skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

1.74x

Quality

81%

Does it follow best practices?

Impact

94%

1.74x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

73%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 with excellent workflow sequencing and validation, but is dragged down by noticeable conversational padding and several broken file references that undermine navigation.

Suggestions

Trim conversational asides ('Cool? Cool.', the plumbers anecdote, 'billions a year in economic value', 'Good luck!') and consolidate the core loop to a single statement to improve token efficiency.

Fix broken references: the agents/*.md files and eval-viewer/generate_review.py do not exist in the bundle — either create them or point to the actual scripts/ paths (e.g., scripts/generate_report.py).

Verify that every referenced script path matches an actual file under scripts/ so navigation is reliable.

Dimension	Reasoning	Score
Conciseness	Several padded conversational asides ('Cool? Cool.', the plumbers/grandparents anecdote, 'billions a year in economic value', 'Sorry in advance but I'm gonna go all caps here') and triple-repetition of the core loop make it noticeably verbose despite substantive instructional content.	2 / 5
Actionability	Provides copy-paste-ready commands, exact JSON structures, precise field names (text/passed/evidence), and concrete placeholder-substitution steps covering the common eval/iteration cases.	5 / 5
Workflow Clarity	Clear Step 1–5 sequencing with explicit validation checkpoints, gating language ('This is the only opportunity to capture this data'), and feedback loops (grade → aggregate → review → improve → rerun).	5 / 5
Progressive Disclosure	Good section structure with one-level-deep, clearly signaled references to references/schemas.md and assets/eval_review.html, but several referenced paths do not exist (agents/grader.md, agents/comparator.md, agents/analyzer.md, eval-viewer/generate_review.py), preventing a 5.	4 / 5
	Total	16 / 20 Passed

Description

88%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 comprehensive and well-structured, explicitly covering both capabilities and concrete trigger contexts in third person. It is among the stronger examples, with only minor gaps in synonym coverage and slight overlap risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills, modify and improve existing skills', 'measure skill performance', 'run evals', 'benchmark skill performance with variance analysis', 'optimize a skill's description' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Create new skills, modify and improve existing skills, and measure skill performance') and 'when' via a concrete 'Use when users want to...' clause enumerating trigger contexts.	5 / 5
Trigger Term Quality	Good coverage of natural phrases ('create a skill from scratch', 'edit', 'optimize an existing skill', 'run evals', 'benchmark skill performance'), though a few common synonyms ('build/make a skill') and extension forms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a distinct skill-creation/optimization niche with clear triggers; minor overlap risk with generic 'improve' or 'optimize' prompts keeps it just below a 5.	4 / 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: ZHangZHengEric/Sage
Path: app/skills/skill-creator/SKILL.md
Commit: 84f9704

Reviewed: 3 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.