llm-friendly-context

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

Quality

79%

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 ./dev-skills/skills/llm-friendly-context/SKILL.md

Quality

Content

75%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 well-organized, self-contained instruction skill with concrete rewrite patterns and observable checklists. The main improvements are minor: deduplicate the shared prohibition/unresolved items across the two checklists and consider illustrating one full before/after transformation.

Suggestions

Deduplicate the prohibition clause and unresolved-item guidance that recur across the Handoff Checklist and Generated Artifact Checklist to tighten conciseness.

Add one fully worked before/after example (e.g., a vague handoff rewritten per the Rewrite Patterns table) to lift actionability from pattern-form to copy-paste-ready.

Consider extracting the two checklists into a single consolidated verification section or a one-level-deep reference to give the SKILL.md body a leaner overview shape.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining basics, but the prohibition clause and some unresolved-handling items recur across the two checklists, leaving minor redundancy that keeps it just below a 5.	4 / 5
Actionability	The Rewrite Patterns table gives concrete ambiguous-to-specific transformations and the checklists list observable items, but guidance is in pattern form rather than full worked before/after examples, fitting anchor 4 for an instruction-only skill.	4 / 5
Workflow Clarity	Rules followed by rewrite patterns and then verification checklists form a clear sequence with checkpoint-style validation; it lacks an explicit error-recovery feedback loop, so it lands at 4 rather than 5.	4 / 5
Progressive Disclosure	Content is well-sectioned with no nested references and no bundle files to navigate, but at ~80 lines as a single self-contained file it exceeds the simple-skill threshold and is not structured as an overview pointing to references, so it is below 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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 description that cleanly answers both what and when with concrete trigger phrases and a well-scoped niche. Its only weakness is that the capability is expressed through one verb applied to a list rather than multiple distinct actions, slightly limiting specificity.

Dimension	Reasoning	Score
Specificity	"Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions" enumerates several concrete objects, but relies on a single verb rather than multiple distinct actions, so it sits below the comprehensive-anchor 5 and above the 1-2-action anchor 3.	4 / 5
Completeness	It explicitly states what (clarifies inputs, outputs, success criteria, decisions, unresolved conditions) and when (concrete "Use when..." trigger phrases), matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	"Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions" offers good natural keyword coverage, though it lacks the synonym/extension variety that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	The LLM-facing-artifact framing and "downstream consumers can execute without guessing" carve a distinct niche, with only minor overlap risk against generic review/report skills, fitting anchor 4 rather than the minimal-conflict 5.	4 / 5
	Total	17 / 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: shinpr/claude-code-workflows
Path: dev-skills/skills/llm-friendly-context/SKILL.md
Commit: 9b7f687

Reviewed: 2 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.