability	Fully executable guidance: exact tool names, concrete parameter values, JSON/JavaScript call examples, and explicit output-extraction patterns that are copy-paste ready across common cases.	5 / 5
Workflow Clarity	Clearly sequenced Steps 0–8 with an explicit mandatory validation gate (Step 2c preview) and feedback loops (No → re-collect and re-preview), plus a comprehensive error-handling table; the batch operation has validation, so the batch cap at 3 does not apply.	5 / 5
Progressive Disclosure	Good in-file section structure and easy navigation via headers, but the skill is monolithic — only icon assets exist, with no reference files, so the preset-plan buckets, mood→preset table, and error-handling table are all inlined rather than split out.	3 / 5
	Total	16 / 20 Passed

Description

95%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 that clearly states the skill's purpose, audience, concrete actions, and explicit natural-language triggers. The only gap is that the listed actions don't cover the full pipeline (presets, blur, crop).

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Automatically applies auto-straighten, auto-tone, and auto-light', 'Outputs a preview grid and download folder') but omits presets/blur/crop, leaving minor coverage gaps consistent with a 4 rather than a 5.	4 / 5
Completeness	Explicitly answers both what ('Bulk-retouch a folder of portrait photos…applies auto-straighten, auto-tone, and auto-light…Outputs a preview grid') and when ('Use this skill when the user says…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases ('retouch my photos', 'batch process these portraits', 'process my wedding photos', 'clean up this folder of images', 'run my headshots through Adobe') plus the upload/select-a-folder phrasing, covering synonyms and user wording.	5 / 5
Distinctiveness Conflict Risk	Clear niche (portrait retouching for wedding/event photographers via Adobe tools) with distinct, specific triggers that minimize overlap with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (659 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
Path: plugins/adobe/skills/adobe-retouch-portraits/SKILL.md
Commit: 5fd93af

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.