Menu
SkillsMP a collecté 18 skills depuis Arenukvern/skill_steward. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 18 skills collectés sur 18.
Steward public stories about any work — creation ethics, application ethics, and maintenance of the story plus its disclosures (generated, drafted, curated, authored). Use when writing a public article, origin story, talk, README narrative, or showcase about…
Langue du texte source : anglais
Establish or audit a structural quality contract for any agent-operated engineering repository: app, library, CLI/tool, plugin, harness, or meta repo.
Langue du texte source : anglais
Establish or audit a structural quality contract for any agent-operated engineering repository: app, library, CLI/tool, plugin, harness, or meta repo. Use when a repo needs charter clarity, docs/decision ownership, type-native validation gates, evidence…
Langue du texte source : anglais
Designs public or private Agent Skill and plugin marketplaces for Cursor, Claude Code, Codex, Zed, Open Plugin, and npx skills—manifest layout, install matrix, and Skill Steward vs product boundaries. Use when setting up a marketplace, distributing…
Langue du texte source : anglais
Scaffold and formally review a new Agent Skill in this marketplace repo. Covers valid SKILL.md generation, directory layout, registry entries, and spec auditing. Use when adding a skill, validating frontmatter, or checking marketplace readiness before a PR.
Langue du texte source : anglais
Maintains repo-local action contracts and harness repositories where product CLI and MCP adapters stay thin over core libraries. Use when adopting or improving steward.yaml actions, capability-level adoption evidence, cold-start proof loops, probes,…
Langue du texte source : anglais
Critically analyze whether a product, repo, skill, plugin, harness, or architecture vision still fits the real application, user intent, implementation, evidence, and likely future direction. Use when asked to assess vision vs application, predict future fit,…
Langue du texte source : anglais
Maintain stewardship protocol continuity and tool/personality boundaries. Use when a repo agent needs steward-mode threshold checks, self-model update decisions, delegation hygiene, boundary violation review, or handoff-safe continuity context without…
Langue du texte source : anglais
Replace with what this skill does and when to use it. Include trigger phrases users say, e.g. "audit my API", "scaffold a skill"; activation-critical routing belongs here.
Langue du texte source : anglais
This skill has a name that does not match its directory.
Langue du texte source : anglais
This skill incorrectly includes a README.md which should be a warning.
Langue du texte source : anglais
Name uses uppercase and underscores which violates the kebab-case rule.
Langue du texte source : anglais
A skill that is intentionally missing its license frontmatter field to test the validator warning path.
Langue du texte source : anglais
A skill that is missing its references/sources.md on purpose.
Langue du texte source : anglais
This skill is used to test the line count warning in the validator.
Langue du texte source : anglais
Does something useful when the user wants to do X. Triggered by phrases like "help me with X".
Langue du texte source : anglais
Simulates a skill directory that is well-formed but absent from skills.sh.json, to exercise registry drift detection in the validator.
Langue du texte source : anglais
This skill exists to test the body length <50 chars warning in the validator.
Langue du texte source : anglais