yaojingang
377 lines
26 KiB
HTML
377 lines
26 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="utf-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<title>Yao Meta Skill Review Viewer</title>
|
|
<style>
|
|
:root {
|
|
--text: #111111;
|
|
--muted: #666666;
|
|
--line: #e8e8e8;
|
|
--soft: #f6f6f4;
|
|
--white: #ffffff;
|
|
}
|
|
* { box-sizing: border-box; }
|
|
body {
|
|
margin: 0;
|
|
background: var(--white);
|
|
color: var(--text);
|
|
font-family: "Helvetica Neue", Helvetica, Arial, sans-serif;
|
|
line-height: 1.6;
|
|
}
|
|
.page {
|
|
max-width: 1120px;
|
|
margin: 0 auto;
|
|
padding: 48px 32px 72px;
|
|
}
|
|
.hero {
|
|
padding-bottom: 28px;
|
|
border-bottom: 1px solid var(--line);
|
|
margin-bottom: 28px;
|
|
}
|
|
h1, h2, h3 {
|
|
margin: 0 0 12px;
|
|
letter-spacing: -0.02em;
|
|
font-weight: 600;
|
|
}
|
|
h1 { font-size: 40px; line-height: 1.08; }
|
|
h2 { font-size: 22px; margin-top: 34px; }
|
|
h3 { font-size: 16px; }
|
|
p, li, span { font-size: 15px; }
|
|
.lede {
|
|
max-width: 860px;
|
|
font-size: 18px;
|
|
color: var(--muted);
|
|
margin: 0 0 18px;
|
|
}
|
|
.meta {
|
|
display: flex;
|
|
gap: 10px;
|
|
flex-wrap: wrap;
|
|
margin-top: 16px;
|
|
}
|
|
.meta span {
|
|
border: 1px solid var(--line);
|
|
padding: 6px 10px;
|
|
background: var(--soft);
|
|
}
|
|
.arch-grid {
|
|
display: grid;
|
|
grid-template-columns: repeat(5, minmax(0, 1fr));
|
|
gap: 12px;
|
|
margin-top: 16px;
|
|
}
|
|
.arch-step, .panel, .direction-card, .baseline-box {
|
|
border: 1px solid var(--line);
|
|
background: var(--white);
|
|
}
|
|
.arch-step {
|
|
padding: 14px;
|
|
min-height: 132px;
|
|
}
|
|
.step-label {
|
|
font-size: 12px;
|
|
text-transform: uppercase;
|
|
letter-spacing: 0.08em;
|
|
color: var(--muted);
|
|
margin-bottom: 10px;
|
|
}
|
|
.step-detail {
|
|
font-size: 14px;
|
|
}
|
|
.grid {
|
|
display: grid;
|
|
grid-template-columns: 1.1fr 0.9fr;
|
|
gap: 18px;
|
|
margin-top: 16px;
|
|
}
|
|
.panel {
|
|
padding: 18px;
|
|
}
|
|
.panel ul {
|
|
margin: 0;
|
|
padding-left: 18px;
|
|
}
|
|
.direction-grid {
|
|
display: grid;
|
|
grid-template-columns: repeat(3, minmax(0, 1fr));
|
|
gap: 16px;
|
|
margin-top: 16px;
|
|
}
|
|
.variant-grid {
|
|
display: grid;
|
|
grid-template-columns: repeat(3, minmax(0, 1fr));
|
|
gap: 16px;
|
|
margin-top: 16px;
|
|
}
|
|
.direction-card {
|
|
padding: 18px;
|
|
}
|
|
.direction-card ul {
|
|
margin: 12px 0;
|
|
padding-left: 18px;
|
|
}
|
|
.minor {
|
|
color: var(--muted);
|
|
font-size: 13px;
|
|
}
|
|
.variant-card {
|
|
border: 1px solid var(--line);
|
|
background: var(--white);
|
|
padding: 18px;
|
|
}
|
|
.variant-head {
|
|
display: flex;
|
|
justify-content: space-between;
|
|
gap: 12px;
|
|
align-items: baseline;
|
|
}
|
|
.variant-head span {
|
|
color: var(--muted);
|
|
font-size: 12px;
|
|
text-transform: uppercase;
|
|
letter-spacing: 0.06em;
|
|
}
|
|
.variant-description {
|
|
margin: 14px 0;
|
|
padding-left: 14px;
|
|
border-left: 2px solid var(--line);
|
|
color: var(--text);
|
|
}
|
|
.variant-metrics {
|
|
display: flex;
|
|
flex-wrap: wrap;
|
|
gap: 8px;
|
|
margin-bottom: 14px;
|
|
}
|
|
.variant-metrics span {
|
|
border: 1px solid var(--line);
|
|
background: var(--soft);
|
|
padding: 6px 10px;
|
|
font-size: 12px;
|
|
}
|
|
.variant-cues p {
|
|
margin: 8px 0 6px;
|
|
}
|
|
.variant-cues ul {
|
|
margin: 0 0 12px;
|
|
padding-left: 18px;
|
|
}
|
|
table {
|
|
width: 100%;
|
|
border-collapse: collapse;
|
|
margin-top: 14px;
|
|
font-size: 14px;
|
|
}
|
|
th, td {
|
|
border-top: 1px solid var(--line);
|
|
text-align: left;
|
|
padding: 10px 8px;
|
|
vertical-align: top;
|
|
}
|
|
th {
|
|
font-size: 12px;
|
|
text-transform: uppercase;
|
|
letter-spacing: 0.06em;
|
|
color: var(--muted);
|
|
}
|
|
@media (max-width: 1000px) {
|
|
.arch-grid, .direction-grid, .variant-grid, .grid {
|
|
grid-template-columns: 1fr;
|
|
}
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<div class="page">
|
|
<section class="hero">
|
|
<p class="minor">Review Viewer</p>
|
|
<h1>Yao Meta Skill</h1>
|
|
<p class="lede">Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</p>
|
|
<div class="meta">
|
|
<span>maturity: governed</span>
|
|
<span>archetype: governed</span>
|
|
<span>format: agent-skills</span>
|
|
<span>updated: 2026-03-31</span>
|
|
<span>intent confidence: 100 / 100</span>
|
|
</div>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Architecture at a glance</h2>
|
|
<div class="arch-grid"><div class='arch-step'><div class='step-label'>Inputs</div><div class='step-detail'>workflow, prompt, transcript, docs, or notes</div></div><div class='arch-step'><div class='step-label'>Boundary</div><div class='step-detail'>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</div></div><div class='arch-step'><div class='step-label'>Logic</div><div class='step-detail'>Decide whether the request should become a skill and choose the lightest fit.; Capture job, output, exclusions, constraints, and standards.; Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.</div></div><div class='arch-step'><div class='step-label'>Usage</div><div class='step-detail'>Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.; Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</div></div><div class='arch-step'><div class='step-label'>Next</div><div class='step-detail'>Review the top iteration directions before growing the package.</div></div></div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Core logic</h2>
|
|
<ul><li>Decide whether the request should become a skill and choose the lightest fit.</li><li>Capture job, output, exclusions, constraints, and standards.</li><li>Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.</li><li>Write the `description` early and test route quality before expanding the package.</li><li>Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter.</li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>How to use it</h2>
|
|
<ul><li>Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.</li><li>Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</li></ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Intent questions</h2>
|
|
<ul><li><strong>If this skill worked beautifully, what recurring job would it reliably handle for the user every time?</strong><br><span>This reveals the real job-to-be-done and gives the package a humane center instead of a guessed prompt shape.</span></li><li><strong>When someone reaches for this skill in the real world, what materials will they actually hand to it?</strong><br><span>Input shape decides whether references, scripts, or templates are needed.</span></li><li><strong>What finished output should it hand back so the user can immediately keep moving?</strong><br><span>Outputs should drive the package structure before extra guidance is added.</span></li><li><strong>Which nearby requests should this skill politely refuse so the boundary stays clean?</strong><br><span>The exclusion list is the fastest route to better trigger quality.</span></li><li><strong>What matters most here: speed, consistency, auditability, portability, governance, or tone/style fit?</strong><br><span>Constraints decide how much structure, packaging, and review the skill actually needs.</span></li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Why this package is strong</h2>
|
|
<ul><li>触发面保持精简，并锚定在 frontmatter description。</li><li>已生成 Skill IR，核心语义可先于平台打包被审查和迁移。</li><li>已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。</li><li>已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。</li><li>已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。</li><li>已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。</li></ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Borrow plan</h2>
|
|
<ul><li>No external benchmark objects recorded yet. Add 2 to 5 references before deepening the package.</li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Compare view</h2>
|
|
<div class='baseline-box'><p><strong>Winner:</strong> Current</p><p class='minor'>{'priority': ['fewest false positives', 'fewest false negatives', 'highest near-neighbor pass rate', 'highest negative pass rate', 'highest precision', 'highest recall', 'shortest description']}</p><table><thead><tr><th>Variant</th><th>Tokens</th><th>Dev Errors</th><th>Holdout Errors</th><th>Strategy</th></tr></thead><tbody><tr><td>Baseline</td><td>8</td><td>0</td><td>0</td><td>existing</td></tr><tr><td>Current</td><td>65</td><td>0</td><td>0</td><td>current</td></tr><tr><td>Current</td><td>65</td><td>0</td><td>0</td><td>current</td></tr></tbody></table></div>
|
|
</div>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Variant diff studio</h2>
|
|
<div class="variant-grid"><div class='variant-card'><div class='variant-head'><h3>Baseline</h3><span>existing</span></div><p class='variant-description'>Create and improve agent skills.</p><div class='variant-metrics'><span>tokens 8 (0)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create and improve agent skills.</li></ul><p><strong>Drops from baseline</strong></p><p class='minor'>No dropped cues.</p></div></div><div class='variant-card'><div class='variant-head'><h3>Current</h3><span>current</span></div><p class='variant-description'>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</p><div class='variant-metrics'><span>tokens 65 (+57)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.</li><li>Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</li></ul><p><strong>Drops from baseline</strong></p><ul><li>Create and improve agent skills.</li></ul></div></div><div class='variant-card'><div class='variant-head'><h3>Winner — Current</h3><span>current</span></div><p class='variant-description'>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</p><div class='variant-metrics'><span>tokens 65 (+57)</span><span>dev 0 (0)</span><span>holdout 0 (0)</span></div><div class='variant-cues'><p><strong>Adds relative to baseline</strong></p><ul><li>Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.</li><li>Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.</li></ul><p><strong>Drops from baseline</strong></p><ul><li>Create and improve agent skills.</li></ul></div></div></div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Evidence readiness</h2>
|
|
<p class="minor">Readiness score: 85/100</p>
|
|
<ul><li><strong>Intent clarity</strong> · ready<br><span>100/100 intent confidence.</span></li><li><strong>Benchmark coverage</strong> · ready<br><span>3 GitHub benchmark repositories attached.</span></li><li><strong>Pattern gate</strong> · ready<br><span>5 accepted, 1 deferred using threshold 4/4.</span></li><li><strong>Conflict handling</strong> · decision needed<br><span>The stated preference leans lightweight or speed-first, while the benchmark mix leans toward governance, review, or heavier evaluation structure.</span></li><li><strong>Output risk profile</strong> · ready<br><span>5 output risk families attached.</span></li><li><strong>Artifact design profile</strong> · ready<br><span>Execution-focused technical artifact with environment assumptions, copyable commands, expected outputs, and side effects made explicit.</span></li><li><strong>Prompt quality profile</strong> · ready<br><span>89.0/100 prompt-facing quality score.</span></li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Honest boundary check</h2>
|
|
<ul>
|
|
<li>Are the known limits visible before the package deepens?</li>
|
|
<li>Does the evidence support the borrowed patterns?</li>
|
|
<li>Should uncertainty become a clarification question instead of more structure?</li>
|
|
</ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Output risk profile</h2>
|
|
<ul><li><strong>Markdown readability</strong><br><span>Tables can render as dense grids with weak hierarchy or poor mobile readability.; Long bullets can make the output look complete while hiding the actual decision logic.</span></li><li><strong>Citation and footnote clutter</strong><br><span>Footnote markers or dense citation notes can interrupt the reading flow.; Evidence can be over-attached to obvious statements and under-attached to risky claims.</span></li><li><strong>Screenshot and visual capture</strong><br><span>Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.; Missing screenshots can cause the skill to invent visual references instead of declaring the gap.</span></li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Self-repair checks</h2>
|
|
<ul><li>Preview whether each table still reads well when columns are narrow.</li><li>Convert any table with paragraph-length cells into bullets or cards.</li><li>Remove decorative citations that do not support a material claim.</li><li>Move repeated source explanations into one compact source note.</li><li>Check that every screenshot reference points to a real provided or generated asset.</li></ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Artifact design profile</h2>
|
|
<p class="minor">Design system: metric editorial</p>
|
|
<ul><li><strong>Code, CLI, or implementation guide</strong><br><span>Execution-focused technical artifact with environment assumptions, copyable commands, expected outputs, and side effects made explicit.</span></li><li><strong>Report or brief</strong><br><span>High-trust editorial report with a clear first-screen thesis, compact evidence blocks, and decisions separated from supporting detail.</span></li><li><strong>Review viewer</strong><br><span>Side-by-side reviewer studio with explicit tradeoffs, evidence readiness, and fast paths for approving, blocking, or requesting one focused fix.</span></li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Visual quality gates</h2>
|
|
<ul><li>Name the working directory and required inputs for commands.</li><li>Mark destructive, networked, or external side-effect operations.</li><li>Prefer the smallest runnable snippet over broad framework scaffolding.</li><li>Keep the first screen useful without requiring the reader to parse every detail.</li><li>Use tables only for comparisons; move explanations below the table.</li></ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Prompt quality profile</h2>
|
|
<p class="minor">Relevance: prompt-heavy · score 89.0 / 100 · complexity expert</p>
|
|
<ul><li><strong>Completeness</strong> · 100 / 100<br><span>Name missing inputs, outputs, constraints, or success standards before deepening the package.</span></li><li><strong>Clarity</strong> · 85 / 100<br><span>Replace broad verbs with observable actions and define what done means.</span></li><li><strong>Consistency</strong> · 90 / 100<br><span>Check that role, task, format, exclusions, and examples do not contradict each other.</span></li><li><strong>Practicality</strong> · 90 / 100<br><span>Add runnable steps, examples, or verification cues instead of abstract advice.</span></li><li><strong>Specificity</strong> · 80 / 100<br><span>Anchor wording in the user's audience, domain nouns, and target outcome.</span></li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>RTF to skill mapping</h2>
|
|
<ul><li><strong>Role</strong><br><span>Use an operator role with explicit boundaries, inputs, outputs, and failure handling.</span></li><li><strong>Task</strong><br><span>Convert the job into ordered steps with validation checks and stop conditions.</span></li><li><strong>Format</strong><br><span>Return a runbook-like handoff with commands, checks, owners, and next actions when relevant.</span></li></ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Reference coach</h2>
|
|
<div class="direction-grid"><div class='direction-card'><h3>obra/superpowers</h3><p><strong>Borrow now</strong></p><ul><li>Borrow the way it turns a messy workflow into a repeatable operating path.</li><li>Borrow the clear execution entrypoints and command structure.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not import process overhead that only exists for that project's scale.</li></ul></div><div class='direction-card'><h3>affaan-m/ECC</h3><p><strong>Borrow now</strong></p><ul><li>Borrow the way it turns a messy workflow into a repeatable operating path.</li><li>Borrow the clear execution entrypoints and command structure.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not import process overhead that only exists for that project's scale.</li></ul></div><div class='direction-card'><h3>multica-ai/andrej-karpathy-skills</h3><p><strong>Borrow now</strong></p><ul><li>Borrow explicit validation and quality gates that make iteration safer.</li><li>Borrow the way it separates explanation, examples, and reusable structure.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not clone heavyweight evaluation scaffolding if a lighter gate is enough here.</li></ul></div></div>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Decide before you deepen</h2>
|
|
<ul>
|
|
<li>Choose one pattern to borrow on purpose, not three at once.</li>
|
|
<li>State one thing this skill will not inherit from the benchmark objects.</li>
|
|
<li>Only deepen the package after that choice is visible in the boundary or execution flow.</li>
|
|
</ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Reference synthesis</h2>
|
|
<div class="direction-grid"><div class='direction-card'><h3>Official skill anatomy and context discipline</h3><p><strong>Borrow now</strong></p><ul><li>Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not let packaging or platform concerns swallow the core job boundary.</li></ul></div><div class='direction-card'><h3>Human-in-the-loop verification</h3><p><strong>Borrow now</strong></p><ul><li>Borrow a review checkpoint wherever trust matters more than raw speed.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not force every skill through heavyweight review when the risk is low.</li></ul></div><div class='direction-card'><h3>Boundary-first design</h3><p><strong>Borrow now</strong></p><ul><li>Borrow the discipline of defining what the skill should not own before growing the package.</li></ul><p><strong>Avoid</strong></p><ul><li>Do not expand execution assets until route boundaries stay clean.</li></ul></div></div>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Borrow now</h2>
|
|
<ul><li>Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.</li><li>Borrow a review checkpoint wherever trust matters more than raw speed.</li><li>Borrow the discipline of defining what the skill should not own before growing the package.</li><li>Borrow the way it turns a messy workflow into a repeatable operating path.</li></ul>
|
|
<p class="minor">Use the recommendation by default. Only surface the underlying benchmark tradeoffs when intent is uncertain or a real design conflict needs a deliberate call.</p>
|
|
</div>
|
|
</section>
|
|
|
|
<section>
|
|
<h2>Top three next moves</h2>
|
|
<div class="direction-grid"><div class='direction-card'><h3>Borrow one proven pattern on purpose</h3><p>You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.</p><ul><li>Read the strongest pattern from obra/superpowers.</li><li>Decide whether to borrow method, structure, execution, or portability, but only one of them first.</li><li>Record what you will not borrow so the package stays light.</li></ul><div class='minor'>Unlocks: A cleaner package shape with less accidental over-design.</div></div><div class='direction-card'><h3>Harden portability semantics</h3><p>The skill already signals reuse across environments, so contract clarity matters early.</p><ul><li>Confirm activation mode, execution context, and trust assumptions.</li><li>Add or review degradation strategy for non-native targets.</li><li>Package the skill once to verify adapter expectations.</li></ul><div class='minor'>Unlocks: Safer cross-environment reuse with less target drift.</div></div><div class='direction-card'><h3>Create an iteration evidence loop</h3><p>The package should show what changed and why after the first draft.</p><ul><li>Generate the HTML skill report and keep it aligned with the package.</li><li>Record reference scan choices and non-goals.</li><li>Capture the next iteration choice explicitly before adding more files.</li></ul><div class='minor'>Unlocks: A clearer path for the next author or reviewer.</div></div></div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Recent feedback</h2>
|
|
<ul><li>No lightweight feedback captured yet. Use `yao.py feedback` to record quick review notes.</li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Promotion status</h2>
|
|
<div class='baseline-box'><p><strong>Promote:</strong> 0</p><p><strong>Keep current:</strong> 3</p><p><strong>Blocked:</strong> 0</p></div>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Package map</h2>
|
|
<ul><li><strong>SKILL.md</strong> — Skill entrypoint</li><li><strong>README.md</strong> — Human-readable usage guide</li><li><strong>agents/interface.yaml</strong> — Neutral interface metadata</li><li><strong>manifest.json</strong> — Lifecycle and portability metadata</li><li><strong>references</strong> — Extended guidance and reusable notes</li><li><strong>scripts</strong> — Deterministic helpers or local tooling</li><li><strong>evals</strong> — Trigger and quality checks</li><li><strong>reports</strong> — Generated evidence and overview artifacts</li></ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>First-pass review frame</h2>
|
|
<ul>
|
|
<li>Does the trigger stay narrow enough for the intended job?</li>
|
|
<li>Does the archetype match the real reuse level?</li>
|
|
<li>Are we adding structure faster than we are adding reliability?</li>
|
|
<li>Should the next step be trigger tightening, execution assets, or portability hardening?</li>
|
|
</ul>
|
|
</div>
|
|
</section>
|
|
|
|
<section class="grid">
|
|
<div class="panel">
|
|
<h2>Authoring discipline</h2>
|
|
<ul>
|
|
<li>Name unresolved assumptions before deepening the package.</li>
|
|
<li>Keep the package no larger than the recurring job requires.</li>
|
|
<li>Touch only files that directly support the requested change.</li>
|
|
<li>Tie every meaningful new artifact to a check or reviewer note.</li>
|
|
</ul>
|
|
</div>
|
|
<div class="panel">
|
|
<h2>Reviewer guardrails</h2>
|
|
<ul>
|
|
<li>Block speculative features that are not backed by real workflow variation.</li>
|
|
<li>Move unverifiable ideas into next-step candidates instead of baseline structure.</li>
|
|
<li>Reject decorative folders, reports, or governance that do not reduce risk.</li>
|
|
<li>Ask for one high-leverage clarification when job, output, or exclusion is still fuzzy.</li>
|
|
</ul>
|
|
</div>
|
|
</section>
|
|
</div>
|
|
</body>
|
|
</html>
|