CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

preview-my-work

Boot, reopen, update, or reset OpenWork PR previews. Discover script worlds; choose preview-desktop (app only), preview-den (Den only), preview-full (Den plus desktop), or preview-app-web locally, on a private Daytona URL, or on Freestyle for hands-on testing.

Quality

79%

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 ./.opencode/skills/preview-my-work/SKILL.md
SKILL.md
Quality
Evals
Security

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.

An exceptionally actionable, well-validated operational guide whose weaknesses are length and monolithic structure: heavy caveat-dense prose and several deep-dive sections that should be split into reference files.

Suggestions

Move the "Saved web evidence checkpoints" and app-web proxy/signed-URL sections into separate reference files, keeping SKILL.md a lean overview with one-level-deep pointers.

Convert the long caveat sentences into short imperative bullets and consolidate the many scattered "do not" warnings per topic to reduce token load.

Consider moving per-placement credential details and preset-specific edge cases (Windows, Freestyle restrictions) into a reference table to shorten the main body.

DimensionReasoningScore

Conciseness

No space is spent on concepts Claude already knows, but the ~400-line body is dense with long caveat-laden sentences; sections like "Saved web evidence checkpoints" and the app-web signed-URL/proxy internals could be significantly tightened or trimmed.

3 / 5

Actionability

Fully executable, copy-paste-ready commands with exact flags (e.g. `pnpm world up preview-desktop --place daytona --stage pr-1234 --detach -- --release 0.18.44 --distribution enterprise --scenario blank`), concrete credential-loading patterns, and a 3-step quick path covering the common intents.

5 / 5

Workflow Clarity

The lifecycle (discover → plan → up → verify → update → down) is clearly sequenced with explicit validation: plan preflight "exits 1 with the fix", up "checks the requirements again before any side effect", readiness verification before reporting, hint-line error recovery, and ownership verification before manual cleanup.

5 / 5

Progressive Disclosure

Sections are well organized and the one referenced script (scripts/update-preview.py) is a real bundle file, but ~400 lines are inlined with substantial material (evidence checkpoints, app-web security details) that clearly belongs in separate reference files, which do not exist.

3 / 5

Total

16

/

20

Passed

Description

70%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, distinctive description with concrete actions and named presets, weakened by a missing explicit use-when trigger clause and jargon-heavy phrasing that crowds out natural user keywords.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to preview, test, or demo a PR or branch change in the OpenWork app."

Include natural phrasings users would actually say ("test my PR", "spin up a preview", "try out my change") alongside the preset names.

Mention the evidence-checkpoint and published-release preview capabilities so the description's coverage matches the skill's scope.

DimensionReasoningScore

Specificity

"Boot, reopen, update, or reset" lists four concrete actions, plus four named presets (preview-desktop, preview-den, preview-full, preview-app-web) and three placements. Not 5 because the body reveals capabilities the description omits (evidence checkpoints, published release/Windows previews), leaving minor gaps in coverage.

4 / 5

Completeness

The "what" is clear (boot/reopen/update/reset OpenWork PR previews and choose among presets), but there is no explicit "Use when..." clause; "for hands-on testing" only weakly implies when, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural terms like "PR previews", "boot", "reset", and "hands-on testing" are present, but the description leans on jargon ("script worlds", "Daytona URL", "Freestyle") and misses common user phrasings like "test my PR" or "try out my change".

4 / 5

Distinctiveness Conflict Risk

"OpenWork PR previews" with named presets and specific platforms is a clear niche with distinct triggers; minimal risk of firing for a different skill.

5 / 5

Total

16

/

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

different-ai/openwork

Path

.opencode/skills/preview-my-work/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.