From odin
Authors a new SKILL.md with optional references, scripts, and evals following Anthropic's progressive-disclosure conventions. Triggers on requests to write, create, or draft skills.
npx claudepluginhub outlinedriven/odin-claude-plugin --plugin odinThis skill uses the workspace's default tool permissions.
Skill authoring loop: gather requirements, draft against the SKILL.md contract, review with the user, refine. One concern per skill; one skill per directory. Apply the `skill-creator:skill-creator` methodology (three-level progressive disclosure, pushy descriptions, evals.json).
Scaffold new cc-settings skill (frontmatter, layout, MANUAL.md registration). Triggers "create a skill", "write a skill", "new skill", or repeated prompt patterns worth turning into a skill.
Guides creation or updating of skills extending Codex with specialized knowledge, workflows, and tool integrations. Use when building new or modifying existing skills.
Guides creation of effective skills extending AI model capabilities with specialized knowledge, workflows, and tool integrations. Useful when users request new or updated skills.
Share bugs, ideas, or general feedback.
Skill authoring loop: gather requirements, draft against the SKILL.md contract, review with the user, refine. One concern per skill; one skill per directory. Apply the skill-creator:skill-creator methodology (three-level progressive disclosure, pushy descriptions, evals.json).
write-a-skill — authors one SKILL.md for one capability inside an existing skills tree.skill-creator:skill-creator — the upstream methodology this skill applies; consult it for the canonical contract.Gather requirements — surface decisions before drafting:
Draft the SKILL.md — write to the contract below. Keep body terse and decision-oriented.
Review with the user — present the draft, surface ambiguous decisions, and refine.
Verify — run any bundled evals.json cases; targeted re-read of the SKILL.md to confirm description triggers and body alignment.
skill-name/
SKILL.md # contract; required
references/ # deeper docs loaded on-demand
REFERENCE.md
EXAMPLES.md
scripts/ # deterministic helpers
helper.{ts,py,sh}
evals.json # trigger / behavior evals
Reference paths in SKILL.md use references/X.md, never ./X.md.
---
name: skill-name
description: <what the skill does>. <when to trigger it — concrete phrases or contexts>.
---
<One-line imperative summary of the skill's posture.>
## <Section> — terse decision-oriented prose
<Body in imperative voice with brief why. ≤200 lines.>
Frontmatter rules:
name — kebab-case, matches directory.description — pushy: name what AND when. Max 1024 chars. Third person. First sentence states capability; second sentence states triggers.disable-model-invocation: true — preserve verbatim from source if present; do not fabricate.Weak: Helps with documents. Strong: Extract text and tables from PDF files, fill forms, merge documents. Trigger when user mentions PDFs, forms, or document extraction.
Add a script when the operation is deterministic and the same code would otherwise be regenerated each invocation. Skip scripts when the work is contextual reasoning the model must perform fresh each time.
Imperative or third person. No "you/your" addressee. English-mandate: grammatical English, articles preserved. Banned tooling absent: prefer bat -P -p -n, fd, git grep, ast-grep, srgn, hyperfine, difft, eza, rip over their banned counterparts.