CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

portfolio-showcase

Automated skill and workflow for adding or updating web project showcases in the portfolio. Handles page discovery, asking the user to confirm target pages/URLs, capturing high-resolution clean screenshots (bypassing onboarding tours/tooltips), generating multi-page composite cover mockups with the portfolio #FBEAD4 background and brand logo, and updating data/showcase.json.

Quality

73%

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 ./.agents/skills/portfolio-showcase/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.

A well-structured, concise SOP with genuinely concrete capture parameters and a sensible phase sequence. The main deficits are missing script invocation examples with the referenced scripts absent from the bundle, and no error-recovery guidance around the build-verification step.

Suggestions

Ship the referenced 'scripts/capture.mjs' and 'scripts/generate-covers.mjs' in the bundle (e.g. under scripts/) or replace the references with self-contained, copy-paste-ready Puppeteer/Node snippets.

Add executable invocation examples for each script (e.g. 'node scripts/capture.mjs --urls <url1,url2> --out public/screenshots/<slug>'), since the capture workflow currently lacks the specific commands to run.

Add a feedback loop after Phase 4: what to check when 'npm run build' fails and when to re-capture (e.g. blank screenshots or visible onboarding tooltips), so the verification step has explicit recovery guidance.

DimensionReasoningScore

Conciseness

The body is lean and directive, assuming Claude's competence with terse bullets and concrete values, but contains minor redundancy — the two scripts are described both inside Phases 2-3 and again in the 'Helper Scripts Reference' section, plus decorative emoji headers — keeping it just below fully efficient.

4 / 5

Actionability

Concrete parameters are given (viewport '1440x900' with 'deviceScaleFactor: 2', specific localStorage keys, '.react-joyride__tooltip' selectors, 'npm run build'), but there are no executable invocation examples for the scripts, and the referenced 'scripts/capture.mjs' and 'scripts/generate-covers.mjs' do not exist in the bundle — key details are missing rather than minor gaps.

3 / 5

Workflow Clarity

A clear four-phase sequence with an explicit mandatory user-confirmation checkpoint in Phase 1 and a build-verification step in Phase 4; however, there is no error-recovery feedback loop (e.g. what to do when the build fails or a screenshot comes back blank), so it does not reach the fully validated anchor.

4 / 5

Progressive Disclosure

Sections and phases are well-organized for a short skill, but its only external references — 'scripts/capture.mjs' and 'scripts/generate-covers.mjs' — point to files absent from the bundle, so the reference structure does not actually resolve for navigation.

3 / 5

Total

14

/

20

Passed

Description

71%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 specific, well-scoped description that clearly conveys the full showcase-generation pipeline with concrete, verifiable details. Its main weakness is the complete absence of a 'when to use' trigger clause, which caps completeness and slightly weakens trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when adding or updating a project in the portfolio showcase, or when the user mentions showcase covers, project screenshots, or the portfolio gallery.'

Include a few natural synonyms users might say, such as 'gallery', 'featured projects', or 'portfolio covers', to broaden trigger coverage.

State the target repository context (e.g. a Next.js portfolio site) so the skill is less likely to trigger for unrelated screenshot requests.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions covering the full pipeline — 'page discovery', 'capturing high-resolution clean screenshots (bypassing onboarding tours/tooltips)', 'generating multi-page composite cover mockups with the portfolio #FBEAD4 background and brand logo', and 'updating data/showcase.json' — which is comprehensive for this skill's scope, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

The 'what' is clearly and thoroughly described, but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Contains good natural keywords users would say — 'portfolio', 'showcase', 'web project', 'screenshots', 'cover mockups' — but misses common variations like 'gallery', 'featured work', or 'add a project to the portfolio', so it falls just short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The portfolio-specific details ('#FBEAD4 background', 'data/showcase.json', 'brand logo') carve out a distinct niche, though 'capturing screenshots' leaves minor overlap risk with generic screenshot-capture skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

glenrioariesto/Portofolio

Path

.agents/skills/portfolio-showcase/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.