A skill-building pipeline that turns a problem description into a structured agent skill, including its instructions, input and output rules, and failure statuses.

Use it to create a new skill from a short request, preview the result without writing files, and validate the generated files with voice, syntax, scrubber, and smoke checks.

It limits generated work to a fixed template and runs checks before saving the new skill, reducing the chance of producing an incomplete or invalid one.

meta-skill — Skill for Claude Code and Codex by dailyaiagents-cpu

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 dailyaiagents-cpu/dailyai-os --skill meta-skill

Clone the repo

git clone --depth 1 https://github.com/dailyaiagents-cpu/dailyai-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/meta-skill/github.svg)](https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/meta-skill)

Your own site

<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/meta-skill"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/meta-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dailyaiagents-cpu/dailyai-os/meta-skill"><img src="https://agentmods.dev/badge/skills/dailyaiagents-cpu/dailyai-os/meta-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,149 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.

Model	Per session	Once invoked
Fable 5.1	$0.00128	$0.01149
Opus 5.5	$0.00051	$0.00460
Sonnet 5.5	$0.00026	$0.00230
Haiku 4.5	$0.00013	$0.00115

Measured 2mo ago against content hash 648bd8239cea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meta-skill 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/meta-skill/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

meta-skill

The thesis: AI agents writing arbitrary code is risky and unbounded. AI agents filling a structured template under hard validation is bounded and shippable. This skill is the demonstration: a tightly-shaped pipeline where the LLM authors only the parts of a new skill that humans would hand-write anyway, while the bash skeleton, error handling, and gate calls are generated deterministically.

Procedure

bash skills/meta-skill/run.sh "I need a skill that watches X for Y and writes to Z"
bash skills/meta-skill/run.sh --dry-run "<problem>"  # parse + validate, no write

Pipeline

Parse the problem string via local Ollama qwen3.5:latest. Extract:
- skill_name (kebab-case, 3-6 words)
- owner_agent (one of: content, builder, ops, sales, research, accountant, trading, hermes)
- description (one sentence, voice-rule-compliant)
- pipeline_steps (3-7 numbered steps)
- trigger (cron / event / manual / on-skill-call)
- inputs (named parameters; empty list OK)
- outputs (paths or stdout shape)
Generate SOUL.md (intent + failure mode + voice anchor; 100-200 words).
Generate SKILL.md (frontmatter + procedure + status codes; static template filled with extracted fields).
Generate run.sh (skeleton with proper error handling, voice-gate calls if outputs are text-bound, smoke-test stub, TODO markers for the actual pipeline body).
Validate: a. python3 tools/voice/score.py on the SKILL.md description → must score >= 60. b. python3 tools/voice/scrubber.py on the description → must pass. c. bash -n run.sh → must pass syntax check. d. Smoke-test: bash run.sh --dry-run → must exit non-error (rc != 2) and produce a STATUS= line.
Land:
- If all 4 validations pass → write to ~/.openclaw/skills/<name>/ (or ~/.hermes/skills/<name>/ for hermes-owned).
- If any fails → write to data/proposed_skills/cont-17-meta/<name>/ for Cooper review, with a _VALIDATION.md file detailing what failed.
Output JSON to stdout: {status, skill_path, smoke_test_result, gates_passed}.

Read the full file on GitHub · 89 lines

Files

What ships with it

2 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.

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.

2mo ago First seen · 89 lines · 128 tokens per session scan A 648bd8239cea

Subscribe to this mod's changes

meta-skill is a skill published in the GitHub repository dailyaiagents-cpu/dailyai-os (0 stars, last pushed 6mo ago), licensed MIT. It adds 128 tokens to every session and 1,149 once invoked, about $0.0005 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 2026-08-31.

Building agents

meta-skill next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
meta-skilldailyaiagents-cpu/dailyai-os	Skill	0	6mo ago	MIT	A	128	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code

meta-skill

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

meta-skill

Procedure

Pipeline

What ships with it

What this file has done since we first saw it

meta-skill compared with skills from other repositories