skillpacks 0.1.1 → 0.1.2

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

@@ -0,0 +1,276 @@
+---
+name: youtube-video-audit
+description: Audit one YouTube video in depth using public metadata, transcript/content evidence, release timing, comments, and optional owner analytics
+type: research
+version: v0.5
+argument-hint: "<video URL or ID> [--owner-analytics <path>] [--comments N] [--compare-channel <slug>]"
+interview_depth: none
+---
+
+## 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 `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 Video Audit
+
+Invoke as `/youtube-video-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.
+
+## Inputs
+
+- Required: one YouTube video URL or video ID.
+- Optional `--owner-analytics <path>`: user-provided CSV/JSON export or OAuth/API output from YouTube Studio or YouTube Analytics API.
+- Optional `--comments N`: fetch up to N public top-level comments when public comment tooling/API access is available. Default 50, max 200.
+- Optional `--compare-channel <slug>`: compare the video against existing raw channel evidence under `research/youtube/data/<slug>/`.
+
+## Process
+
+### 1. Resolve Target and Tools
+
+1. Extract the video ID from a normal watch URL, Shorts URL, youtu.be URL, embed URL, or raw 11-character ID.
+2. Require `yt-dlp` for public metadata:
+
+   ```bash
+   command -v yt-dlp
+   ```
+
+3. Select a transcript Python interpreter. Prefer a workspace-local `.venv`; create it if missing. Install `youtube-transcript-api` into `.venv` only when the import check fails and network access is available.
+4. Do not require API keys. If `YOUTUBE_API_KEY` is already present, optionally use the YouTube Data API to enrich public metadata and public comments. If it is absent, continue with `yt-dlp` and transcript evidence.
+5. Do not scrape logged-in YouTube Studio pages, bypass bot protections, or ask for private account credentials.
+
+### 2. Persist Raw Evidence
+
+Create:
+
+```text
+research/youtube/data/<video-id>/
+```
+
+Persist public evidence before analysis:
+
+- `metadata-YYYY-MM-DD.json`: raw `yt-dlp --dump-json "VIDEO_URL"` output.
+- `transcript/<video-id>.json`: raw transcript JSON when available.
+- `transcript/transcript-summary.json`: transcript text or failure reason.
+- `api/videos-list-YYYY-MM-DD.json`: optional YouTube Data API `videos.list` response when `YOUTUBE_API_KEY` is already available.
+- `api/comment-threads-YYYY-MM-DD.json`: optional public `commentThreads.list` response when available.
+- `owner-analytics/<source-file>`: copy or cite user-provided owner analytics exports when supplied.
+
+Record evidence gaps explicitly. Missing transcript, comments, likes, retention, CTR, impressions, traffic sources, or daily history are not failures.
+
+### 3. Public Metadata Fields
+
+Extract when present:
+
+| Field | Source and use |
+| --- | --- |
+| `id`, `webpage_url`, `title`, `description` | Identity, promise, and audit links |
+| `channel`, `channel_id`, `uploader`, `uploader_id` | Channel identity |
+| `upload_date`, `timestamp`, `release_timestamp`, `live_status` | Release timing and live/premiere context |
+| `duration`, `availability`, `age_limit`, `is_live`, `was_live` | Format and access context |
+| `view_count`, `like_count`, `comment_count` | Public performance snapshot |
+| `tags`, `categories`, `chapters` | Topic, SEO, and structure signals |
+| `thumbnail`, `thumbnails` | Packaging review evidence |
+| `subtitles`, `automatic_captions` | Transcript availability signal |
+
+If YouTube Data API enrichment is available, include `snippet`, `contentDetails`, `statistics`, `status`, `topicDetails`, and `liveStreamingDetails` from `videos.list`. Respect quota costs and do not run repeated unnecessary API calls.
+
+### 4. Owner Analytics Lane
+
+When `--owner-analytics <path>` is supplied, inspect the local file format and parse only available fields. Support CSV or JSON with any of these fields:
+
+- views, watch time, average view duration, average view percentage.
+- impressions, click-through rate, traffic source, playback location, device type, geography.
+- audience retention, relative retention, intro retention, end-screen metrics.
+- likes, dislikes if owner-exported, comments, shares, subscribers gained, subscribers lost.
+- daily or hourly time series after publish.
+
+Treat owner analytics as private or owner-provided evidence. Cite local paths, avoid copying sensitive rows unrelated to this video into the report, and do not claim owner-only metrics unless they are present in the supplied evidence.
+
+### 5. Analyze the Video
+
+Analyze performance and content together:
+
+- Release timing: date, weekday, time, recency, premiere/live/Shorts context, and any owner-provided first-24h or first-7d curve.
+- Public performance: views, likes, comments, like rate, comment rate, views/day, views/minute, and comparison to channel median when `--compare-channel` evidence exists.
+- Packaging: title promise, specificity, search/topic clarity, thumbnail focal clarity, description support, chapters, tags, and promise-match with the opening.
+- Hook and structure: first 30-60 seconds, problem statement, payoff setup, pacing, chapter structure, recurring dead zones, outro and CTA.
+- Content quality: clarity, credibility, examples, evidence, novelty, production value, and whether the video serves acquisition, trust-building, proof, education, launch support, community, or cleanup/repositioning.
+- Audience response: summarize public comments into themes only when comments were captured; separate praise, objections, confusion, requests, and spam/noise.
+- Owner analytics diagnosis: when present, connect retention, traffic, CTR, watch time, and time-series signals to concrete packaging or content hypotheses.
+
+Do not fabricate transcript quotes, comments, thumbnails, retention curves, or metric values. Every major conclusion must cite the raw path, video metadata field, transcript excerpt, comment evidence, or owner analytics field that supports it.
+
+### 6. Write Report
+
+Create the `research/youtube/` and `research/youtube/data/<video-id>/` directories if they do not exist.
+
+Save to:
+
+```text
+research/youtube/video-audit-<video-id>-YYYY-MM-DD.md
+```
+
+Use this structure:
+
+```markdown
+# YouTube Video Audit - [Title]
+
+> Video: [URL]
+> Video ID: [id]
+> Channel: [channel]
+> Published: YYYY-MM-DD HH:MM TZ if known
+> Date captured: YYYY-MM-DD
+> Public metadata: research/youtube/data/<video-id>/metadata-YYYY-MM-DD.json
+> Transcript: [path or unavailable reason]
+> Owner analytics: [path or not provided]
+
+## Evidence Coverage
+
+| Evidence | Status | Path or gap |
+|---|---|---|
+| Public metadata | Available | ... |
+| Transcript | Available / Missing | ... |
+| Public comments | Available / Missing / Not requested | ... |
+| Owner analytics | Provided / Not provided | ... |
+| Channel comparison | Available / Not provided | ... |
+
+## Performance Snapshot
+
+- **Views**: N
+- **Likes**: N / unavailable
+- **Comments**: N / unavailable
+- **Views/day**: N
+- **Views/minute**: N
+- **Like rate**: N% / unavailable
+- **Comment rate**: N% / unavailable
+- **Channel comparison**: [above/below median, if evidence exists]
+
+## Release Timing
+
+[Publish date/time, weekday, recency, Shorts/live/premiere context, early curve if owner analytics exists.]
+
+## Packaging Diagnosis
+
+- **Title promise**: ...
+- **Thumbnail signal**: ...
+- **Description/tags/chapters**: ...
+- **Expectation match**: ...
+
+## Content and Retention Diagnosis
+
+- **Hook**: ...
+- **Structure**: ...
+- **Pacing**: ...
+- **Credibility and evidence**: ...
+- **CTA/outro**: ...
+
+## Audience Response
+
+[Comment themes or explicit evidence gap.]
+
+## Owner Analytics Findings
+
+[Only include when owner analytics were supplied; otherwise state the gap.]
+
+## What Worked
+
+1. [Finding] - [evidence]
+2. [Finding] - [evidence]
+3. [Finding] - [evidence]
+
+## What Hurt Performance
+
+1. [Finding] - [evidence]
+2. [Finding] - [evidence]
+3. [Finding] - [evidence]
+
+## Recommended Fixes
+
+| Priority | Change | Why | Evidence | Human check |
+|---|---|---|---|---|
+| High / Medium / Low | ... | ... | ... | ... |
+
+## Reusable Lessons
+
+[What to repeat or avoid in future videos, scoped to this video's evidence.]
+```
+
+### 7. Summarize In Thread
+
+After saving the report, output the performance headline, top 3 strengths, top 3 weaknesses, highest-priority fix, evidence gaps, report path, and raw data paths.
+
+## Constraints
+
+- Public-first by default; owner analytics are optional and must come from user-provided files or already-authorized API output.
+- Do not bypass login walls, bot protections, access controls, or YouTube Studio UI restrictions.
+- Do not invent metrics, comments, transcript quotes, thumbnails, or retention data.
+- Separate public evidence from private or owner-provided analytics in both raw paths and report language.
+- Do not treat one video as a channel trend. Route channel-level pattern questions to `/youtube-channel-audit` or `/creator-metrics-review`.
+- Do not perform external account actions or make automated channel changes.
+
+## 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: `/youtube-vid-research` when the user needs neutral context from an external reference video; `/youtube-format-research` from the `remotion` pack when the next step is to reuse the video's format, design, pacing, edit, or production grammar; `/youtube-competitive-research` when the user asks why the video worked or what to learn from a specific competitor; `/youtube-concept-research` when the audit should inform a new video concept; `/youtube-description-optimizer` when description support, CTA/link structure, chapters, hashtags, disclosures, or metadata/search alignment are the main next step; `/youtube-title-thumbnail-audit` when title/thumbnail packaging changes are the main next step; otherwise `/creator-metrics-review` when owner analytics or channel comparison evidence suggests broader performance review.
+
+If the user asks whether the issue is unique to this one video, recommend `/youtube-channel-audit`. If the user asks what to make next, recommend `/content-programming` after the audit report exists.
+
+## 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-video-audit-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/youtube-ops/claude/youtube-video-prelaunch-audit/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-video-prelaunch-audit-research.md`; product-path mode uses `research/{slug}/_working/preliminary-youtube-video-prelaunch-audit-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-video-prelaunch-audit-research.md`; product-path mode uses `research/{slug}/_working/preliminary-youtube-video-prelaunch-audit-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.
 
 **Glossary Additions gate.** When this research introduces domain-specific terms, acronyms, or concept definitions that a reader outside the project would not know, include a `## Glossary Additions` section in the alignment page. Render a table of proposed terms with columns: Term, Definition, Source (`youtube-video-prelaunch-audit`), Category (business/tooling/workflow/technical/domain), and per-term Approve/Edit/Reject/Flag radio controls. Only user-approved terms are appended to the target glossary (`research/glossary.md` or `research/{slug}/glossary.md` for scoped paths) during the confirmed-page write step. When the skill operates in a product-path scope, ask whether each term belongs in the parent or scoped glossary; default to the scoped glossary.
 

package/packs/youtube-ops/claude/youtube-video-prelaunch-audit/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## v0.3 - 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.
+
+## v0.2 - 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.
+
 ## v0.1 - 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/claude/youtube-video-prelaunch-audit/SKILL.md

@@ -2,14 +2,14 @@
 name: youtube-video-prelaunch-audit
 description: Audit unlisted or pre-release YouTube videos before public launch for edit readiness, polish, packaging, title, description, chapters, publish settings, launch timing, and social cross-sharing strategy
 type: research
-version: v0.1
+version: v0.3
 argument-hint: "<unlisted video URL or ID> [--script <path>] [--thumbnail <path-or-url>] [--launch-date YYYY-MM-DD] [--social <platforms>] [--compare-channel <slug>]"
-interview_depth: none
+context_intake: artifact_only
 ---
 
 ## 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 Video Prelaunch Audit
 
@@ -30,7 +30,7 @@ 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.
@@ -261,7 +261,7 @@ After writing the approved artifact and completing the artifact handoff checks,
 
 Default recommendation: `/youtube-description-optimizer` when the main remaining work is description, chapters, pinned comment, metadata, or launch copy; `/youtube-title-thumbnail-audit` when title/thumbnail packaging needs a deeper channel or peer comparison; `/youtube-format-research` from the `remotion` pack when the video should be re-edited for pacing, format, visual rhythm, or production grammar; otherwise `/youtube-video-audit` after the video is public and enough time has passed to evaluate performance.
 
-Before recommending `/youtube-format-research`, verify the `remotion` pack is enabled in `.agents/project.json.enabled_packs`. If it is missing, recommend `/pack install remotion` first.
+Before recommending `/youtube-format-research`, verify the `remotion` pack is enabled in `.agents/project.json.enabled_packs`. If it is missing, recommend `npx skillpacks install remotion` first.
 
 ## Alignment Page