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 Search Positioning
Invoke as $youtube-search-positioning.
Report-First Approval Gate
Default to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.
Do not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write/update/fix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research/report writes.
When stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. 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.
Identify the next search-led topic opportunities by connecting channel evidence, peer coverage, and YouTube query result competition.
Inputs
research/youtube/channel-audit-<slug>.mdresearch/youtube/peer-benchmark-<slug>.mdresearch/youtube/data/<slug>/videos-*.jsonl- Optional seed keywords from the user, titles, transcripts, descriptions, or peer top videos.
Workflow
- Require a channel slug, handle, or channel audit path.
- Ensure channel audit and peer benchmark evidence exists when peers are part of the strategy question.
- Build a seed keyword set from top-performing titles, recurring transcript topics, channel positioning, peer breakout videos, and explicit user keywords.
- For each keyword/query, search YouTube manually or through available local tooling. Record query text, retrieval date, top result titles, channels, upload dates, view counts when visible, and whether the target channel appears.
- Classify each query by demand signal, competition strength, recency window, creator fit, and production feasibility.
- Identify underserved queries where demand is visible but top results are stale, shallow, off-position, or weakly packaged.
- Write
research/youtube/search-positioning-<slug>.md.
Create the research/youtube/ directory if it does not exist.
Report Sections
- Evidence coverage: query count, search date, geography/account caveats, and unavailable metrics.
- Current search footprint: queries the channel already ranks for or plausibly owns.
- Keyword opportunity table: query, demand signal, competition level, top-result quality, fit, and priority.
- Closing windows: topics where larger peers have entered or ranking opportunity is likely declining.
- Underserved opportunities: demand-backed topics with few strong results.
- Topic recommendations: next videos or series candidates, each tied to search evidence and channel fit.
- Risks and caveats: personalization, regional variance, stale result pages, and metric availability.
- Strategic search-positioning recommendation.
Constraints
- Use exact query strings and cite evidence paths or search notes.
- Do not present YouTube search rank as stable; date every ranking observation.
- Do not infer demand from intuition alone. Mark weak signals as weak.
- Prefer differentiated topic angles over direct imitation of peer winners.
- Route prioritized topics into
$content-programming or $series-spec.
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-Skill Routing
After writing the artifact, recommend the next contextual creator-media skill in the final response as Recommended next skill: <command>.
Default recommendation: $youtube-cadence-diagnosis.
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 $creator-metrics-review when metrics evidence exists, otherwise recommend the default successor and explain the missing artifact.
Alignment Page
When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following ALIGNMENT-PAGE.md in this skill's directory. Output: alignment/youtube-search-positioning-{topic}.html.
1---2name: youtube-search-positioning-33description: Find YouTube search opportunities by comparing channel topics against query demand, ranking competition, and underserved results4---5
6## Pack Availability Guard
7
8Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `$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.
9
10# YouTube Search Positioning
11
12Invoke as `$youtube-search-positioning`.
13
14## Report-First Approval Gate
15
16Default to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.
17
18Do not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write/update/fix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research/report writes.
19
20When stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. 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.
21
22Identify the next search-led topic opportunities by connecting channel evidence, peer coverage, and YouTube query result competition.
23
24## Inputs
25
26- `research/youtube/channel-audit-<slug>.md`
27- `research/youtube/peer-benchmark-<slug>.md`
28- `research/youtube/data/<slug>/videos-*.jsonl`
29- Optional seed keywords from the user, titles, transcripts, descriptions, or peer top videos.
30
31## Workflow
32
331. Require a channel slug, handle, or channel audit path.
342. Ensure channel audit and peer benchmark evidence exists when peers are part of the strategy question.
353. Build a seed keyword set from top-performing titles, recurring transcript topics, channel positioning, peer breakout videos, and explicit user keywords.
364. For each keyword/query, search YouTube manually or through available local tooling. Record query text, retrieval date, top result titles, channels, upload dates, view counts when visible, and whether the target channel appears.
375. Classify each query by demand signal, competition strength, recency window, creator fit, and production feasibility.
386. Identify underserved queries where demand is visible but top results are stale, shallow, off-position, or weakly packaged.
397. Write `research/youtube/search-positioning-<slug>.md`.
40
41Create the `research/youtube/` directory if it does not exist.
42
43## Report Sections
44
45- Evidence coverage: query count, search date, geography/account caveats, and unavailable metrics.
46- Current search footprint: queries the channel already ranks for or plausibly owns.
47- Keyword opportunity table: query, demand signal, competition level, top-result quality, fit, and priority.
48- Closing windows: topics where larger peers have entered or ranking opportunity is likely declining.
49- Underserved opportunities: demand-backed topics with few strong results.
50- Topic recommendations: next videos or series candidates, each tied to search evidence and channel fit.
51- Risks and caveats: personalization, regional variance, stale result pages, and metric availability.
52- Strategic search-positioning recommendation.
53
54## Constraints
55
56- Use exact query strings and cite evidence paths or search notes.
57- Do not present YouTube search rank as stable; date every ranking observation.
58- Do not infer demand from intuition alone. Mark weak signals as weak.
59- Prefer differentiated topic angles over direct imitation of peer winners.
60- Route prioritized topics into `$content-programming` or `$series-spec`.
61
62## Approved Artifact Handoff
63
64After an approved synthesized write, explicit write/update mode, or any direct artifact mutation:
65
66- List every created or updated synthesized artifact path in the final response.
67- State the verification performed, such as readback, schema/check command, or why no executable verification applies for a Markdown-only strategy artifact.
68- 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.
69- Do not imply the research workflow is complete while approved artifacts remain untracked or uncommitted unless the user explicitly asked not to ship.
70- If stopping for approval before writing, the approval request remains the next action; do not include downstream routing.
71
72## Intent-Aware Routing
73
74Before applying the default `## Next-Skill Routing` sequence, classify the user's immediate intent and route to the missing action that best serves that intent:
75
76- Strategy refresh: recommend the missing or stale positioning, programming, portfolio, metrics, or product-media artifact.
77- Recording prep: recommend the missing series spec, script, build proof, walkthrough guide, or validation artifact needed before recording.
78- Upload prep: recommend packaging, title/thumbnail, description, chapters, or final metadata work before broader strategy work.
79- Performance review: recommend metrics, cadence, portfolio, peer benchmark, or owner-analytics export work before new content planning.
80- Owner analytics or private/manual platform evidence: route to an explicit manual/guide handoff instead of inventing unavailable metrics.
81- Dirty intended artifacts: route to shipping/commit/handoff first, not another creator strategy skill.
82
83Use the default next-skill sequence only when no stronger user intent, missing artifact, manual blocker, or dirty-artifact handoff applies.
84
85## Next-Skill Routing
86
87After writing the artifact, recommend the next contextual creator-media skill in the final response as `Recommended next skill: <command>`.
88
89Default recommendation: `$youtube-cadence-diagnosis`.
90
91If the default successor already exists and is current, recommend the first missing or stale downstream creator-media artifact in this order:
92
93`$youtube-channel-audit` -> `$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`
94
95If 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.
96
97## Alignment Page
98
99When 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-search-positioning-{topic}.html`.
GeorgeQLe