New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Skill Perfection

by OmidZamani in OmidZamani/dspy-skills

A skill your agent uses when you need to QA audit and fix a plugin skill file.

MITAuto-check passed

Install Skill Perfection

skills CLI
$ npx skills add OmidZamani/dspy-skills --skill skill-perfection -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OmidZamani/dspy-skills skill-perfection --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OmidZamani/dspy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills-skill-perfection .claude/skills/skill-perfection && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-perfection
GitHub stars
123
Token cost
~1.6k tokens
SKILL.md length
655 words
Files
2 (incl. scripts)
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when you need to QA audit and fix a plugin skill file.

  • Works in 4 steps: Preflight (Optional, Advisory) → Audit + Fix (Single Pass) - THE CORE → Verification (Spot-Check) → …
  • You need to QA audit and fix a plugin skill file
  • SKILL.md covers Core Principle, Process Overview, Phase 1: Preflight (Optional,… and Phase 2: Audit + Fix (Single…, plus 5 more sections
  • Runs Python scripts from its folder; calls uv

What it does

Skill Perfection is an agent skill from OmidZamani/dspy-skills. Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/preflight.py`).

It works with Python. The repository describes itself as: Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically. The licence is MIT.

When your agent uses it

  • You need to QA audit and fix a plugin skill file

Example prompts

  • “/skill-perfection”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Preflight (Optional, Advisory)
  2. Audit + Fix (Single Pass) - THE CORE
  3. Verification (Spot-Check)
  4. Generate Report

What it can do on your machine

Read from SKILL.md and the folder at commit f5db3b7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Perfection loads about 1.6k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 655 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OmidZamani/dspy-skills at commit f5db3b7, republished under its MIT licence (© OmidZamani). 655 words, ~1,630 tokens.

Download SKILL.mdSave it as .claude/skills/skill-perfection/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
skill-perfection
description
Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.
version
1.1.0

Skill Perfection

A systematic process for auditing and fixing plugin skills in a single pass.

Core Principle

Audit + Fix in One Pass: When you find an issue, fix it immediately, then continue. This eliminates redundant research and multiple iterations.

Process Overview

[Optional Preflight] → Audit+Fix (single pass) → Verify (spot-check) → Report

Phase 1: Preflight (Optional, Advisory)

A Python-based preflight script is bundled for Python-heavy skills only.

When to Use Preflight
Skill ContentUse Preflight?
Mostly Python code blocks✅ Yes
Mixed Python + other languages⚠️ Optional (Python blocks only)
Non-Python (JS, Rust, Go, etc.)❌ Skip, go to Phase 2
Skill about the preflight script itself❌ Skip (conflict of interest)
Running Preflight
bash
uv run python ${SKILL_DIR}/scripts/preflight.py <path-to-skill.md> --no-urls
Interpreting Results
ResultAction
✅ PASSEDGood signal. Proceed to Phase 2, trust syntax is valid.
❌ FAILED with clear errors (syntax error at line X)Fix those specific issues, then proceed to Phase 2.
❌ FAILED with confusing/many errorsIgnore preflight entirely. Proceed to Phase 2, let LLM verify.
Script crashes or hangsIgnore preflight entirely. Proceed to Phase 2.
Key Rule: Preflight is Advisory

The preflight script is a helper, not a gatekeeper. If it produces confusing output, skip it. The LLM-based Phase 2 is always authoritative.

Signs to ignore preflight:

  • More than 10 errors on a skill that "looks fine"
  • Errors that don't make sense (line numbers don't match)
  • Python tracebacks from the script itself
  • Timeouts or hanging

When in doubt, skip preflight and let the LLM verify everything.

Phase 2: Audit + Fix (Single Pass) - THE CORE

This is the main phase. Work through the skill file section by section.

2.1 Identify the Technology

From the skill's content, identify:

  • Primary technology/framework (e.g., LangGraph, React, Axum, Go-kit)
  • Version constraints if mentioned
  • Official documentation domain
2.2 Research Strategy

Batch similar lookups to minimize web calls:

Example: For a skill with 10 import statements from the same package,
do ONE search that covers them all, not 10 separate searches.

Documentation priority:

  1. Official docs (use site: filter)
  2. Official GitHub repo (examples, tests, README)
  3. Package registry (PyPI, npm, crates.io, pkg.go.dev)
  4. Official blog/changelog
2.3 For Each Verifiable Item
Item TypeWhat to Verify
Import/require statementPackage exists, path is current, not deprecated
API callSignature matches official docs, parameters correct
Code exampleWould execute, complete imports, correct syntax
URL/linkAccessible (WebFetch), points to claimed content
Version claimCurrent/accurate
Best practice claimAligned with official recommendations
2.4 Fix-As-You-Go

When you find an issue:

  1. STOP auditing that section
  2. FIX the issue immediately (Edit tool)
  3. LOG the change in memory: {location, old, new, reason, source_url}
  4. CONTINUE auditing

All severities get fixed in one pass - don't defer anything.

Show full SKILL.md (253 more words)Show less
2.5 Syntax Verification (LLM-based)

For code blocks, verify syntax by reading carefully:

Python: Check for matching parentheses, correct indentation, valid syntax JavaScript/TypeScript: Check for matching braces, valid syntax, correct imports
Rust: Check for matching braces, semicolons, valid syntax Go: Check for matching braces, correct package structure Any language: Apply your knowledge of that language's syntax rules

If unsure about syntax validity, note it but don't block on it - focus on semantic correctness against official docs.

Phase 3: Verification (Spot-Check)

After completing Phase 2:

  1. Re-read the modified skill file
  2. Spot-check 3-5 items you fixed (not everything)
  3. Verify URLs you added/modified (WebFetch)

If spot-checks pass → Proceed to Phase 4 If spot-checks fail → Fix those specific items, re-check only those

Do NOT do a full re-audit. You already verified everything in Phase 2.

Phase 4: Generate Report

Create a concise report (<100 lines):

markdown
# Skill Perfection Report

**Skill**: {skill-name}
**Date**: {date}  
**Version**: {old} → {new}
**Status**: ✅ PERFECTED | ⚠️ NEEDS REVIEW

## Summary
- Items verified: {N}
- Issues found and fixed: {N}

## Changes Made

### High Priority
| Location | Change | Reason | Source |
|----------|--------|--------|--------|
| line 45 | `old` → `new` | why | [docs](url) |

### Medium/Low Priority
| Location | Change | Reason | Source |
|----------|--------|--------|--------|
| line 12 | `old` → `new` | why | [docs](url) |

## Verification
- [x] All imports verified against official docs
- [x] All API signatures match current documentation
- [x] Code examples are complete and correct
- [x] All URLs accessible

## Sources
1. {url}
2. {url}

Save to: {skill-directory}/PERFECTION_REPORT.md

Efficiency Guidelines

MetricTarget
Web searches<20 per skill (batch similar items)
Iterations1 audit+fix pass + 1 spot-check
Report length<100 lines

Anti-Patterns

❌ Run preflight on non-Python skills ✅ Skip preflight, let LLM verify

❌ Trust confusing preflight output
✅ Ignore preflight when output doesn't make sense

❌ Separate audit pass, then separate update pass ✅ Fix issues as you find them

❌ Full re-audit after fixes ✅ Spot-check only changed items

❌ Research same API multiple times
✅ Batch similar lookups, cache results

Bundled Scripts

scripts/preflight.py

Purpose: Quick syntax check for Python-heavy skills Limitation: Only useful for Python; advisory only

bash
# Use for Python skills
uv run python ${SKILL_DIR}/scripts/preflight.py skill.md --no-urls

# Skip for non-Python skills or if output is confusing

If preflight causes problems, ignore it entirely. The LLM-based audit is always the authoritative verification.

© OmidZamani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in .claude/skills-skill-perfection of OmidZamani/dspy-skills.

  • SKILL.md
  • scripts/preflight.py

Open the folder on GitHubat commit f5db3b7

Compare with similar skills

Skill Perfection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Perfection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Perfection this skillOmidZamani/dspy-skills123—~1.6kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k47 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use29k6 repos~3kAutomated safety check: PassMIT
PPT Masterhugohe3/ppt-master59k1 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 47 repos~2k tokens
    Documents & OfficeAuto-check passed

  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes

  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    29k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed

  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    59k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

  • Scikit Learn

    zLanqing/codex-claude-academic-skills

    Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.

    4.7k GitHub starsUsed in 16 repos~3.9k tokens
    Data & AnalyticsAuto-check passed

More from OmidZamani/dspy-skills

All 17 skills in this repo

  • Dspy Haystack Integration

    OmidZamani/dspy-skills

    A skill your agent uses for integrating DSPy with Haystack, optimizing Haystack prompts, improving retrieval pipelines, and extracting DSPy prompts.

    123 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Dspy Adapters Multimodal

    OmidZamani/dspy-skills

    A skill your agent uses for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.

    123 GitHub stars~864 tokensUpdated 3 mo ago
    Auto-check passed

  • Dspy Advanced Module Composition

    OmidZamani/dspy-skills

    A skill your agent uses for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.

    123 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed

  • Dspy Better Together

    OmidZamani/dspy-skills

    A skill your agent uses for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p - w - p.

    123 GitHub stars~756 tokensUpdated 3 mo ago
    Auto-check passed

  • Dspy Bootstrap Fewshot

    OmidZamani/dspy-skills

    A skill your agent uses for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.

    123 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Dspy Custom Module Design

    OmidZamani/dspy-skills

    A skill your agent uses for creating custom DSPy modules, extending dspy.Module, reusable components, stateful modules, serialization, and module testing.

    123 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Skill Perfection

What does Skill Perfection do?

A skill your agent uses when you need to QA audit and fix a plugin skill file. Skill Perfection is an agent skill from OmidZamani/dspy-skills. Use this skill when you need to QA audit and fix a plugin skill file.

When should I use Skill Perfection?

Skill Perfection fits situations like: you need to QA audit and fix a plugin skill file.

How do I install Skill Perfection in Claude Code?

Run `npx skills add OmidZamani/dspy-skills --skill skill-perfection -a claude-code`. Or copy the skill folder (.claude/skills-skill-perfection in OmidZamani/dspy-skills) into .claude/skills/skill-perfection in your project. Claude Code loads it when a task matches its description.

How do I install Skill Perfection in Codex?

Run `npx skills add OmidZamani/dspy-skills --skill skill-perfection -a codex`. Or copy the skill folder (.claude/skills-skill-perfection in OmidZamani/dspy-skills) into .agents/skills/skill-perfection in your project. Codex loads it when a task matches its description.

Can I use Skill Perfection in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OmidZamani/dspy-skills --skill skill-perfection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-perfection, .gemini/skills/skill-perfection, .github/skills/skill-perfection and .opencode/skills/skill-perfection in your project.

What does Skill Perfection need to run?

Going by SKILL.md and its folder, Skill Perfection needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Skill Perfection access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Skill Perfection safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Skill Perfection use?

Skill Perfection is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Perfection use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Perfection?

Skills that share tags, products or a category with Skill Perfection: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Perfection?

OmidZamani (a GitHub user) maintains it in OmidZamani/dspy-skills, which has 123 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on June 23, 2026.

Source: OmidZamani/dspy-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.