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 agentmods add skills/zfinix/aster/skill-creatornpx skills add Zfinix/aster --skill skill-creatorgit clone --depth 1 https://github.com/Zfinix/asterWhat 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 | $0.00057 | $0.00541 |
| Opus 5 | $0.00028 | $0.00270 |
| Sonnet 5 | $0.00011 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
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 2d 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.
What it actually says
Skill creator
- Check the index first. If an existing skill already covers the workflow, extend that skill's file instead of creating a near-duplicate.
- Confirm before creating. A skill is a repo or config file; say what you are about to write and where, and get a yes. Exception: the user already asked for the skill in this turn.
- Pick the root by scope. Project-specific workflow:
.aster/skills/<name>/SKILL.mdin the repo. Personal preference that applies everywhere:<aster home>/skills/<name>/SKILL.md. Kebab-case name, under 64 characters. - The description is the trigger, so write it as one. The index shows only name and description; the body loads when a request matches. State what the skill does, then the concrete situations that should fire it: "Use when the user asks to X, mentions Y, or a Z fails."
- Body format: numbered imperative rules with counter-examples. Each
rule is one behavior, stated as a command, with a literal do-this and
never-this where it helps. Write "Stage named files:
git add src/a.rs. Nevergit add -A." Never write essays about philosophy. - Capture the evidence, not the theory. Put in the exact commands that worked this session, the failure that motivated the rule, and the check that proves the workflow succeeded. A skill mined from a real session beats one written from imagination.
- Keep it small. A few hundred to a couple thousand words. Past that, split into two skills with distinct triggers.
- Frontmatter is exactly
nameanddescriptionbetween---fences, then the markdown body. Verify after writing: the skill should appear in the index next session, andread_skillshould return the body now. - Corrections are skill fuel. When the user corrects the same thing a
second time, that is the signal: offer to fold it into a skill or a
remembernote so they never repeat it again.
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.
- 2d ago First seen · 37 lines · 57 tokens per session scan A c667f464d576
skill-creator is a skill published in the GitHub repository Zfinix/aster (40 stars, last pushed 7d ago), licensed Apache-2.0. It adds 57 tokens to every session and 541 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 2026-08-30.
Other skills, from other repositories
lemma-evals
Design, run, and review repeatable evaluations for Lemma agents, functions, and workflows. Use when defining evaluation contracts and case datasets, comparing a baseline with a candidate revision or runtime, checking deterministic correctness or rubric-scored judgment, measuring repeated-run variance, testing…
lemma-skill-creator
Create, revise, publish, and smoke-test pod-owned Lemma agent skills under /skills/skill-name. Use when defining a skill's triggers and instructions, organizing its references or scripts, safely updating an existing custom skill, publishing one through Lemma files, or checking that an agent discovers and follows it.…
coordinate
Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
Prompting
Meta-prompting standard library for generating, optimizing, and composing prompts programmatically via Standards, Handlebars Templates, and Tools; output is always a prompt to use elsewhere, not final content. USE WHEN meta-prompting, template generation, prompt optimization, prompt engineering, write a prompt, create…
BitterPillEngineering
Audits any AI instruction set for over-prompting using the core test — would a smarter model make this rule unnecessary? Applies Five Questions to every rule (Claude already does this? Contradiction? Redundant? One-off fix? Vague?) then classifies as CUT/RESOLVE/MERGE/EVALUATE/SHARPEN/MOVE/KEEP. Workflows: Audit (full…
Fabric
Execute any of 240+ specialized prompt patterns natively across Extraction, Summarization, Analysis, Creation, Improvement, Security, Rating. Common: extractwisdom, createthreatmodel, analyzeclaims, improvewriting, reviewcode, mermaid, youtubesummary. CLI used only for YouTube transcript (-y) and URL fallback (-u).…