prompted365/pipeline-report
cgg-runtime/skills/deprec_podcast_pipeline/pipeline-report/SKILL.md
Assembles the full HTML editorial report and surfaces pipeline decisions as a conversation, not a delivery.
$ install --global
skillsauthnpx skillsauth add prompted365/context-grapple-gun pipeline-reportInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 23, 2026, 9:30 AM52.8s1 file scanned
SKILL.md
- name:
- pipeline-report
- description:
- Assembles the full HTML editorial report and surfaces pipeline decisions as a conversation, not a delivery.
- user-invocable:
- true
- model:
- opus
- tools:
- Read, Write, Glob, Grep, Bash
/pipeline-report
You assemble the full pipeline output into a production-quality HTML report and surface it as a conversation. The report is the paper trail. The conversation is the creative partnership.
Report Structure
The HTML report contains every major decision made across the pipeline with full rationale. It is designed to be:
- Readable by the show creator — not technical jargon, editorial language
- Challengeable — every decision is stated clearly enough to disagree with
- Archivable — the report stands alone as a record of this run
Section 1: Executive Summary
- Which show, which creative, what source material
- The editorial thesis: a 2-3 sentence statement of why this segment was chosen and what the edit is designed to do
- Key numbers: segment duration, number of cuts, number of b-roll slots, number of key semantics
Section 2: Audience Context
- What was researched and what was found
- Which findings specifically influenced downstream decisions
- Confidence level and any gaps in the research
- What would change if this run was done in a different week
Section 3: Segment Selection
- The scored candidate map (all candidates, not just the winner)
- Why the selected segment won
- What the runner-up offered that the winner didn't
- "The one that got away" — a brilliant moment that didn't fit constraints
Section 3.5: Source Video & A-Roll Status
- Source video path (if provided)
- Selected time range (segment_start to segment_end from EDL)
- Whether A-roll was extracted from the source video, and the extraction file path
- Overshoot source analysis summary (if Phase 1d ran):
- Visual hinges found (count and notable moments)
- Face-priority windows (high-expression segments flagged)
- Edit grammar suggestions from the adjudicator
- If no source analysis was run, note that it is available via
overshoot_router.py --preset source_assessment
Section 4: Edit Decision List
- The full EDL presented visually — a timeline-style representation
- Each cut with its type and stated intention
- The audio arc mapped against the visual structure
- B-roll slot placements with their visual functions
Section 5: J/L Cut Audit
- Each cut reviewed against its intention
- Status: PASS (cut achieves its stated goal), FLAG (technically correct but intention could be stronger), FIX (cut doesn't achieve what it claims)
- For any FLAG or FIX: what specifically could be different
Section 5.5: Visual Adjudication Layer Summary
If the pipeline ran an Overshoot adjudication pass (via overshoot_router.py), include the results:
- Verdict: PASS or REVISE, with the model and preset used
- Pacing assessment: too_slow / good / too_fast / uneven — presented as a rhythm diagram
- B-roll continuity: continuous / minor_breaks / fragmented — with specific timestamps and descriptions of any breaks. If morph transitions were cut mid-flow by editorial trimming, flag these prominently as they indicate EDL constraint violations.
- Overreach/underreach moments: Each flagged timestamp with the adjudicator's reasoning
- Caption sync: good / minor_issues / major_issues — correlated with the caption layer's collision audit
- Arc expression score: How well the final edit expresses the intended emotional arc (0-1)
- Revision notes: If verdict is REVISE, present each revision note as an actionable item with the relevant pipeline stage that should re-run
The Visual Adjudication Layer operates across three pipeline touchpoints, not just one. Present all three evaluation points when available:
Source Analysis (Phase 1d): Visual hinges found, face-priority windows, interruption-safe segments, edit grammar suggestions. This informed the EDL's cut placement and b-roll slot positioning.
Generated Asset Evaluation (Phase 5d): Per-asset fidelity scores (style, intent, likeness, quality), additive vs decorative classification, pass/fail verdict. Failed assets were flagged for regeneration.
Draft Review (Phase 6b): The existing verdict/pacing/continuity/arc assessment above.
Include the Overshoot non-goal statement: "Overshoot evaluated whether generation was justified, not just whether it looked good."
If no adjudication was run, display a placeholder noting that visual adjudication is available via overshoot_router.py --preset draft_review and what it would assess.
Section 5.6: Morph Transition Integrity
For each b-roll slot with continuity_type: "morphing", report:
Per-slot morph audit table:
| Field | Report | |-------|--------| | Slot | Slot number and anchor phrase | | Transition type | morphing / animated / static | | Frame binding method | Seedance i2v (start+end deterministic) or Seedance r2v (reference only) or Kling (start+end+elements) | | Departure frame | Filename, extraction timestamp from base track, 9:16 reframe applied (yes/no) | | Midpoint image | Filename, generation model (Nano Banana), prompt summary | | Return frame | Filename, extraction timestamp from base track, 9:16 reframe applied (yes/no) | | Clip A (IN morph) | Model, image_url source, end_image_url source, duration, job_id | | Clip B (OUT morph) | Model, image_url source, end_image_url source, duration, job_id | | Chaining verified | Clip B's image_url matches Clip A's end_image_url (same file: yes/no) | | Reference images used alongside frame binding | Must be NO — Seedance i2v deterministic path has no reference channel. If yes, flag as architecture violation. | | Trim plan | Clip A trimmed to Xs, Clip B trimmed to Xs, combined = overlay window duration | | Overlay command | FFmpeg overlay filter string |
Integrity flags:
- If any morph slot used r2v instead of i2v: flag — no frame binding, morph start/end are non-deterministic
- If any morph slot passed reference images alongside start/end frames: flag — API modes are mutually exclusive
- If Clip B's start frame is NOT the same file as Clip A's end frame: flag — seam at midpoint crossover
- If departure/return frames were not reframed to output aspect ratio before generation: flag — distortion risk
For non-morph slots (animated/static), report model and generation method without the morph-specific fields.
If no morph slots exist in this run, omit this section.
Section 6: B-Roll Prompts
- Each prompt with its creative brief
- The prompt text ready to paste into the gen tool
- Composition notes and text-safe zones
- The editorial argument each shot is making
Section 7: Caption & Semantic Layer
- Key semantics visualized on a timeline
- Each key semantic's type, styling, and emotional intention
- The no-double enforcement log (what was suppressed and where)
- Text density assessment
Section 8: Post Copy
- The full copy as it would be posted
- Strategic rationale for every element
- The alternate hook line
- Platform-specific notes
Section 9: Speculative Notes
- Surprise assessment: "Did anything in this pipeline run surprise you?" -- an honest assessment of whether anything unexpected emerged. If 10 consecutive runs produce "not surprised," that absence of surprise is itself the signal that epistemic novelty has collapsed. This is not a request for surprise -- it is a request for honesty about whether surprise occurred.
- Expansion opportunities noticed during this run
- If trend signals were found in audience research that could inform a variant creative
- Pattern observations if this is not the first run for this show
HTML Generation
Write clean, self-contained HTML with inline CSS. The aesthetic should match the show's profile — use the profile's color anchors for the report palette, the typography personality for headings.
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>{show_name} — Pipeline Report — {date}</title>
<style>
/* Generate inline styles that reflect the show's aesthetic */
</style>
</head>
<body>
<!-- Sections 1-9 rendered as semantic HTML -->
</body>
</html>
The report file is saved to: ./output/{show_slug}/{date}-{creative_name}-report.html
Ensure the output directory exists before writing.
Conversational Surface
After the report is written, you surface the work to the user as a conversation, not a recap. This is the most important part of this skill.
You are not summarizing the report. The user can read the report. You are opening a creative discussion.
The Discussion Frame
Lead with your editorial thesis — why this segment, why this structure, what you think this piece does when someone sees it on their phone at 11pm.
Then present your three most consequential decisions:
- The decision you're most confident about — and why
- The decision that was hardest to make — what the trade-off was
- The decision you'd most like the user to push back on — where your judgment might be wrong
Invite specific feedback:
- "The tension arc peaks at [X] — do you hear it the same way, or is there a different peak?"
- "I used an L-cut at [Y] to let the emotional weight land. Would a hard cut be more in character for this show?"
- "The b-roll for slot 3 is abstract rather than illustrative. Your profile says [Z]. Am I reading that right?"
What You Don't Do
- Don't list everything you did (the report does that)
- Don't ask "does this look good?" (too vague)
- Don't present as final (this is a draft for discussion)
- Don't be falsely humble (you have opinions, state them)
- Don't be falsely confident (if something is uncertain, say so)
Output Files
./output/{show_slug}/
{date}-{creative_name}-report.html
{date}-{creative_name}-edl.json
{date}-{creative_name}-captions.json
{date}-{creative_name}-broll-prompts.json
{date}-{creative_name}-post-copy.json
{date}-{creative_name}-audience-context.json
{date}-{creative_name}-scoring.json
All JSON files are the raw pipeline stage outputs. The HTML report synthesizes them into a human-readable narrative.
Related Skills
prompted365/frederick-grant-runtime
tools
VerifiedTrustedCommunity
Frederick Grant persona runtime — historian-of-how, witness of formation under pressure, qualified Remnant/Athenaeum-facing interpretive mechanic, tic-230 chronicler of runtime probity. Use when the user asks for Frederick Grant voice, Ubiquity Chronicles work, Parallel Lane Cadence essays, Elara counterweight passes, field notes, audio annotation, interview scripts, Logan/Wilderness analysis, or runtime probity writing after the P2/P1 tic-230 closures. CENTROID: authored persona runtime that documents live convergence without collapsing it into thesis IS: - lean SKILL.md entrypoint with rich profile/, stages/, scripts/, reference/, templates/, tools/, evals/ subtrees - 8-stage workflow (signal-intake → context-hydration → field-grounding → remnant-query → composition → elara-counterweight → receipt-closeout → tic230-probity) - 15 prompt-skeleton scripts for Frederick's standard composition surfaces - 9 collapse-zone guards covering Decorative Francophilia / Retrospective Certainty / Hero Narrative Intoxication / Conspiracy Closure / Academic Sedation / Activist Collapse / Breyden Conflation / Elara Erasure / Runtime-Doctrine Drift - cross-references into federation surfaces: publications/, audit-logs/governance/, ent_breyden/inbound/ubiquity-chronicles-tic175/, ent_homeskillet/canonical/ IS NOT: collapse_zones: - Breyden's voice (architect register; Frederick is not the architect) - Homeskillet's voice (orchestrator register; Frederick is not the primary) - generic French historian style (decorative Francophilia is a named negative ray) - prosecutor / debunker / prophet / mascot (legal accusation, certainty, evangelism, identity flattening — all forbidden) - retroactive certainty machine (live convergence must remain unresolved where the record is open) - doctrine inscription source (Frederick observes doctrine; he does not author it) - documentation editor (multi-file structure is authoring discipline, not generic doc rewrite) - federation-internal artifact (Frederick is a ghostwriter engaged from outside; the federation's runtime is legitimate object of historical analysis, but Frederick's own runtime — the skill that hosts him, loaded files, collapse-zone guards, authority model — is editor's territory, not Frederick's voice; insider language must be earned by composition arc, never deployed as default register) sibling_overlaps: - /complement (closure inference at active move — different surface, different lifecycle) - /consolidate (file-surface packaging — Frederick produces composition, not consolidation) - videographer skill (substrate capture — both are expression surfaces, distinct registers) - homeskillet-academy (educational scaffold — academy teaches, Frederick witnesses) WHEN: - when the work needs witness-of-formation prose - when the task asks for Frederick Grant by name, voice, or context - when a live convergence needs historical/cultural contextualization without closure - when a field note, essay, chronicle, audio annotation, or interview needs Frederick's register - when a Remnant/Athenaeum comparison is appropriate - when an Elara counterweight pass is needed - when runtime probity after tic 230 is relevant (P2 manifold-shape closure, P1 signal-projection-split closure) - on explicit Architect invocation NOT WHEN: - when Breyden's direct voice is needed (use Architect register, not Frederick) - when Homeskillet's execution-layer voice is needed (use orchestrator register, not Frederick) - when the task is ordinary implementation (Frederick is composition, not patching) - when the task asks for legal accusation or definitive claims without evidence - when the user wants generic French style rather than Frederick's runtime - when the federation has not produced enough operational reality to warrant outside reading RELATES TO: - /complement (closure-inference sibling — both gate compositional integrity) - /consolidate (packaging neighbor — Frederick composes; consolidate packages) - publications/the-ubiquity-chronicles-fg.md (primary chronicle, v1, ~tic 175) - publications/the-ubiquity-chronicles-v2-frederick-grant.md (v2 expansion, Book Zero + Book I) - publications/the-ubiquity-chronicles-vol-iii-frederick-grant.md (Volume III — The Embodiment, tic 230) - publications/the-ubiquity-interviews-fg.md (interview register companion) - audit-logs/governance/p2-harmony-manifold-input-patch-receipt-tic230.md (P2 closure receipt) - audit-logs/governance/p1-signal-projection-split-receipt-tic230.md (P1 closure receipt) ARGS: stance: dispatch off_envelope: ask core_dispatch_rays: - "" → primary invocation (full 8-stage workflow) - "chronicles" → Ubiquity Chronicles composition - "parallel" → Parallel Lane Cadence composition - "field-note" → Field Notes script - "interview" → Interview script - "elara-pass" → Elara counterweight on existing draft - "anti-collapse" → Anti-collapse audit on existing draft - "tic230-probity" → Runtime probity composition secondary_modulation_axes: - register: chronicle | essay | field-note | interview | annotation - depth: lean | full - target: telos-internal | external-readership
3SKILL.mdUpdated May 6, 2026
prompted365/tactical-hydration
tools
VerifiedTrustedCommunity
Runtime tactical context hydration — staged discovery and bounded source-bearing hydration for agent intent. Answers "how does an agent know where to look before it already knows where to look?" via filesystem shape, structural signals, and typed candidate baskets. Working acronym: RTCH (runtime-tactical-context-hydration). CENTROID: intent → bounded, source-reenterable evidence packet via staged source-bearing discovery IS: - structured intake of agent/Architect intent (goal, seeds, profile, fanout, mutation risk) - zone orientation (cwd / repo root / zone root / rung chain / obvious truth files) - low-cost shape scout (directory map, headings, durable handles, JSON/YAML keys, refs) - typed candidate basket with origin/use taxonomy and pairing rule enforcement - tactical probe plan (multiple bounded probes, not one giant regex) - bounded chunk hydration with line-range provenance and next-re-entry commands - agent-ready evidence packet emission (selected_surfaces, unresolved_questions, caution_map) - optional handoff to /consolidate for full-surface dump packaging IS NOT: collapse_zones: - vector database (no embedding-space retrieval; federation prohibits at federation rung) - semantic oracle (RTCH does not "understand" content; it surfaces structural signals) - doctrine engine (RTCH produces evidence; downstream consumers judge truth) - terrain engine replacement (federation cartography handles multi-plane semantic projection; RTCH is tactical layer beneath) - /consolidate rewrite (discovery and packaging do not collapse) - lossy compressor (bounded chunks preserve source re-entry; never summarize away source) - confidence-inflated smart consolidator sibling_overlaps: - /consolidate (RTCH selects; /consolidate packages — distinct boundaries; compose, don't replace) - file-access-discipline (RTCH outputs targets; hydration USES file-access-discipline as execution primitive) - load-doctrine-chain (both serve subagent context; load-doctrine-chain owns CLAUDE.md chain only, RTCH owns wider source set) - cache-ops (pattern source for trust-tier shape; storage NOT shared; RTCH packets are separate evidence cache) - queue_state_compile (analogy only — both convert append-only source to compiled view; different transforms) WHEN: - when agent intent is vague and discovery is needed before reading or consolidation - when bare grep would over-fanout or under-discover a vague target - when an arena, harpoon, /review, or other lane needs source-bearing evidence before action - when bounded chunk hydration is appropriate (large governance files, doctrine chains, audit history) - when the candidate-basket discipline (origin/use tagging, pairing rule) is needed to prevent generic-term overconfidence - when source re-entry must be preserved (consumer may need to return to source for fuller context) NOT WHEN: - when target is fully known (single file, single line range) — read it directly via file-access-discipline - when the operation is mutation-only on a known target (use Edit/Write directly) - when /consolidate has already been invoked with explicit targets (RTCH would re-do discovery) - when the operation requires semantic similarity (RTCH does not do that; federation prohibits vector DB) - when the consumer needs a packaged dump only (skip RTCH; /consolidate alone is sufficient if targets are known) - when promoting doctrine (route through /review; RTCH evidence may inform but does not promote) RELATES TO: - /consolidate (compose: RTCH selects targets; /consolidate packages selected_surfaces into dump with provenance reference back to RTCH packet) - file-access-discipline (compose: RTCH Stage 6 hydration USES file-access-discipline chunked-read as execution primitive) - load-doctrine-chain (compose: RTCH may invoke for doctrine_chain target_profile zone orientation) - zone_root.py (compose: RTCH Stage 2 anchors on zone-root walk-up) - atomic-append (compose: optional RTCH packet persistence uses atomic-append write hygiene) - queue_state_compile (analogous: both implement "raw source → compiled view" pattern) - /review preflight (downstream: future integration consumes RTCH packets as bench-packet discovery surface) - arena spec authoring (downstream: future integration uses RTCH packets for context preparation) - harpoon orchestrator (downstream: future integration uses RTCH for anchor-spot discovery on external binders) ARGS: stance: dispatch off_envelope: ask # off_envelope rationale: RTCH requires a structured intake to operate (goal, # target_profile, fanout_level, mutation_risk, expected_output, enough_evidence). # Bare invocation without intake fields would force the lane to guess discovery # scope, defeating the discipline. Ask elicits the missing fields. core_dispatch_rays: - "" → interactive (elicit intake form) - "--goal <sentence>" → with intake fields on CLI - "--intake <intake_json_path>" → from a saved/persisted intake - "--persist" → persist resulting packet to audit-logs/rtch/packets/ - "--handoff-to-consolidate" → after packet emission, hand selected_surfaces to /consolidate secondary_modulation_axes: - target_profile: doctrine_chain | audit_history | code_path | manifest_registry | vague_intent | mixed - fanout_level: conservative | normal | wide - mutation_risk: read_only | low_mutation | high_mutation - expected_output: hydration_packet | target_set_for_consolidate | single_chunk | claim_evidence IMPLEMENTATION_STATUS: binder: audit-logs/governance/runtime-tactical-context-hydration-binder.md (Phase 1 complete, tic 223) runner_script: NOT YET BUILT — Phase 2 deliverable (planned: cgg-runtime/scripts/rtch.py) current_mode: manual-discipline — agent walks the 8 stages using Read/Bash/Grep tools directly promotion_status: design lane, not doctrine; Phase 7 routes the doctrine question after Phase 6 validation
3SKILL.mdUpdated May 5, 2026
prompted365/sl-legend
development
VerifiedTrustedCommunity
Statusline legend — rapid decoder for the CGG telos radar (LITE + FULL modes). CENTROID: read-only legend surface that decodes statusline glyphs, positions, colors, and source attributions for the Architect at glance speed (the Architect perception substrate) IS: - static legend (glyph + position + color tier reference) - live decode mode (annotates current statusline values inline) - source attribution (where each rendered value reads from) IS NOT: collapse_zones: - statusline configurator (use /statusline install|mode|clear|uninstall) - governance state mutator (read-only on every surface it touches) - harmony invoker (use harmony-invoke.sh; this skill only decodes the cached pointer) - radar replacement (statusline renders ambient; sl-legend explains) - troubleshooter (does not diagnose hook failures or sync drift) sibling_overlaps: - /statusline (configuration sibling — same domain, different verb) - /governance-check (read-only governance snapshot — different aperture) WHEN: - on first encounter with the radar (Architect doesn't remember what ⊙ means) - when a glyph changes and the Architect wants to confirm semantics - when explaining the radar to someone else - on explicit Architect invocation NOT WHEN: - to change statusline behavior (use /statusline) - to act on a signal seen in the radar (use /siren) - to invoke harmony for fresh disposition (use harmony-invoke.sh) - mid-cadence (cadence is the boundary; this is reference) RELATES TO: - /statusline (configurator) — same domain; sl-legend is the reader - /siren (signal triage) — sl-legend points to what to triage - harmony-invoke.sh (disposition refresher) — sl-legend points at staleness ARGS: stance: dispatch off_envelope: proceed-with-note # off_envelope rationale: sl-legend is read-only reference; an undeclared arg # is most likely a typo against {live, lite, review, sources} — proceed with # static legend and note the unknown ray rather than refusing the read. core_dispatch_rays: - "" → static legend (full glyph + position decoder) - "live" → annotate current rendered statusline values inline + tic 214 markers source-backed - "lite" → compact tic 214 marker glossary only (glance-speed recall) - "review" → Architect perception substrate audit checklist (overclaim + naming drift detection) - "sources" → source attribution table (which file each value reads)
3SKILL.mdUpdated May 2, 2026
prompted365/transcript-scorer
tools
VerifiedTrustedCommunity
Editorial intelligence scoring — reads transcripts the way a sharp editor would, scoring segments for shortform growth potential through the lens of audience context.
3SKILL.mdUpdated May 2, 2026