CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

codex-image-gallery

Start or reuse a self-contained local web gallery for browsing Codex-generated images. Use when the user asks to browse Codex generated images, open a local image gallery, inspect ~/.codex/generated_images, view a Codex image output folder, or browse image files produced by Codex.

76

Quality

95%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean, fully executable runbook: every command can be pasted as-is, the workflow has real validation checkpoints and recovery paths for port conflicts, and the heavy code/UI content is properly offloaded to the bundle files. The only blemish is the verbatim repetition of the API-check command between steps 1 and 3, which slightly inflates the token budget without adding information.

DimensionReasoningScore

Conciseness

The body is lean with no concept-explanation padding and assumes Claude's competence, but the identical `node -e 'fetch(...)'` API-check command appears verbatim in both Workflow step 1 and step 3, a duplication that could be trimmed. Anchor 4 (efficient with minor instances that could be trimmed) fits better than anchor 5's "every token earns its place".

4 / 5

Actionability

All guidance is copy-paste executable (`node scripts/server.mjs`, the fetch-based API probe, `pgrep -fl`, `GALLERY_ROOT=... node scripts/server.mjs`, `node --check`, `open http://127.0.0.1:8765/`) and covers the common cases including an already-running server, an occupied port, and a custom image root. Fully matches the anchor-5 example.

5 / 5

Workflow Clarity

A clearly sequenced five-step workflow with explicit validation checkpoints (probe the API before reuse, check for a running process, verify any reused URL before reporting success) plus a dedicated Validation section (`node --check`, endpoint verification), and error-recovery guidance for port conflicts. This is a read-only server skill, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

SKILL.md serves as a concise overview with correctly signaled, one-level-deep references to real bundle files (`scripts/server.mjs`, `assets/index.html`, both present), and the server code and UI template are appropriately split out of the body. Sections are well organized and navigation is trivial, matching the anchor-5 structure.

5 / 5

Total

19

/

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: it states a concrete capability in third person and pairs it with an explicit, well-phrased trigger clause covering multiple natural user formulations including the exact output folder path. The only gap is that the action list stops at start/reuse/browse without hinting at configuration options, which is a minor coverage issue rather than a flaw.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("Start or reuse a self-contained local web gallery for browsing Codex-generated images") with minor coverage gaps (e.g., configurable image root is not mentioned). It lists more than the 1-2 actions of anchor 3 but is not comprehensive enough for anchor 5.

4 / 5

Completeness

Explicitly answers both what ("Start or reuse a self-contained local web gallery for browsing Codex-generated images") and when ("Use when the user asks to browse Codex generated images, open a local image gallery, ...") with concrete trigger phrases, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Comprehensive natural terms with synonyms ("browse", "open", "inspect", "view") plus a concrete path trigger ("~/.codex/generated_images") and folder phrasing ("Codex image output folder"). Matches the comprehensive synonym/extension-style coverage of the anchor-5 example.

5 / 5

Distinctiveness Conflict Risk

Clear niche scoped to Codex-generated images with a distinct path-based trigger; unlikely to fire for unrelated gallery or image skills. Fits the anchor-5 "clear niche with distinct triggers; minimal conflict risk".

5 / 5

Total

19

/

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

daymade/claude-code-skills

Path

daymade-codex/codex-image-gallery/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.