All skills
simota avatar

/tome

@35ffd55
by shingo imotasimota/agent-skills85 stars
15

Converting technical knowledge into durable learning documents and publishable articles. Use for diff-based teaching, decision records, onboarding, note/Zenn/Qiita/dev.to posts, article series, retrospectives, and cross-platform repurposing.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/tome

This session only. Nothing lands on disk.

referencehandoffs.md

≈839 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Handoff Templates

Purpose: Handoff templates between Tome and other agents. Read when: Confirming inter-agent collaboration formats.


Incoming Handoffs

From User (Direct Request)

USER_TO_TOME:
  target:
    type: "[commit | pr | branch | file_range]"
    ref: "[specific reference]"
  audience:
    level: "[beginner | intermediate | advanced | auto]"
  output:
    format: "[learning_doc | glossary | decision_record | tutorial | learning_series | incremental_doc]"
  mode: "[standard | incremental | batch]"
  prev_doc: "[path to previous learning doc, if incremental]"
  notes: "[additional requests or focus areas]"

From Agent (Generic Handoff)

Used by Trail, Launch, Lens, Scout, and any other upstream agent.

AGENT_TO_TOME_HANDOFF:
  source_agent: "[Trail | Launch | Lens | Scout | ...]"
  investigation:
    target: "[investigation subject]"
    findings: "[key findings or data]"
    commits: "[key commit list, if applicable]"
    root_cause: "[root cause, if applicable]"
    timeline: "[change timeline, if applicable]"
  request:
    focus: "[documentation focus]"
    audience: "[target audience level or auto]"
    format: "[output format]"

Outgoing Handoffs

To Quill (Inline Documentation)

TOME_TO_QUILL_HANDOFF:
  source:
    learning_doc: "[path to generated learning document]"
    key_insights: "[key insights]"
  request:
    action: "[inline comments / JSDoc / README updates]"
    target_files: "[target file list]"
    priority_items:
      - "[most important annotation point 1]"
      - "[most important annotation point 2]"

To Scribe (Specification Documents)

TOME_TO_SCRIBE_HANDOFF:
  source:
    learning_doc: "[path to generated learning document]"
    decisions: "[recorded design decision list]"
  request:
    action: "[spec/design document promotion]"
    format: "[ADR | HLD | design doc]"
    spec_candidates:
      - item: "[item to promote to spec]"
        rationale: "[why it should become a spec]"

To Canvas (Visualization + Knowledge Graph)

TOME_TO_CANVAS_HANDOFF:
  source:
    learning_doc: "[path to generated learning document]"
    flows: "[flows to visualize]"
    knowledge_graph: "[concept relationships as structured data]"
  request:
    action: "[Mermaid/ASCII diagram generation]"
    diagram_types:
      - type: "[sequence | flowchart | state | class | concept_map]"
        scope: "[diagram scope]"
        highlight: "[change portion highlight instructions]"

To Lore (Knowledge Catalog)

TOME_TO_LORE_HANDOFF:
  source:
    learning_doc: "[path to generated learning document]"
    patterns: "[extracted general patterns]"
    quality_scorecard: "[A/B/C per axis]"
  request:
    action: "[knowledge catalog registration]"
    insights:
      - pattern: "[pattern name]"
        description: "[pattern description]"
        applicability: "[applicability scope]"

To Cue (Demo Narration Scripts)

TOME_TO_CUE_HANDOFF:
  source:
    learning_doc: "[path to generated learning document]"
    change_walkthrough: "[step-by-step change flow]"
  request:
    action: "[demo narration script generation]"
    scenes:
      - scene: "[scene description]"
        screen_capture: "[what to show on screen]"
        narration_focus: "[key teaching point]"

Source: SKILL.md on GitHub

No alerts13d4 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The 'tome' skill is a technical documentation and article authoring tool designed to convert git changes and raw source material into structured learning assets. It incorporates robust safety standards, such as a strict 'Documents only' policy and mandatory masking of sensitive information like credentials and client details. While the skill processes external data, it includes explicit mechanisms to prevent the execution of untrusted instructions, ensuring a secure environment for technical writing.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 35ffd55. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/tome