rules-distill

Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files. Use when the same principle keeps recurring across skills and belongs in a rule file instead.

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 ./skills/rules-distill/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.

The body is highly actionable and clearly sequenced with real bundle scripts and a complete subagent prompt template, scoring well on actionability and workflow clarity. Its main weakness is conciseness: the verdict taxonomy and guiding principle are repeated across sections, and a large end-to-end example duplicates already-specified formats.

Suggestions

Remove the standalone 'Verdict Reference' table (or the verdict list inside the subagent prompt) — the taxonomy appears three times and one copy is enough.

Move the full 'End-to-end run' example into a references/ file (e.g. EXAMPLE.md) and keep only a brief pointer in SKILL.md, since it duplicates the Phase 3 summary-table format.

State the 'deterministic collection, LLM judgment' principle once (e.g. in Design Principles) and reference it rather than re-explaining it in the intro and How It Works sections.

Dimension	Reasoning	Score
Conciseness	Most content is substantive procedural guidance Claude would not know, but the verdict taxonomy is repeated (subagent prompt, Verdict Reference table, and Example), the "deterministic collection, LLM judgment" principle is restated three times, and the full end-to-end example duplicates the already-defined summary table format, so it could be tightened beyond the 4-anchor's 'minor' threshold.	3 / 5
Actionability	Executable scan commands with real script paths, a copy-paste-ready subagent prompt with exact JSON output schema, a concrete verdict taxonomy, and a fully specified results.json schema cover the common cases, matching the fully-executable 5-anchor.	5 / 5
Workflow Clarity	The three phases are clearly sequenced with explicit checkpoints (cross-batch merge re-check of the 2+ skills rule, the 3-layer filter checklist, and a mandatory user-approval gate before applying), but the validate→fix→retry feedback loop is lighter than the 5-anchor's automated error-recovery loop, so it sits at 4.	4 / 5
Progressive Disclosure	Structure is good with clear section headers and one-level-deep references to real bundle scripts (scan-skills.sh, scan-rules.sh), but the body is fairly monolithic — the subagent prompt, verdict reference table, and full end-to-end example are all inlined with no references/ directory to split them into, leaving minor organization gaps versus the 5-anchor.	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.

The description is strong: third-person voice, explicit concrete actions, and a clear 'Use when...' trigger that answers both what and when. It is held below top marks only by slightly less comprehensive action/keyword coverage and minor overlap with adjacent rules-management skills.

Dimension	Reasoning	Score
Specificity	"extract cross-cutting principles", "distill them into rules", "append, revise, or create new rule files" lists several concrete actions, but the actions cluster around one workflow rather than spanning distinct capabilities, so it stops short of the comprehensive 5-anchor.	4 / 5
Completeness	It explicitly answers both what ("Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files") and when ("Use when the same principle keeps recurring across skills and belongs in a rule file instead") with a concrete trigger phrase, matching the 5-anchor.	5 / 5
Trigger Term Quality	Natural terms like "principles", "rules", "rule file", and "skills" appear with a concrete trigger ("the same principle keeps recurring across skills"), giving good keyword coverage, but synonyms a user might say (e.g. "consolidate", "organize rules") are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	The rules-distillation niche is mostly distinct with specific triggers, but the body itself references overlapping concerns ("skill-stocktake", general rules maintenance), indicating minor overlap risk with closely related skills rather than the minimal-conflict 5-anchor.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/rules-distill/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.