CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An extremely lean, well-organized principle skill that fully respects the token budget. Its main gap is actionability: the fallback guidance is abstract and would benefit from one concrete before/after example.

Suggestions

Add a brief before/after example showing a repeated instruction converted into a lint rule or runtime check, which the body itself recommends ('add an example of the failure mode') but does not provide.

Restate the primary rule (encode the lesson structurally) at the top of the body so the fallback paragraph reads as a branch of a complete decision flow rather than a standalone opening.

Specify what 'make the instruction more prominent' means concretely, e.g., moving it to a section header, a checklist item, or bolded text.

DimensionReasoningScore

Conciseness

The body is roughly 40 words with zero padding and no explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

The directives are concrete in form ("make the instruction more prominent", "add an example of the failure mode", "only use the structural fix") but lack a worked example, such as a before/after of a repeated instruction turned into a lint, and 'more prominent' is left unspecified.

3 / 5

Workflow Clarity

The decision branches (encode structurally; fall back to prominence plus a failure example; structural fix only) are each stated clearly, but the body opens mid-branch since the primary rule lives only in the description, and the branches are never assembled into one coherent flow.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and the body is well organized with a heading and a clearly signaled corollary, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

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.

A concise, well-scoped description with an explicit trigger clause and a clear statement of what the skill does. Its main weaknesses are the second-person phrasing in the trigger and limited coverage of synonymous trigger terms.

Suggestions

Rewrite the trigger in third person, e.g., "Apply when the same instruction is being written a second time or a correction keeps recurring," to satisfy the voice guideline.

Broaden trigger coverage with natural variations such as "repeated instruction", "duplicate rule", or "keeps making the same correction" so more phrasings match.

DimensionReasoningScore

Specificity

The description lists several concrete encoding mechanisms ("Encode the rule as a lint, metadata flag, runtime check, or script"), which would anchor at 4, but the second-person voice ("when you catch yourself writing") triggers the rubric's -1 voice penalty, landing at 3.

3 / 5

Completeness

It explicitly answers both questions: the 'what' is "Encode the rule as a lint, metadata flag, runtime check, or script instead of more text" and the 'when' is the explicit "Apply when..." clause with two concrete trigger conditions.

5 / 5

Trigger Term Quality

"writing the same instruction a second time" and "recurring correction" are natural trigger phrases, but common variations and synonyms (e.g., "repeated", "duplicate instruction", "keep saying the same thing") are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The trigger (noticing oneself repeating an instruction or a recurring correction) is a highly specific meta-condition that no common skill domain shares, giving it a clear niche with minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

geut/factory-skills

Path

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

Reviewed

Table of Contents

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.