fraimz

DEPRECATED legacy flow compatibility. Load only when a user explicitly asks to run an EXISTING evals/flows/*.flow file. New coverage uses write-a-spec and run-tests.

Quality

80%

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

86%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 a tight, well-structured guide with concrete commands, an explicit existence check, and an honest-reporting feedback rule. The only soft spot is the underspecified 'launch the app' step, which slightly caps actionability and workflow clarity at 4.

Suggestions

Specify how to launch the app (e.g., the exact `pnpm` script or command) instead of the vague 'launch the app if that existing flow requires it'.

Show the expected `--list` output shape so the existence check is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude knows what flows/evals are, and every line (boundary, run command, honest-reporting rule) earns its place with no padding, matching the 'lean and efficient' anchor.	5 / 5
Actionability	It gives concrete executable commands (`pnpm evals:legacy --list`, `pnpm evals:legacy:demo --flow ... --cdp-url ...`), but 'launch the app if that existing flow requires it' is an unspecified step, leaving a minor gap that keeps it just below fully copy-paste ready.	4 / 5
Workflow Clarity	A clear sequence (confirm ID exists -> launch app if needed -> run -> report) with an explicit validation checkpoint (`--list`) and an error path (stop and report if broken), but the conditional 'launch the app' step is underspecified, a minor checkpoint gap.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, and well-organized into clear sections with a single one-level pointer to `evals/README.md`; no bundle files exist to require deeper structure, so the simple-skill exception applies.	5 / 5
	Total	18 / 20 Passed

Description

75%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.

The description is short, third-person, and clearly scopes a deprecated niche with an explicit trigger clause, giving strong completeness and distinctiveness. Specificity and trigger-term quality are mid-tier because the actions and keywords are somewhat technical and limited in number.

Suggestions

Add 1-2 more concrete actions (e.g., 'list, run, and report results for existing flows') to lift specificity toward 4-5.

Include a natural-language trigger synonym a user might actually say (e.g., 'Use when the user asks to run an old demo or eval flow') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('legacy flow compatibility') and a concrete action ('run an EXISTING evals/flows/*.flow file'), but does not enumerate several specific actions, fitting the 'domain + 1-2 concrete actions' anchor rather than the multi-action anchors at 4-5.	3 / 5
Completeness	It states what it does (legacy flow compatibility / run existing flow files) and gives an explicit, concrete trigger clause ('Load only when a user explicitly asks to run an EXISTING evals/flows/*.flow file'), satisfying both what and when with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Relevant terms ('run', 'flow', 'evals/flows/*.flow file') are present, but the phrasing is technical and lacks common natural synonyms a user would casually say, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	A very narrow niche (frozen legacy flows only) with an explicit redirect of new work to write-a-spec/run-tests yields a distinct trigger and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 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: 7b76a2b

Reviewed: 3 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.