fraimz

create a fraimz, make fraimz, prove it works, frame proof, PR proof, validate experience, e2e evidence, fraimz.html. The full fraimz loop — frame the claim, drive the real app via CDP, validate/repair, output fraimz.html. Use whenever a task ends with "please create a fraimz" or any change needs end-to-end proof.

Quality

85%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and clearly sequenced with validation feedback loops, and it uses a clean source-of-truth section for deeper reference. Its only real weakness is conciseness — a few rhetorical lines and overall length could be trimmed without losing clarity.

Suggestions

Trim rhetorical/mission lines (e.g. "A fraimz is never a bare test log", "If you cannot say which of the two your fraimz is, you have not framed the experience yet") to tighten the body.

Consider moving the full ctx.* helpers list and the Pitfalls block into a bundled reference file, keeping SKILL.md as a tighter overview that links to it.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and assumes Claude's competence (no explaining of CDP/PRs), but rhetorical lines like "A fraimz is never a bare test log" and "If you cannot say which of the two your fraimz is, you have not framed the experience yet" plus the overall length could be tightened.	2 / 3
Actionability	It gives copy-paste-ready commands ("pnpm fraimz --flow <id> --cdp-url <electron-cdp-url>", "OPENWORK_ELECTRON_REMOTE_DEBUG_PORT=9826 pnpm dev") and concrete API calls like ctx.prove("claim", { voiceover, action, assert, screenshot }).	3 / 3
Workflow Clarity	"The loop" is a clear 6-step sequence with an explicit validate/repair/repeat feedback loop (step 5) and a verdict gate that only reports Passed when every claim is backed by an observable assertion.	3 / 3
Progressive Disclosure	A "Source of truth" section gives well-signaled one-level-deep pointers (evals/README.md for the full ctx.* reference, evals/flows/ for flows) while the body stays a concise operational overview; no nested reference chains.	3 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-crafted: it states concrete actions, an explicit Use-when trigger, and a distinct niche. Its main weakness is a keyword-stuffed opening that trades natural phrasing for buzzword variations.

Suggestions

Replace the stuffed opening ("create a fraimz, make fraimz, frame proof, PR proof, e2e evidence") with one or two natural trigger phrases users would actually say.

Lead with the operational sentence ("The full fraimz loop — frame the claim, drive the real app via CDP, validate/repair, output fraimz.html") so the concrete actions come before the keyword list.

Dimension	Reasoning	Score
Specificity	It names multiple concrete actions — "frame the claim, drive the real app via CDP, validate/repair, output fraimz.html" — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It answers both what ("The full fraimz loop — frame the claim, drive the real app via CDP, validate/repair, output fraimz.html") and when ("Use whenever a task ends with 'please create a fraimz' or any change needs end-to-end proof") with an explicit trigger clause.	3 / 3
Trigger Term Quality	It includes some natural phrases ("prove it works", "end-to-end proof", "please create a fraimz") but opens with keyword-stuffed, awkward constructions ("create a fraimz, make fraimz, frame proof, PR proof, e2e evidence") that users would not naturally say.	2 / 3
Distinctiveness Conflict Risk	The coined "fraimz" concept and its end-to-end proof niche are clearly distinct and tied to specific triggers, making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: different-ai/openwork
Path: .opencode/skills/fraimz/SKILL.md
Commit: 1345d51

Reviewed: about 14 hours 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.