improve-skills

improve-skills is a command for Claude Code from athola/claude-night-market. It costs 17 tokens per session (1,672 once invoked), scanned A, original, MIT.

A command for finding and applying improvements to skills using execution logs, user evaluations, and a file of recorded lessons. It can preview proposed changes or implement them.

In plain words
What is it for?
Use it to analyze all skills or one skill, rank improvement opportunities, generate proposals, or apply them after a dry run.
Why use it?
It turns recurring failures, slow runs, and user friction into specific updates to the skills.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the abstract plugin — 16 skills, 17 commands, 5 agents, 4 hooks shipped together

Good fit Use it to analyze all skills or one skill, rank improvement opportunities, generate proposals, or apply them after a dry run.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/athola/claude-night-market/improve-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Or install abstract, the plugin that ships this one along with the rest of its 16 skills, 17 commands, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for improve-skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/athola/claude-night-market/improve-skills/github.svg)](https://agentmods.dev/commands/athola/claude-night-market/improve-skills)
Your own site
<a href="https://agentmods.dev/commands/athola/claude-night-market/improve-skills"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/improve-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for improve-skills

Your own site · 80×15
<a href="https://agentmods.dev/commands/athola/claude-night-market/improve-skills"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/improve-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.01672
Opus 5 $0.00009 $0.00836
Sonnet 5 $0.00003 $0.00334
Haiku 4.5 $0.00002 $0.00167

Measured 12d ago against content hash 7d604bb0a441, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

improve-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/abstract/commands/improve-skills.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Improve Skills from Observability Data

Automatically identify and implement skill improvements based on execution logs and user evaluations.

Usage

/abstract:improve-skills                          # Analyze all skills
/abstract:improve-skills --skill proof-of-work    # Improve specific skill
/abstract:improve-skills --top 5                  # Top 5 improvement opportunities
/abstract:improve-skills --dry-run                # Preview without implementing

Purpose

Part of Issue #69 Phase 5, this command closes the self-improvement loop by:

  1. Reading LEARNINGS.md for improvement opportunities
  2. Prioritizing by severity (frequency × impact × ease)
  3. Generating skill update proposals
  4. Optionally implementing changes with validation

What It Does

  1. Loads LEARNINGS.md from ~/.claude/skills/LEARNINGS.md
  2. Identifies opportunities:
    • High-impact issues (failure rates, excessive failures)
    • Slow execution times
    • Low user ratings with specific friction points
  3. Prioritizes improvements:
    • Frequency: How often is this skill used?
    • Impact: How much does the issue hurt?
    • Ease: How simple is the fix?
  4. Generates proposals:
    • What to change (specific file/section)
    • Why (data from evaluations)
    • How (implementation approach)
  5. Optionally implements:
    • Updates skill files
    • Runs validation tests
    • Creates commit

Prioritization Formula

Priority Score = (Frequency × Impact) / Ease

Where:
- Frequency: Execution count in analysis period
- Impact:
  - High failure rate: 10
  - Low rating: rating_diff × 2 (e.g., 2.5 vs 5.0 = 5.0 impact)
  - Slow execution: seconds_over_threshold / 10
- Ease:
  - Simple text update: 1
  - Add examples: 2
  - Restructure workflow: 5
  - Refactor logic: 10

Threshold: Priority > 5.0 = implement now, 2.0-5.0 = discuss, <2.0 = defer

Examples

Analyze All Skills

/abstract:improve-skills

# Output:
# Reading LEARNINGS.md...
# Found 12 improvement opportunities
#
# Top 5 by priority:
# 1. imbue:proof-of-work (Priority: 8.5)
#    Issue: 42% failure rate (11/26 executions)
#    Fix: Add error handling for missing PROOF.md
#    Ease: Simple (add try/catch)
#
# 2. abstract:skill-auditor (Priority: 6.2)
#    Issue: 2.8/5.0 rating - "too verbose"
#    Fix: Add --quiet flag
#    Ease: Medium (new parameter)
# ...
#
# Implement top 5? (y/n):

Read the full file on GitHub · 248 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 248 lines · 17 tokens per session scan A 7d604bb0a441

Subscribe to this mod's changes

improve-skills is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,672 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.