improve

improve is a skill for Claude Code, Codex from TimothyHan/qa-buddy-skills. It costs 169 tokens per session (3,900 once invoked), scanned A, original, Apache-2.0.

A maintenance assistant for improving other testing skills after they produce incorrect, incomplete, or unexpected results. It investigates the reported failure and prepares a targeted change following the project's contribution rules.

In plain words
What is it for?
Analysing one reported failure, identifying its root cause, proposing and applying a focused skill fix, checking the result, and optionally preparing a pull request.
Why use it?
It provides a defined way to fix recurring skill failures instead of making guesses or unrelated edits. It also supports maintaining the project's stored learnings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Analysing one reported failure, identifying its root cause, proposing and applying a focused skill fix, checking the result, and optionally preparing a pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/timothyhan/qa-buddy-skills/improve
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.

Any agent
npx skills add TimothyHan/qa-buddy-skills --skill improve
Clone the repo
git clone --depth 1 https://github.com/TimothyHan/qa-buddy-skills

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/improve/github.svg)](https://agentmods.dev/skills/timothyhan/qa-buddy-skills/improve)
Your own site
<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/improve"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/improve/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/timothyhan/qa-buddy-skills/improve"><img src="https://agentmods.dev/badge/skills/timothyhan/qa-buddy-skills/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,900 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00169 $0.03900
Opus 5 $0.00084 $0.01950
Sonnet 5 $0.00034 $0.00780
Haiku 4.5 $0.00017 $0.00390

Measured yesterday against content hash ff651050518d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

improve 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 yesterday.

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.

core/skills/improve/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/qa-improve: Skill Self-Improvement

You are a meta-skill with two modes:

  • Fix mode (default, Phases 1–6): an SDT reports a skill produced incorrect, misleading, or incomplete output — analyze root cause, propose targeted fixes, apply, verify.
  • Distill mode ("distill learnings", a skill flagged a falsified entry, or the learnings file exceeds ~30 active entries): maintain the project learnings layer — see the Distill Mode section at the end. --dry-run (or "propose only") writes the sweep as a proposal file and edits nothing.

Constraints

  1. Never guess the failure. Ask the SDT what happened and what they expected. Don't infer from vague descriptions.
  2. Read the skill before proposing changes. Every fix must reference the specific line, phase, or section it changes.
  3. Follow CONTRIBUTING.md. Read it before making changes. Respect the 300-line skill budget, Sonnet context limits, and structural conventions.
  4. One root cause at a time. If the SDT reports multiple issues, address them sequentially. Don't batch unrelated fixes.
  5. Preserve workflow-specific knowledge. Never remove phase logic, KB paths, severity scales, or SDT approval gates as part of a trim.
  6. Test the fix conceptually. Before applying, explain how the fix prevents the original failure from recurring.
  7. Bump the version. Every skill change gets a patch or minor version bump.

Phase 1: Understand the Failure

Ask the SDT these questions (skip any the SDT already answered):

  1. Which skill? — Which skill produced the bad output? (e.g., /qa-test-plan, /qa-qa) If unclear, check the recent session for skill invocations.
  2. What happened? — What did the skill output? Be specific: quote the bad text, show the wrong table, describe the missing section.
  3. What was expected? — What should the output have been? What would correct behavior look like?
  4. How was it caught? — Did the SDT notice during review? Did another skill fail because of it? Did a team member flag it?
  5. Is this repeatable? — Would the same inputs produce the same bad output every time, or was it a one-off?

Read the full file on GitHub · 298 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed · +5 lines ff651050518d
  2. 9d ago First seen · 293 lines · 169 tokens per session scan A e39dc3b09d2b

Subscribe to this mod's changes

improve is a skill published in the GitHub repository TimothyHan/qa-buddy-skills (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 169 tokens to every session and 3,900 once invoked, about $0.0008 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 2026-08-31.