skillpacks 0.1.1 → 0.1.2

package/packs/youtube-ops/codex/youtube-audit/archive/v0.5/SKILL.md

@@ -0,0 +1,356 @@
+---
+name: youtube-audit
+description: Analyze a YouTube channel with evidence-first metadata, transcripts, performance fields, portfolio shape, and repeated content-quality patterns
+type: research
+version: v0.5
+argument-hint: "<channel URL or handle> [--count N]"
+interview_depth: none
+---
+
+# YouTube Audit — Evidence-First Channel Analysis
+
+Invoke as `$youtube-audit`.
+
+## Report-First Approval Gate
+
+Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.
+
+Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.
+
+After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.
+
+Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+## Staged Research Workflow
+
+Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
+
+1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled YAML approval of the research scope. Do not perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+3. **Stage 3 - Finalize approved artifacts.** Consume final compiled YAML for artifact approval only when it has no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths below, and convert the alignment page to `confirmed` with the approval record preserved.
+
+Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.
+
+## Evidence And Feedback Handling
+
+Treat user feedback as input to evaluate, not as automatic ground truth.
+
+- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
+- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
+- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Prerequisites
+
+Two CLI tools are required. Neither needs API keys.
+
+- **yt-dlp**: Lists channel videos as JSON. Install: `brew install yt-dlp` or `pip install yt-dlp`.
+- **youtube-transcript-api**: Fetches transcripts via Python. If the active Python is externally managed, such as Homebrew Python on macOS under PEP 668, install this package in a project-local virtual environment instead of the system Python.
+
+Check `yt-dlp` before proceeding. The transcript dependency should be handled through a project-local `.venv` when it is missing.
+
+## Process
+
+### 1. Parse Arguments
+
+- `$ARGUMENTS` must contain a YouTube channel URL or handle (e.g. `@handle`).
+- Optional `--count N` sets how many recent videos to fetch (default 20, max 50).
+- If no channel is provided, ask the user for one and stop.
+- Normalize handles to channel video URLs when needed: `@handle` -> `https://www.youtube.com/@handle/videos`.
+- Validate that `yt-dlp` is available first:
+
+```bash
+command -v yt-dlp
+```
+
+- Select the Python interpreter for transcript fetching. Prefer a workspace-local virtual environment when present; if one is not present, create it before checking the transcript import:
+
+```bash
+if [ ! -x .venv/bin/python ]; then
+  python3 -m venv .venv
+fi
+TRANSCRIPT_PYTHON=.venv/bin/python
+"$TRANSCRIPT_PYTHON" -c "from youtube_transcript_api import YouTubeTranscriptApi; print('ok')"
+```
+
+- If the import check fails, install the missing package into the project-local virtual environment, then rerun the import check:
+
+```bash
+.venv/bin/python -m pip install youtube-transcript-api
+"$TRANSCRIPT_PYTHON" -c "from youtube_transcript_api import YouTubeTranscriptApi; print('ok')"
+```
+
+- Store the selected interpreter path and use it for every transcript-fetching command in this audit.
+- If package installation fails because network access is unavailable or denied, stop and report the exact safe install commands below:
+
+```bash
+python3 -m venv .venv
+.venv/bin/python -m pip install youtube-transcript-api
+```
+
+Do not recommend installing `youtube-transcript-api` into Homebrew/system Python with `python3 -m pip install ...`, and do not recommend `--break-system-packages`. The local-venv path avoids PEP 668 `externally-managed-environment` failures on Homebrew Python.
+
+### 2. Archive Previous Audit
+
+If `research/youtube/youtube-audit-*.md` or legacy `research/youtube-audit-*.md` already exists for the same channel (check the `> Channel:` header in existing files):
+
+1. Copy the existing file to `docs/history/archive/YYYY-MM-DD/HHMMSS/research/youtube-audit-*.md`.
+2. Preserve the archived snapshot exactly.
+3. Then proceed to overwrite the canonical path.
+
+New files do not need archive snapshots.
+
+### 3. Fetch Video List
+
+Create:
+
+```text
+research/youtube/data/<slug>/
+```
+
+Run full metadata export, not flat playlist metadata:
+
+```bash
+yt-dlp --dump-json --playlist-end N "CHANNEL_URL/videos"
+```
+
+Persist the raw newline-delimited response exactly to:
+
+```text
+research/youtube/data/<slug>/videos-YYYY-MM-DD.jsonl
+```
+
+Parse each JSON object for at least:
+
+| Field | Notes |
+| --- | --- |
+| `id`, `webpage_url`, `title`, `description` | Identity and audit links |
+| `channel`, `channel_id`, `uploader`, `uploader_id` | Channel identity |
+| `upload_date`, `timestamp` | Used for recency and views/day |
+| `duration` | Used for views/minute |
+| `view_count`, `like_count`, `comment_count` | Performance |
+| `tags`, `categories`, `chapters` | Positioning and packaging signals |
+| `thumbnail`, `thumbnails` | Packaging review signal |
+
+Build a video table sorted by upload date (newest first). Report total videos found.
+
+### 4. Fetch Transcripts
+
+Use the same Python interpreter that passed the import check. If `.venv/bin/python` exists and passed the import check, run transcript fetching with `.venv/bin/python`; otherwise use the Python executable that passed the import check. Fetch transcripts sequentially and persist raw transcript JSON:
+
+```python
+from youtube_transcript_api import YouTubeTranscriptApi
+from pathlib import Path
+import json, sys, time
+
+video_ids = json.loads(sys.argv[1])
+out_dir = Path(sys.argv[2])
+out_dir.mkdir(parents=True, exist_ok=True)
+results = {}
+errors = []
+
+for vid in video_ids:
+    try:
+        transcript = YouTubeTranscriptApi.get_transcript(vid)
+        (out_dir / f"{vid}.json").write_text(json.dumps(transcript, ensure_ascii=False, indent=2))
+        results[vid] = " ".join(entry["text"] for entry in transcript)
+    except Exception as e:
+        errors.append({"id": vid, "reason": str(e)})
+    time.sleep(1.5)
+
+summary = {"transcripts": results, "errors": errors}
+(out_dir / "transcripts-summary.json").write_text(json.dumps(summary, ensure_ascii=False, indent=2))
+json.dump(summary, sys.stdout)
+```
+
+- Fetch sequentially with 1.5s delay to avoid rate limiting.
+- Skip videos without transcripts and log the reason.
+- If more than 80% lack transcripts, warn the user and ask whether to proceed.
+- Do not fabricate transcript text; transcript gaps are evidence quality limits.
+
+### 5. Prepare Analysis Context
+
+Build structured records per video:
+
+| Field | Computation |
+| --- | --- |
+| Title, date, URL, duration, views, likes, comments | Direct from metadata |
+| Age in days | From upload date to current date |
+| Views/day | `view_count / max(age_days, 1)` |
+| Views/minute | `view_count / max(duration_minutes, 1)` |
+| Like rate | `like_count / view_count` when both exist |
+| Transcript coverage | `yes`, `no`, or `partial` |
+| Archetype | Format pattern such as founder update, interview, tutorial, analysis, vlog, launch, reaction, teardown |
+| Content role | Strategic role such as acquisition, trust-building, proof, education, launch support, community retention, cleanup candidate |
+
+If total transcript text exceeds 80,000 words, truncate each transcript to preserve:
+- First 500 words (hook and intro)
+- Last 300 words (outro and CTA)
+- Trim the middle proportionally across all videos to fit the budget
+
+### 6. Analyze Content
+
+Analyze performance and content in one pass.
+
+### Performance And Portfolio Fields
+
+Include:
+
+- Total videos analyzed, transcript coverage, total views, median views, top video, bottom video.
+- Views/day and views/minute leaders.
+- Top-video concentration: top 1, top 3, and top 5 share of analyzed views.
+- Portfolio distribution by archetype and content role.
+- Packaging signals from titles, thumbnails, tags, descriptions, and chapters.
+- Cleanup candidates: videos with poor fit, weak performance relative to channel median, stale positioning, or inconsistent audience promise. Mark as `keep`, `refresh`, `unlist/private candidate`, or `needs human review`; do not recommend deletion as an automated action.
+
+### Content Quality Patterns
+
+Split into positive patterns (double down) and critical patterns (fix).
+
+**Every finding must cite evidence from 2+ videos to qualify as a pattern.** Single-video observations are not patterns — discard them.
+
+Analyze across these dimensions:
+
+| Dimension | What to look for |
+| --- | --- |
+| Positioning | Who is this channel for? Is it consistent? Does the creator own a niche? |
+| Hooks | First 30 seconds — do they create curiosity, state a problem, or waste time? |
+| Interview style | If applicable — question quality, follow-ups, guest chemistry, interruptions |
+| Credibility | Does the creator demonstrate expertise? Name-drop experiences? Show receipts? |
+| Topic selection | Are topics timely, evergreen, niche, or scattered? Do they match the audience? |
+| Pacing | Does the content drag or rush? Are there dead zones? |
+| Editing signals | Verbal cues for cuts, chapters, graphics. Does the script feel edited or rambling? |
+| Startup rigor | If startup/business content — are frameworks used? Is advice actionable or generic? |
+| Audience trust | Does the creator build trust or erode it? Sponsorship handling, honesty, consistency |
+| Portfolio fit | Does each video serve a clear role in the channel strategy? |
+| Packaging | Do title, thumbnail, topic, and opening promise align? |
+
+### 7. Write Report
+
+Save to `research/youtube/youtube-audit-<slug>-YYYY-MM-DD.md`:
+
+```markdown
+# YouTube Audit — [Channel Name]
+
+> Channel: [URL]
+> Videos analyzed: N
+> Transcripts available: N of M
+> Date: YYYY-MM-DD
+> Raw metadata: research/youtube/data/<slug>/videos-YYYY-MM-DD.jsonl
+> Raw transcripts: research/youtube/data/<slug>/transcripts/
+
+## Videos Analyzed
+
+| # | Title | Date | Views | Likes | Views/day | Views/min | Duration | Archetype | Role | Transcript |
+|---|-------|------|-------|-------|-----------|-----------|----------|-----------|------|------------|
+| 1 | [Title](URL) | YYYY-MM-DD | N | N | N | N | Xm | [type] | [role] | Yes/No |
+| ... | | | | | |
+
+## Performance Snapshot
+
+- **Total views analyzed**: N
+- **Median views**: N
+- **Top 1 concentration**: N%
+- **Top 3 concentration**: N%
+- **Views/day leader**: [video]
+- **Views/minute leader**: [video]
+
+## Portfolio Shape
+
+| Archetype | Videos | View share | Notes |
+|---|---:|---:|---|
+| ... | | | |
+
+| Content role | Videos | View share | Notes |
+|---|---:|---:|---|
+| ... | | | |
+
+## Positive Patterns (Double Down)
+
+### [Pattern Title]
+- **Frequency**: Found in N of M videos
+- **Evidence**: [Video 1 title] — "[quote or description]"; [Video 2 title] — "[quote or description]"
+- **Recommendation**: [What to keep doing or amplify]
+
+### ...
+
+## Critical Patterns (Fix)
+
+### [Pattern Title]
+- **Severity**: High / Medium / Low
+- **Frequency**: Found in N of M videos
+- **Evidence**: [Video 1 title] — "[quote or description]"; [Video 2 title] — "[quote or description]"
+- **Impact**: [Why this hurts the channel]
+- **Recommendation**: [Specific fix]
+
+### ...
+
+## Cleanup Candidates
+
+| Video | Recommendation | Evidence | Human check |
+|---|---|---|---|
+| [Title](URL) | Keep / Refresh / Unlist-private candidate / Needs human review | [performance + fit evidence] | [what to inspect before action] |
+
+## Summary
+
+### Top 3 Strengths
+1. [Strength] — [one-line why]
+2. [Strength] — [one-line why]
+3. [Strength] — [one-line why]
+
+### Top 3 Weaknesses
+1. [Weakness] — [one-line why]
+2. [Weakness] — [one-line why]
+3. [Weakness] — [one-line why]
+
+### Strategic Recommendation
+[2-3 sentences: the single most impactful change the channel should make, grounded in the patterns found]
+```
+
+Create the `research/youtube/` and `research/youtube/data/<slug>/` directories if they do not exist.
+
+### 8. Summarize In Thread
+
+After saving the report, output: top 3 strengths, top 3 weaknesses, performance/portfolio headline, strategic recommendation, report path, and raw data paths.
+
+## Constraints
+
+- **Pattern-only reporting**: Every finding must have evidence from 2+ videos. No single-video observations.
+- **Sequential fetching**: Do not parallelize transcript fetches — use 1.5s delay to avoid IP rate limiting.
+- **No API keys**: Both tools work unauthenticated against public data. Do not ask the user for API keys.
+- **Smart truncation**: When truncating, always preserve hooks (first 500 words) and outros (last 300 words).
+- **Honest coverage**: If transcripts are sparse, say so. Do not fabricate transcript content or hallucinate quotes.
+- **Raw evidence first**: Always persist raw `yt-dlp` JSONL and transcript JSON before writing analysis.
+- **No automated destructive content advice**: Cleanup candidates are review recommendations, not instructions to delete content.
+- **Stay in analysis mode**: Do not propose video ideas, scripts, or content calendars. The job is to audit what exists.
+
+## Approved Artifact Handoff
+
+After an approved synthesized write, explicit write/update mode, or any direct artifact mutation:
+
+- List every created or updated synthesized artifact path in the final response.
+- State the verification performed, such as readback, schema/check command, or why no executable verification applies for a Markdown-only strategy artifact.
+- Check and report the relevant git status for intended artifacts when the project is a git repository. If intended artifacts are modified or untracked, make the next action shipping, committing, or an explicit dirty-artifact handoff before recommending downstream strategy work.
+- Do not imply the research workflow is complete while approved artifacts remain untracked or uncommitted unless the user explicitly asked not to ship.
+- If stopping for approval before writing, the approval request remains the next action; do not include downstream routing.
+
+## Intent-Aware Routing
+
+Before applying the default next-step routing, classify the user's immediate intent and route to the missing action that best serves that intent:
+
+- Strategy refresh: recommend the missing or stale positioning, programming, portfolio, metrics, or product-media artifact.
+- Recording prep: recommend the missing series spec, script, build proof, walkthrough guide, or validation artifact needed before recording.
+- Upload prep: recommend packaging, title/thumbnail, description, chapters, or final metadata work before broader strategy work.
+- Performance review: recommend metrics, cadence, portfolio, peer benchmark, or owner-analytics export work before new content planning.
+- Owner analytics or private/manual platform evidence: route to an explicit manual/guide handoff instead of inventing unavailable metrics.
+- Dirty intended artifacts: route to shipping/commit/handoff first, not another creator strategy skill.
+
+Use the default next-skill sequence only when no stronger user intent, missing artifact, manual blocker, or dirty-artifact handoff applies.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/youtube-audit-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/youtube-ops/codex/youtube-cadence-diagnosis/ALIGNMENT-PAGE.md

@@ -9,6 +9,8 @@ When this skill produces durable deliverables (research, specs, plans, reports,
 
 The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected by the upgrade script). The bundled ALIGNMENT-PAGE.md receives tier-appropriate rendering guidance from the generator.
 
+**Context intake.** This skill declares `context_intake: artifact_only` (Artifact-driven). Work from concrete artifacts, data, logs, or existing instructions by default; ask concise clarification questions only when the available artifacts are missing, contradictory, or unsafe to interpret.
+
 **Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, local section-feedback YAML only after a section feedback choice is selected, and one bottom `Compile Responses` control. `confirmed` is the post-approval page after the agent has consumed final compiled response YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
 
 **Central alignment index.** When a research-producing skill writes or updates an HTML alignment page, also maintain the repository's central alignment index. Look for `alignment/index.html` at the repository root; if the target repo documents a different central alignment-index path, use that path and report it. If the index does not exist, create it as a self-contained HTML page that works from `file://`, links to every active `alignment/*.html` page except itself, and includes the newly written page. Every index entry must include the page's alignment date in a muted meta span after the link, formatted `YYYY-MM-DD`, for example `<a href="page.html">Title</a> <span class="meta">2026-06-09</span>`. The alignment date is the review or confirmed date written inside the page itself; new pages use today's date. If the index exists, update it instead of blindly appending: preserve valid existing entries, metadata, and entry dates; remove duplicate entries for the same page path; keep links repo-relative; and include the new or updated page. When updating an existing index, add a date only to entries that are missing one, deriving it from the page's internal alignment date, or from file history when the page has no internal date. If a `new` marker is used, combine it with the date as `<span class="meta">new · YYYY-MM-DD</span>`, and remove stale `new` markers from entries that are no longer the latest addition.
@@ -57,7 +59,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-youtube-cadence-diagnosis-research.md`; product-path mode uses `research/{slug}/_working/preliminary-youtube-cadence-diagnosis-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-youtube-cadence-diagnosis-research.md`; product-path mode uses `research/{slug}/_working/preliminary-youtube-cadence-diagnosis-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Visual tier rendering.** This skill's alignment page uses the `visual` tier. Inline charts and diagrams are rendered via self-contained Canvas/SVG within the HTML file. Use the alignment chart snippet library (`scripts/alignment-chart-snippets.js`) as reference — copy needed chart functions directly into the page's `<script>` block. Charts must read CSS variables (`--chart-1` through `--chart-8`) for the data visualization palette. Every chart must include a `<table>` fallback, `aria-label` on canvas/SVG, and a "View as table" toggle. Data is embedded as inline JSON — no external fetches.
 

package/packs/youtube-ops/codex/youtube-cadence-diagnosis/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.6 - 2026-06-12
+
+- Clarified staged research review pages must render complete working-packet substance as structured HTML UI, with raw Markdown packet text allowed only as a supplemental source view.
+
+## v0.5 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.4 - 2026-06-10
 
 - Changed report-first research flow to require alignment-page research-scope approval before synthesized findings, candidate rankings, recommendations, working packets, or canonical research writes.

package/packs/youtube-ops/codex/youtube-cadence-diagnosis/SKILL.md

@@ -2,15 +2,15 @@
 name: youtube-cadence-diagnosis
 description: Diagnose YouTube publishing cadence, gaps, streaks, and post-gap performance effects against channel and peer evidence
 type: research
-version: v0.4
+version: v0.6
 argument-hint: "<channel slug or handle> [--peer <channel>...] [--count N]"
-interview_depth: none
+context_intake: artifact_only
 visual_tier: visual
 ---
 
 ## Pack Availability Guard
 
-Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `$pack install <pack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `npx skillpacks install <pack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # YouTube Cadence Diagnosis
 
@@ -31,7 +31,7 @@ Do not include `Recommended next skill`, `Recommended next command`, or downstre
 Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
 
 1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled YAML approval of the research scope. Do not perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
-2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
 3. **Stage 3 - Finalize approved artifacts.** Consume final compiled YAML for artifact approval only when it has no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths below, and convert the alignment page to `confirmed` with the approval record preserved.
 
 Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.

package/packs/youtube-ops/codex/youtube-cadence-diagnosis/archive/v0.4/SKILL.md

@@ -0,0 +1,128 @@
+---
+name: youtube-cadence-diagnosis
+description: Diagnose YouTube publishing cadence, gaps, streaks, and post-gap performance effects against channel and peer evidence
+type: research
+version: v0.4
+argument-hint: "<channel slug or handle> [--peer <channel>...] [--count N]"
+interview_depth: none
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `$pack install <pack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# YouTube Cadence Diagnosis
+
+Invoke as `$youtube-cadence-diagnosis`.
+
+## Report-First Approval Gate
+
+Default to scope-first approval: before synthesized research, inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions in a `review` alignment page plus a concise conversation summary.
+
+Do not perform synthesized research, rank candidates, make recommendations, or write working packets or canonical deliverables until final compiled YAML approves the research scope. Minimal pre-approval discovery may identify available files, source categories, and open questions; label it as scope evidence, not findings.
+
+After approved research-scope YAML, perform the research and write only the non-canonical working packet defined in the staged workflow. Then update the `review` alignment page with findings and stop again for feedback-only YAML or final compiled YAML artifact approval before creating or updating canonical research, spec, or task files.
+
+Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.
+
+## Staged Research Workflow
+
+Use this staged workflow for synthesized research or report outputs that would create or update canonical research, spec, or task files.
+
+1. **Stage 1 - Scope discovery and approval.** Inspect only enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` HTML alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled YAML approval of the research scope. Do not perform synthesized research, rank candidates, make recommendations, or write working packets, canonical research, spec, or task files in Stage 1.
+2. **Stage 2 - Research and artifact review.** Only after approved research-scope YAML with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback, perform the synthesized research, run required source/code checks, and write only a non-canonical working packet: flat mode uses `research/_working/preliminary-<skill>-research.md`; product-path mode uses `research/{slug}/_working/preliminary-<skill>-research.md`. Replace `<skill>` with this skill's `name` value. Raw evidence or search logs may remain as supporting evidence where this skill already requires them, but synthesized deliverables stay in the working packet. Update the `review` HTML alignment page with the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Stop for either feedback-only YAML or final compiled YAML. Feedback-only YAML revises the working packet and page, then remains in Stage 2.
+3. **Stage 3 - Finalize approved artifacts.** Consume final compiled YAML for artifact approval only when it has no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths below, and convert the alignment page to `confirmed` with the approval record preserved.
+
+Canonical output paths remain unchanged. Search logs and other supporting evidence remain allowed only where this skill's output contract already requires them.
+
+## Evidence And Feedback Handling
+
+Treat user feedback as input to evaluate, not as automatic ground truth.
+
+- For factual, evidentiary, technical, or source-backed claims: verify against available evidence. If the user appears to misunderstand the evidence or states something factually incorrect, push back clearly and cite the evidence. Do not rewrite findings merely to agree.
+- For taste, brand, positioning preference, risk appetite, prioritization, or other subjective judgment calls: weigh user feedback heavily and adapt the recommendation unless it conflicts with verified evidence.
+- When feedback mixes facts and preference, separate them explicitly: correct the factual part, then incorporate the preference where it is a legitimate judgment call.
+- When uncertain, say what is known, what is inferred, and what would change the conclusion.
+
+## Inputs
+
+- `research/youtube/channel-audit-<slug>.md`
+- `research/youtube/data/<slug>/videos-*.jsonl`
+- Optional `research/youtube/peer-benchmark-<slug>.md`
+- Optional peer raw metadata under `research/youtube/data/<peer-slug>/`
+
+## Process
+
+1. Require a channel slug, handle, or channel audit path.
+2. Ensure raw upload metadata exists. If not, run `$youtube-channel-audit <channel> [--count N]`.
+3. Parse publish dates, views, views/day, content roles, and video archetypes from raw metadata.
+4. Compute upload intervals, streaks, longest gaps, rolling 30/60/90-day publish counts, and current streak status.
+5. Compare pre-gap and post-gap performance while controlling for topic, video age, and outlier videos where the evidence allows it.
+6. Compare cadence against stage-matched peers when peer metadata exists.
+7. Decide whether the data points to frequency, topic selection, packaging, or production quality as the more likely bottleneck.
+8. Write `research/youtube/cadence-diagnosis-<slug>.md`.
+
+Create the `research/youtube/` directory if it does not exist.
+
+## Report Sections
+
+- Evidence coverage: videos analyzed, date range, peer coverage, and missing fields.
+- Upload timeline: chronological table with intervals, gaps, topics, roles, and views/day.
+- Cadence metrics: median interval, longest gaps, streaks, rolling publish counts, and current streak.
+- Gap analysis: pre-gap baseline, post-gap performance, outlier handling, and confidence level.
+- Peer cadence benchmark: publish frequency and consistency compared with comparable channels.
+- Bottleneck diagnosis: cadence vs topic vs packaging vs production constraints.
+- Practical cadence recommendation: minimum viable cadence, stretch cadence, batching options, and warning signs.
+- Strategic programming implication.
+
+## Constraints
+
+- Do not claim causation when the evidence only supports correlation.
+- Always name confounders such as topic mix, video age, search seasonality, and packaging changes.
+- Use exact dates and intervals.
+- Keep recommendations realistic for solo or small-team production unless evidence shows otherwise.
+- Route the resulting rhythm into `$content-programming`.
+
+## Approved Artifact Handoff
+
+After an approved synthesized write, explicit write/update mode, or any direct artifact mutation:
+
+- List every created or updated synthesized artifact path in the final response.
+- State the verification performed, such as readback, schema/check command, or why no executable verification applies for a Markdown-only strategy artifact.
+- Check and report the relevant git status for intended artifacts when the project is a git repository. If intended artifacts are modified or untracked, make the next action shipping, committing, or an explicit dirty-artifact handoff before recommending downstream strategy work.
+- Do not imply the research workflow is complete while approved artifacts remain untracked or uncommitted unless the user explicitly asked not to ship.
+- If stopping for approval before writing, the approval request remains the next action; do not include downstream routing.
+
+## Intent-Aware Routing
+
+Before applying the default `## Next-Skill Routing` sequence, classify the user's immediate intent and route to the missing action that best serves that intent:
+
+- Strategy refresh: recommend the missing or stale positioning, programming, portfolio, metrics, or product-media artifact.
+- Recording prep: recommend the missing series spec, script, build proof, walkthrough guide, or validation artifact needed before recording.
+- Upload prep: recommend packaging, title/thumbnail, description, chapters, or final metadata work before broader strategy work.
+- Performance review: recommend metrics, cadence, portfolio, peer benchmark, or owner-analytics export work before new content planning.
+- Owner analytics or private/manual platform evidence: route to an explicit manual/guide handoff instead of inventing unavailable metrics.
+- Dirty intended artifacts: route to shipping/commit/handoff first, not another creator strategy skill.
+
+Use the default next-skill sequence only when no stronger user intent, missing artifact, manual blocker, or dirty-artifact handoff applies.
+
+## Next-Step Routing
+
+After writing the artifact, recommend the next contextual creator-media skill in the final response as `Recommended next skill: <command>`.
+
+Default recommendation: `$creator-positioning`.
+
+If the default successor already exists and is current, recommend the first missing or stale downstream creator-media artifact in this order:
+
+`$youtube-channel-audit` -> `$youtube-video-audit` -> `$youtube-vid-research` -> `$youtube-concept-research` -> `$youtube-competitive-research` -> `$youtube-title-thumbnail-audit` -> `$youtube-description-optimizer` -> `$youtube-portfolio` -> `$youtube-peer-benchmark` -> `$youtube-search-positioning` -> `$youtube-cadence-diagnosis` -> `$creator-positioning` -> `$content-programming` -> `$series-spec` -> `$product-led-media-map` -> `$creator-metrics-review`
+
+If the sequence is ambiguous, multiple upstream artifacts are stale, or the recommendation depends on channel-level strategy vs programming-level changes, recommend `$creator-metrics-review` when metrics evidence exists, otherwise recommend the default successor and explain the missing artifact.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/youtube-cadence-diagnosis-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.