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 ldclabs/anda-bot --skill skill-creatorgit clone --depth 1 https://github.com/ldclabs/anda-botWrote 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/ldclabs/anda-bot/skill-creator)<a href="https://agentmods.dev/skills/ldclabs/anda-bot/skill-creator"><img src="https://agentmods.dev/badge/skills/ldclabs/anda-bot/skill-creator/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/ldclabs/anda-bot/skill-creator"><img src="https://agentmods.dev/badge/skills/ldclabs/anda-bot/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 75 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 173 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 287 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00069 | $0.03102 |
| Opus 5.5 | $0.00028 | $0.01241 |
| Sonnet 5.5 | $0.00014 | $0.00620 |
| Haiku 4.5 | $0.00007 | $0.00310 |
Grade A, and why
skill-creator 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 21d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
This skill helps create and improve Anda Bot runtime skills. Anda Bot loads
skills from ~/.anda/skills or other configured skill directories. Each skill
is a directory containing SKILL.md and optional bundled resources.
Use this skill to:
- Create a new skill from a workflow the user describes.
- Update an existing skill while preserving its name and contract.
- Convert a skill written for another agent runtime into an Anda Bot skill.
- Create behavior test prompts and trigger evals.
- Run evals through
anda agent runwhen a configured Anda runtime is available. - Package a finished skill for installation.
Core Loop
At a high level:
- Understand what the skill should help Anda Bot do.
- Draft or revise
SKILL.md. - Create a few realistic test prompts.
- Run the prompts with the skill and compare against a baseline when useful.
- Review qualitative outputs and quantitative checks with the user.
- Improve the skill based on evidence.
- Repeat until the skill is useful and not overfit.
- Optionally optimize the frontmatter description and package the skill.
Be flexible. If the user explicitly wants a quick edit without evals, make the edit and run lightweight validation instead of forcing the full loop.
Communicating With The User
Adjust terminology to the user's familiarity. "Eval" and "benchmark" are fine for technical users, but briefly explain them for users who may not use those terms. Avoid making skill creation sound harder than it is: the core file is a Markdown instruction file plus optional helper files.
Creating Or Updating A Skill
Capture Intent
Extract intent from the current conversation first. If the user says "turn this workflow into a skill", identify the sequence of steps, tools used, corrections the user made, input formats, output formats, and success criteria.
Answer these questions before drafting:
- What should this skill enable Anda Bot to do?
- When should the skill trigger? Include user phrases, file types, task types, and near-misses where it should not trigger.
- What should the output look like?
- What tools, local files, scripts, APIs, or external programs does it need?
- Should test cases be created now?
What ships with it
17 files 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.
- agents/analyzer.md 10 KB
- agents/comparator.md 7.1 KB
- agents/grader.md 8.8 KB
- assets/eval_review.html 6.9 KB
- eval-viewer/generate_review.py 16 KB runs code
- eval-viewer/viewer.html 44 KB
- LICENSE.txt 11 KB
- references/schemas.md 12 KB
- scripts/__init__.py 0 B runs code
- scripts/aggregate_benchmark.py 14 KB runs code
- scripts/generate_report.py 13 KB runs code
- scripts/improve_description.py 8.9 KB runs code
- scripts/package_skill.py 4.2 KB runs code
- scripts/quick_validate.py 6.3 KB runs code
- scripts/run_eval.py 16 KB runs code
- scripts/run_loop.py 15 KB runs code
- scripts/utils.py 1.6 KB runs code
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.
- 21d ago Changed 3fede6358be8
- 1mo ago First seen · 421 lines · 69 tokens per session scan A 6d33597482f2
skill-creator is a skill published in the GitHub repository ldclabs/anda-bot (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 3,102 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…