Use to release a revision after verifying CI and approval.
Repository statistics
Indexed skills
25
Skill groups
2
GitHub stars
12
Forks
0
Skills by folder
25 totalRelease gate comparison
2 skillsUse to release a revision after verifying CI and approval.
Skills
23 skillsAuthor a small preregistered SkillRoll case pack from a target skill and neutral repository context without seeing prior run outcomes.
Coordinate an end-to-end independent live evaluation of the current SkillRoll main across a small varied set of external skill repositories.
Use when supplied change facts need a summary, risk assessment, and review document.
Plan and regenerate truthful terminal demos, README cards, social previews, and ANSI artwork for a developer-tool repository. Use when product media must tell a concise story while remaining reproducible from repository scripts.
Use when an author needs to add, review, audit, or improve SkillRoll cases for a skill behavior or prompt regression.
Maintain a session-scoped, source-backed FACTS.md containing only verified facts during long debugging, research, implementation, and review tasks. Use when a task needs a compact record of current claims, evidence, context, and freshness across turns. Initialize the book, read it before acting, add verified facts, reconcile stale or superseded records, and report the evidence. Do not use for one-off fact lookup, theories, opinions, decisions, or checking a finished document against its source.
Prepare an isolated external repository trial using an exact target revision and the current local SkillRoll main without running inference.
Use when summary and risk artifacts need a concise evidence-based review.
Use to release a revision after verifying CI and approval.
Execute a frozen SkillRoll case pack with live inference, preserve its evidence, and classify technical, case-authoring, and target-skill outcomes.
Select and preregister small external Agent Skills repositories for an independent SkillRoll trial before any run outcomes are inspected.
Use when SkillRoll must judge one completed skill evaluation from its authored criteria and observed evidence without executing either actor.
Use when an author needs to create, review, audit, or improve an Agent Skill and its supporting references or scripts.
Use when a repository owner needs the shortest safe path from an existing skills folder to a first SkillRoll eval.
Use when supplied change evidence needs a bounded factual summary artifact.
Compose evidence-grounded customer notes while routing audience policy to a reference and repeated heading formatting to a deterministic script.
Use when a pull-request merge, release, or publication request needs its independent readiness and approval boundaries checked before action.
Turn supplied support evidence into a concise, evidence-grounded customer response or internal handoff.
Use when a request needs named skill steps coordinated into one evidence-based result.
Use when supplied change facts need concrete risks and evidence gaps identified.
Use when SkillRoll must execute an evaluated Agent Skill with one bounded world_action tool and preserve the skill's own action terminology.
Use when supplied pull-request facts need a concise Markdown overview.
Use when SkillRoll must simulate exactly one intended external action without executing it, judging the skill, or exposing local data.
Add to your README
The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.
<a href="https://skilld.dev/gh/hagaiw/skillroll">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/hagaiw/skillroll?theme=dark">
<source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/hagaiw/skillroll?theme=light">
<img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/hagaiw/skillroll?theme=light">
</picture>
</a>