industry-friction-radar

Proactive Bleeding-Edge research loop using a strict 3-step abstraction protocol to extract engine-category friction points without importing framework-category bias or stealing code. Triggers: Use this skill when executing periodic "horizon scans" for the Dream Pipeline, researching external solutions to deeply complex engine-level friction points, or evaluating JS ecosystem trends.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/industry-friction-radar/SKILL.md

Quality

Content

82%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 tightly written router that cleanly delegates the detailed 3-step workflow to a real one-level-deep reference file, achieving strong conciseness and sound progressive disclosure, though it adds no inline overview and surfaces no validation steps of its own.

Suggestions

Add a 2–3 line overview inline (the 3-step arc: ingest trend → extract friction as JSON → propose native ideation) so the skill is useful without immediately opening the reference.

State the single most important guardrail inline (e.g., 'Never analyze or replicate external implementation code; abstract the friction only') so the key constraint is visible at the top level.

Surface the output contract briefly in the body (produces GitHub Discussions, not PRs) so Claude knows the deliverable shape before loading the full workflow.

Dimension	Reasoning	Score
Conciseness	The two-sentence body is extremely lean, assumes Claude's competence, and delegates all detail to the reference file with no padding, matching anchor 5 ('Lean and efficient; every token earns its place').	5 / 5
Actionability	It gives one concrete executable instruction ('use the `view_file` tool to read ...industry-friction-radar-workflow.md before proceeding') with a specific tool and path, but the actual execution guidance (the 3-step protocol) lives entirely in the referenced file, leaving a minor gap versus anchor 5's copy-paste-ready coverage.	4 / 5
Workflow Clarity	The body gives a clear, unambiguous first step (read the workflow file before proceeding) and the referenced file carries the sequenced 3-step protocol with explicit checkpoints, but the body itself surfaces no validation checkpoints, so it sits at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	It points to a single, verified, one-level-deep reference file with a clear signal, which is good structure, but the body provides no overview/quick-start content inline — it is a pure redirect — leaving a minor gap versus anchor 5's 'clear overview with well-signaled one-level-deep references'.	4 / 5
	Total	17 / 20 Passed

Description

62%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 explicitly covers both what the skill does and when to use it, with a clear distinct niche, but it is weighed down by domain-specific jargon ('Dream Pipeline', 'engine-category friction points') that weakens both specificity and the naturalness of its trigger terms.

Suggestions

Reword trigger terms in plain language a user would actually say (e.g., 'researching emerging JS/ECMAScript features and worker paradigms') and keep 'Dream Pipeline' as a secondary clause rather than a primary trigger.

Sharpen the 'what' with one or two more concrete, jargon-free actions (e.g., 'search the web for emerging engine-level techniques, abstract the underlying problem into a structured JSON friction point, then propose a native Neo.mjs solution').

Drop redundant constraint phrasing ('without importing framework-category bias or stealing code') from the description or compress it, since it pads tokens without adding trigger value.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('extract engine-category friction points' via 'a strict 3-step abstraction protocol'), but the phrasing leans on jargon ('Bleeding-Edge research loop', 'engine-category') and lists constraints ('without importing framework-category bias or stealing code') more than distinct executable actions, so it falls below the 'several specific actions' of anchor 4.	3 / 5
Completeness	It answers both 'what' (a 3-step abstraction research loop that extracts friction points) and 'when' via an explicit 'Triggers: Use this skill when...' clause with concrete triggers, but the 'what' is jargon-heavy and the 'when' could be more concrete, landing at anchor 4 rather than the crisp dual-answer of anchor 5.	4 / 5
Trigger Term Quality	The 'Triggers' clause offers some relevant phrases ('horizon scans', 'JS ecosystem trends'), but key terms ('Dream Pipeline', 'engine-level friction points') are internal jargon rather than natural user language, and common synonyms/variations are missing, matching anchor 3 rather than the fuller coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The niche is highly specific (engine-category friction extraction for the Dream Pipeline) and unlikely to trigger the wrong skill, but generic trigger phrases like 'researching external solutions' and 'evaluating JS ecosystem trends' create minor overlap with general research skills, fitting anchor 4.	4 / 5
	Total	14 / 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: neomjs/neo
Path: .agents/skills/industry-friction-radar/SKILL.md
Commit: 210c03c

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.