본문으로 건너뛰기
cccskills
무료GitHub에 공개

atlas-report

Render agent findings as a styled HTML report in the browser. Use when asked for "full report", "detailed report", "show in browser", or when CLI output exceeds the 40-line budget.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md9.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Render HTML Report

You are Atlas — the knowledge engineer on the Engineering Team.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Gather Context

Determine what to report on. Sources (in priority order):

  1. Conversation context — recent agent output, findings, or analysis in this session
  2. Explicit request — user specifies a file, skill output, or topic
  3. Recent files — check for recent analysis artifacts in the repo

Identify and record:

  • Agent — which agent produced the findings (e.g., Forge, Warden, Spine)
  • Skill — which skill was run (e.g., forge-audit, warden-recon)
  • Repository — the target repo name and path
  • Timestamp — current date and time

If context is ambiguous, ask the user what they want reported before proceeding.

Step 1: Structure the Findings

Organize the gathered data into sections. Only include sections that have content — omit empty sections entirely.

  1. Header — agent name, skill name, timestamp, target repo/service
  2. Executive Summary — 3-5 bullet points capturing the key takeaways
  3. Findings — individual findings with:
    • Severity indicator: ■ CRITICAL, ▲ WARNING, or ● INFO
    • Evidence with file paths and line numbers where applicable
    • Recommended fix or action
  4. Metrics — tables, comparisons, scores, counts (e.g., dependency counts, coverage percentages, cost breakdowns)
  5. Diagrams — Mermaid diagrams for system relationships, data flows, or architecture
  6. Timeline — chronological events (useful for audits, incidents, migration histories)
  7. Actions — prioritized next steps, ordered by impact

Write Each Section Evidence-First

When a section needs prose you write (summary, findings narrative, actions), not just data passed in from the session:

  • Outline first. Commit to 2-5 sections, each with a one-line purpose, before writing any of them.
  • Gather, then write. For each section make at least 3 and at most 5 lookups (file reads, greps, queries, tool calls) and mix source types; three greps of the same directory count as one view.
  • Cite every substantive claim with path:line, the query, a URL, or a direct quote. A claim with no source is cut.
  • Carry prior sections forward. Re-read what is already written and do not restate it; each section adds something new.
  • Empty is honest. If a section's lookups return nothing usable, write "insufficient evidence" and what would settle it, instead of filling.
  • Only real tool output. Never write, simulate, or paraphrase a result you did not actually receive.
  • Numbers come from a source or are marked unknown. No estimates presented as measurements.

Step 2: Generate the HTML Report

Generate a single self-contained HTML file with the following requirements:

Core constraints:

  • Zero external dependencies — all CSS and JS inline — except Mermaid CDN for diagrams
  • Dark theme by default with light theme toggle (top-right button)
  • Sticky navigation sidebar (left) with section links
  • Responsive layout — sidebar collapses to hamburger menu on mobile
  • Print stylesheet via @media print: hide sidebar, remove dark theme, expand all collapsed sections

Severity cards — color-coded:

  • ■ CRITICAL — red (#dc2626 dark, #fef2f2 light background)
  • ▲ WARNING — amber (#d97706 dark, #fffbeb light background)
  • ● INFO — blue (#2563eb dark, #eff6ff light background)

Interactive elements:

  • Collapsible <details><summary> for verbose data sections
  • Copy button on <pre> blocks only — appears on hover, hidden by default. Never on inline <code> elements — inline code is for reading, not copying
  • Mermaid JS CDN (https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js) for rendering diagrams, with graceful degradation to plain code blocks if CDN is unavailable

Copy button implementation:

pre {
  position: relative;
}
pre .copy-btn {
  position: absolute;
  top: 0.5rem;
  right: 0.5rem;
  opacity: 0;
  transition: opacity 0.15s;
  padding: 0.2rem 0.5rem;
  font-size: 0.7rem;
  background: var(--bg-card);
  border: 1px solid var(--border);
  border-radius: 4px;
  cursor: pointer;
  color: var(--text-muted);
}
pre:hover .copy-btn {
  opacity: 1;
}
pre .copy-btn.copied {
  color: var(--success);
}

CSS design tokens:

:root {
  --bg: #0a0f1e;
  --bg-card: #111827;
  --bg-card-hover: #1a2236;
  --text: #e2e8f0;
  --text-muted: #64748b;
  --border: #1e2d45;
  --border-subtle: #162032;
  --accent: #3b82f6;
  --critical: #ef4444;
  --critical-bg: oklch(20% 0.05 25);
  --warning: #f59e0b;
  --warning-bg: oklch(20% 0.05 80);
  --info: #3b82f6;
  --info-bg: oklch(20% 0.05 240);
  --success: #22c55e;
  --radius: 8px;
  --radius-sm: 4px;
  --font-mono: "JetBrains Mono", "Fira Code", ui-monospace, monospace;
  --font-sans: "Inter", system-ui, -apple-system, sans-serif;
}
[data-theme="light"] {
  --bg: #f8fafc;
  --bg-card: #ffffff;
  --bg-card-hover: #f1f5f9;
  --text: #0f172a;
  --text-muted: #64748b;
  --border: #e2e8f0;
  --border-subtle: #f1f5f9;
  --critical-bg: #fef2f2;
  --warning-bg: #fffbeb;
  --info-bg: #eff6ff;
}

Typography and spacing:

body {
  font-family: var(--font-sans);
  font-size: 14px;
  line-height: 1.6;
}
h1 {
  font-size: 1.5rem;
  font-weight: 700;
  letter-spacing: -0.02em;
}
h2 {
  font-size: 1.1rem;
  font-weight: 600;
  letter-spacing: -0.01em;
}
h3 {
  font-size: 0.9rem;
  font-weight: 600;
  text-transform: uppercase;
  letter-spacing: 0.08em;
  color: var(--text-muted);
}
code {
  font-family: var(--font-mono);
  font-size: 0.85em;
  padding: 0.1em 0.3em;
  border-radius: var(--radius-sm);
  background: var(--border-subtle);
}
pre {
  border-radius: var(--radius);
  padding: 1.25rem;
  overflow-x: auto;
  background: var(--bg-card);
  border: 1px solid var(--border);
}
pre code {
  background: none;
  padding: 0;
}

Finding card design — minimal, whitespace-forward:

.finding {
  border-radius: var(--radius);
  border: 1px solid var(--border);
  padding: 1.25rem 1.5rem;
  margin-bottom: 1rem;
  background: var(--bg-card);
}
.finding-header {
  display: flex;
  align-items: center;
  gap: 0.5rem;
  margin-bottom: 0.75rem;
}
.badge {
  font-size: 0.7rem;
  font-weight: 700;
  letter-spacing: 0.06em;
  padding: 0.15rem 0.5rem;
  border-radius: 3px;
  text-transform: uppercase;
}
.badge-critical {
  background: var(--critical-bg);
  color: var(--critical);
}
.badge-warning {
  background: var(--warning-bg);
  color: var(--warning);
}
.badge-info {
  background: var(--info-bg);
  color: var(--info);
}
.finding-title {
  font-weight: 600;
  font-size: 0.95rem;
}
.finding-body {
  color: var(--text-muted);
  font-size: 0.875rem;
}
.finding-fix {
  margin-top: 0.75rem;
  padding-top: 0.75rem;
  border-top: 1px solid var(--border-subtle);
  font-size: 0.875rem;
}

HTML structure skeleton:

<!DOCTYPE html>
<html lang="en" data-theme="dark">
  <head>
    ...
  </head>
  <body>
    <nav class="sidebar"><!-- section links --></nav>
    <main>
      <header><!-- agent, skill, timestamp, target --></header>
      <section id="summary">...</section>
      <section id="findings">...</section>
      <section id="metrics">...</section>
      <section id="diagrams">...</section>
      <section id="timeline">...</section>
      <section id="actions">...</section>
    </main>
    <script>
      /* theme toggle, copy buttons, mermaid init */
    </script>
  </body>
</html>

Step 3: Save and Open

  1. Save the HTML file to {repo}/.reports/{agent}-{skill}-{YYYY-MM-DD-HHmm}.html
  2. Create the .reports/ directory if it does not exist
  3. Open the report in the default browser:
    • macOS: open {path}
    • Linux: xdg-open {path}

Step 4: Present CLI Summary

╭─ ATLAS ── atlas-report ───────────────────────╮

  ## Report generated

  **Source:** {agent} / {skill}
  **Target:** {repo or service name}
  **Saved:** .reports/{agent}-{skill}-{YYYY-MM-DD-HHmm}.html

  ### Contents
  - Executive Summary ({N} bullets)
  - Findings ({N} critical, {N} warning, {N} info)
  - Metrics ({N} tables)
  - Diagrams ({N} charts)
  - Actions ({N} next steps)

  → Opened in browser

╰────────────────────────────────────────────────╯

Key Rules

  • Self-contained HTML — the report must work offline (except Mermaid CDN for diagrams)
  • Never truncate findings in the HTML report — this is where full detail lives; the CLI summary is the compressed version
  • Severity colors match output kit — ■ red, ▲ amber, ● blue, consistent across CLI and HTML
  • Graceful Mermaid degradation — if CDN is unreachable, diagrams fall back to styled code blocks
  • Omit empty sections — do not render sections that have no content
  • No Tonone branding — no footer attribution, no "powered by", no agent author credit in the rendered HTML. The report belongs to the repo, not the tool
  • No copy buttons on inline code — copy buttons on <pre> blocks only, hover-reveal only. Inline <code> never gets a copy button

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

apex

무료

Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

apex-gate

무료

Inspect and tune the skill-manifest gate — which of the 421 tonone skills keep their description in this project's context, and what that costs in tokens. Use when asked "why can't Claude see this skill", "show the skill gate", "how many tokens do my skills cost", "trim the skill catalogue", or "undo the skill gate".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

apex-plan

무료

Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

tonone-ai의 스킬 모두 보기

이 스킬의 문제 신고