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.
npx skills add ratnesh-maurya/cursor-claude-personas --skill skill-improvergit clone --depth 1 https://github.com/ratnesh-maurya/cursor-claude-personasWrote 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.
[](https://agentmods.dev/skills/ratnesh-maurya/cursor-claude-personas/skill-improver)<a href="https://agentmods.dev/skills/ratnesh-maurya/cursor-claude-personas/skill-improver"><img src="https://agentmods.dev/badge/skills/ratnesh-maurya/cursor-claude-personas/skill-improver/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.
<a href="https://agentmods.dev/skills/ratnesh-maurya/cursor-claude-personas/skill-improver"><img src="https://agentmods.dev/badge/skills/ratnesh-maurya/cursor-claude-personas/skill-improver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01241 |
| Opus 5 | $0.00028 | $0.00620 |
| Sonnet 5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
skill-improver 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Improvement Methodology
Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.
Prerequisites
Requires the plugin-dev plugin which provides the skill-reviewer agent.
Verify it's enabled: run /plugins — plugin-dev should appear in the list. If missing, install from the Trail of Bits plugin repository.
Core Loop
- Review - Call skill-reviewer on the target skill
- Categorize - Parse issues by severity
- Fix - Address critical and major issues
- Evaluate - Check minor issues for validity before fixing
- Repeat - Continue until quality bar is met
When to Use
- Improving a skill with multiple quality issues
- Iterating on a new skill until it meets standards
- Automated fix-review cycles instead of manual editing
- Consistent quality enforcement across skills
When NOT to Use
- One-time review: Use
/skill-reviewerdirectly instead - Quick single fixes: Edit the file directly
- Non-skill files: Only works on SKILL.md files
- Experimental skills: Manual iteration gives more control during exploration
Issue Categorization
Critical Issues (MUST fix immediately)
These block skill loading or cause runtime failures:
- Missing required frontmatter fields (name, description) — Claude cannot index or trigger the skill
- Invalid YAML frontmatter syntax — Parsing fails, skill won't load
- Referenced files that don't exist — Runtime errors when Claude follows links
- Broken file paths — Same as above, leads to tool failures
Major Issues (MUST fix)
These significantly degrade skill effectiveness:
- Weak or vague trigger descriptions — Claude may not recognize when to use the skill
- Wrong writing voice (second person "you" instead of imperative) — Inconsistent with Claude's execution model
- SKILL.md exceeds 500 lines without using references/ — Overloads context, reduces comprehension
- Missing "When to Use" or "When NOT to Use" sections — Required by project quality standards
- Description doesn't specify when to trigger — Skill may never be selected
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.
- 9d ago First seen · 146 lines · 55 tokens per session scan A c59a98378976
skill-improver is a skill published in the GitHub repository ratnesh-maurya/cursor-claude-personas (8 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,241 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
hitl
Rosetta CRITICAL MUST skill to load as Prep Step 3 Step 2 — immediately after orchestrator-contract, right before loading any workflow. Loads the session-wide approval-gate protocol governing when to stop and wait vs proceed. WITHOUT IT decisions proceed silently, violating enterprise policy. Activate it for ALL tasks…
research
To run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
nextauth
NextAuth.js authentication for Next.js. Covers providers, sessions, and callbacks. Use for Next.js authentication. USE WHEN: user mentions "NextAuth", "Next.js auth", "Auth.js", asks about "Next.js authentication", "App Router auth", "next-auth", "authentication providers" DO NOT USE FOR: generic OAuth (use oauth2…
git-workflow
Git workflow best practices. Covers branching, commits, and collaboration. Use for version control guidance. USE WHEN: user mentions "git", "commit", "branch", "pull request", "PR", "merge", "rebase", "version control", asks about "commit message", "branching strategy", "git best practices", "conventional commits"…