product-self-knowledge

Answer questions about Feynman's own product behavior, runtime, settings, commands, skills, connectors, and package state. Use when a response would claim what Feynman can do or how it is wired.

Quality

86%

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.

A tight, well-structured instruction-only skill with a clear sequenced workflow and no padding. The main improvement area is actionability: adding a few concrete pointers (where source lives, which commands discover resources) and an explicit verify-then-correct feedback loop would lift the lower dimensions.

Suggestions

Add a concrete pointer to where Feynman source/package metadata/workbench state actually live (e.g., repo paths or commands) so step 1 is executable rather than directional.

Append an explicit feedback loop after step 3: if verification contradicts the original claim, restate the claim from the verified source rather than the prior assumption.

Optionally name the specific command(s) used for command/resource discovery in step 3 so 'Verify current command/resource discovery' becomes a copy-runnable action.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no concept over-explanation or padding; every line (intro, five workflow steps, closing citation rule) earns its place and assumes Claude's competence, matching the anchor 5 example.	5 / 5
Actionability	Provides concrete, specific directives (read source/package metadata/workbench state, distinguish local-only/packaged/pushed/deployed/live-runtime facts, verify command/resource discovery, name unsupported boundaries) appropriate for an instruction-only skill; not a 5 because it stops short of naming exact repo paths or commands, leaving minor execution gaps.	4 / 5
Workflow Clarity	A clear five-step sequence with an explicit verify checkpoint (step 3) and a boundary-naming check (step 4); not a 5 because there is no explicit feedback/error-recovery loop describing what to do when verification contradicts a claim.	4 / 5
Progressive Disclosure	Under 50 lines, self-contained with no need for external references, and well-organized with a header and numbered workflow; the simple-skill exception applies, so well-organized sections alone warrant a 5.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong, well-scoped description that clearly answers both what and when for a distinct niche (product self-knowledge). The only weakness is a single action verb paired with the comprehensive domain list and a behavioral rather than user-utterance trigger framing.

Dimension	Reasoning	Score
Specificity	Enumerates a concrete capability domain ('product behavior, runtime, settings, commands, skills, connectors, and package state') under a single action ('Answer questions about'), giving several specific areas with only minor coverage gaps; not a 5 because the action verb is singular rather than a list of distinct concrete actions.	4 / 5
Completeness	Explicitly states both what ('Answer questions about Feynman's own product behavior, runtime, settings, commands, skills, connectors, and package state') and when ('Use when a response would claim what Feynman can do or how it is wired') with concrete trigger phrases, matching the anchor 5 example structure.	5 / 5
Trigger Term Quality	Includes natural domain keywords (runtime, settings, commands, skills, connectors) and a behavioral trigger ('Use when a response would claim what Feynman can do or how it is wired'); not a 5 because the trigger is framed around Claude's claim-making rather than a fuller set of user-utterance synonyms.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to claims about a specific product (Feynman) itself, creating a clear niche with distinct triggers and minimal overlap risk with general-purpose skills.	5 / 5
	Total	18 / 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: companion-inc/feynman
Path: skills/product-self-knowledge/SKILL.md
Commit: 95c51d9

Reviewed: about 8 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.