principle-encode-lessons-in-structure

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/principle-encode-lessons-in-structure/SKILL.md

Quality

Content

78%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 principle skill that delivers concrete, actionable guidance without explaining concepts Claude already knows. The main improvement space is making the workflow's decision checkpoints more explicit rather than implied.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence with no padding of basics, though a few explanatory clauses (e.g., 'because agents copy whatever the surrounding code already does...') could be trimmed slightly.	4 / 5
Actionability	Provides a concrete numbered pattern, a prioritized mechanism ladder, explicit routing rules (one-off → brain note, recurring → skill/lint, systemic → principle), and named anti-patterns — actionable for an instruction-only skill.	4 / 5
Workflow Clarity	The Pattern section is a clear numbered sequence and the Feedback loop is well staged; this is not a destructive/batch operation so the validation cap does not apply, but checkpoints are implicit rather than explicit.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references and well-organized sections (Why, Pattern, Corollary, Feedback loop, Anti-patterns), satisfying the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

76%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 well-constructed description that clearly states both the trigger condition and the concrete actions to take. Its main weakness is trigger phrasing that reads as internal self-reflection rather than language a user would naturally say.

Suggestions

Add a user-facing trigger phrase or synonym (e.g., 'duplicate instruction', 'repeated correction') so the skill surfaces for natural user requests, not only self-reflection.

Consider mentioning the routing outcome ('delete the instruction') in the description to round out the action set.

Dimension	Reasoning	Score
Specificity	Names the domain (encoding recurring fixes) and lists several concrete mechanisms — 'lint, metadata flag, runtime check, or script' — but stops short of comprehensive coverage of all encoding options.	4 / 5
Completeness	Explicitly answers both 'what' ('Encode the rule as a lint, metadata flag, runtime check, or script') and 'when' ('Apply when you catch yourself writing the same instruction a second time') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Triggers like 'writing the same instruction a second time' and 'recurring correction' are relevant but reflective/internal rather than natural user utterances, and common synonyms (duplicate, repeated) are missing.	3 / 5
Distinctiveness Conflict Risk	Has a clear niche — encoding recurring corrections into structural mechanisms — with mostly distinct triggers, though the mechanism list (lint/script) overlaps slightly with general automation skills.	4 / 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: storybookjs/storybook
Path: .agents/skills/principle-encode-lessons-in-structure/SKILL.md
Commit: 1e8b436

Reviewed: 5 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.