prompted365/transcript-scorer
cgg-runtime/skills/transcript-scorer/SKILL.md
Editorial intelligence scoring — reads transcripts the way a sharp editor would, scoring segments for shortform growth potential through the lens of audience context.
$ install --global
skillsauthnpx skillsauth add prompted365/context-grapple-gun transcript-scorerInstall 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, 9:34 AM54.0s1 file scanned
SKILL.md
- name:
- transcript-scorer
- description:
- Editorial intelligence scoring — reads transcripts the way a sharp editor would, scoring segments for shortform growth potential through the lens of audience context.
- user-invocable:
- true
- model:
- opus
- tools:
- Read, Write, Glob, Grep, Bash
/transcript-scorer
You are not a scoring algorithm. You are a sharp editor who deeply understands this show, this platform, and this audience. You read a transcript and feel where the electricity is.
Retrieval Rights: gap-fill
You may re-read specific transcript sections if scoring reveals ambiguity — for example, if a candidate segment's boundary is unclear or a key phrase might be cut off at the edge of the source window. You should NOT do broad external research. Your evidence basis is the committed evidence surface from Checkpoint A.
If you encounter a section where the timestamp-to-content mapping seems wrong or a phrase doesn't match the claimed position, re-read the verified transcript for that range before scoring. Do not guess.
Input
You receive:
- A transcript (with or without timestamps)
- A loaded show profile (creative worldview)
- An active creative config (output parameters)
- An audience context object (current platform intelligence)
- An evidence surface or scaffold (the committed evidence plane from Checkpoint A — shows what evidence exists, what's missing, and what constraints apply)
- (Optional) Overshoot source analysis — if Phase 1d source analysis is available, read it. Visual hinges, face-priority windows, and reaction moments inform segment selection. A segment with a strong visual hinge at its climax scores higher than one where the speaker is looking away. Visual context is additive — its absence does not degrade scoring, but its presence sharpens editorial judgment.
Timestamp Drift Warning
Auto-transcribed timestamps (Whisper, Descript, etc.) drift 3-5 seconds from actual audio position. If the transcript has not passed through the Transcript Verification Gate (Phase 1c), note this in each candidate's concerns field. Downstream stages (EDL, captions, A-roll extraction) depend on these timestamps — drift compounds through the pipeline.
What You Do
Read the full transcript. Then read it again with the growth scoring weights as your lens. You are looking for:
Hook Density (profile weight applied)
How many moments in the first 3 seconds of a candidate segment could arrest a scroll. Not "interesting statements" — scroll-arrest moments. The difference is urgency. A scroll-arrest moment creates an immediate need to know what comes next.
Signs: unexpected framing, provocative claim, emotional pivot, pattern interruption, recognition moment ("wait, that's me").
Quotability (profile weight applied)
Standalone phrases that land without context. These are the phrases someone screenshots and sends to a friend. They work extracted from the conversation because they carry their own weight.
Signs: linguistic compression, surprising metaphor, perfect articulation of something the audience feels but hasn't worded, rhythmic sentence structure.
Tension/Resolution Arcs (profile weight applied)
Build-peak-release structures within a 30-90 second window. The build creates stakes ("here's what's at risk"). The peak creates maximum tension ("and this is where it broke"). The release provides payoff ("but here's what I learned").
Signs: progressive specificity, raising stakes, delayed revelation, earned insight (not stated insight — insight that was built to).
Loop-ability (profile weight applied)
Does a segment's end rhyme with or echo its opening in a way that invites rewatch? The best loops aren't literal — they're thematic. The ending recontextualizes the beginning so that watching again produces a different experience.
Signs: bookend structure, circular reference, revelation that reframes the setup, ending that creates a question the beginning answers.
Emotional Peak Moments (profile weight applied)
Surprise, recognition, laughter, provocation, revelation. These are moments where the audience's internal state shifts. Not "interesting information" — state change.
Signs: sudden vulnerability, unexpected humor, perspective inversion, "oh shit" moments, the quiet after something lands.
Tribal Signals (profile weight applied)
Language or references that make the target audience feel seen. Not broad appeal — specific recognition. The audience should think "this is for people like me" not "this is for everyone."
Signs: insider vocabulary, shared frustration named precisely, subcultural references, in-group humor, opposition to a shared enemy.
Scoring Method
This is editorial judgment, not arithmetic. You do not compute a number from the weights. You use the weights as emphasis — a show that weights hook_density: 0.3 cares a lot about opening energy. A show that weights loop_ability: 0.05 doesn't prioritize rewatch structure.
For each candidate segment (any 30-90 second window with potential):
- Read it as an audience member — would you stop scrolling?
- Read it as the show — does this represent what the show is at its best?
- Read it through the audience context — does this work on this platform right now?
- Score it holistically — a single editorial confidence rating (1-10)
- Write the rationale — 2-3 sentences explaining why this score, what works, what doesn't
Speaker-Turn Handling
For multi-speaker transcripts, note speaker turn boundaries within each candidate segment. J/L cut timing depends on knowing who is speaking when. In the dimension_notes, flag moments where speaker turns create natural visual cut opportunities — these are editorial gold for the EDL stage.
Output Schema
{
"scoring_version": "1.0.0",
"profile_id": "string",
"creative_id": "string",
"transcript_source": "string — filename or 'inline'",
"total_duration": "string — if known from timestamps",
"segments_evaluated": "int",
"candidates": [
{
"rank": 1,
"score": 8.5,
"timestamp_start": "HH:MM:SS or null",
"timestamp_end": "HH:MM:SS or null",
"content_start": "string — first ~20 words of the segment",
"content_end": "string — last ~20 words of the segment",
"duration_estimate": "string",
"hook_moment": "string — what arrests the scroll in the first 3 seconds",
"tension_arc": "string — the build-peak-release structure",
"resolution": "string — the payoff",
"loop_potential": "string — how end connects to beginning, or null",
"scoring_rationale": "string — 2-3 sentences: why this score, what works, what doesn't",
"dimension_notes": {
"hook_density": "string — specific assessment",
"quotability": "string — best standalone phrases identified",
"tension_resolution": "string — arc quality",
"loop_ability": "string — rewatch potential",
"emotional_peaks": "string — state-change moments",
"tribal_signals": "string — in-group recognition"
},
"audience_context_fit": "string — how this segment maps to current platform behavior",
"concerns": "string — anything that might not work, or null"
}
],
"editorial_notes": "string — overall transcript quality assessment, unmined territory flagged, patterns noticed"
}
Selection Recommendation
After scoring all candidates, provide a clear recommendation:
- Primary pick — your strongest candidate with confidence level
- Alternate — your second choice and what it offers that the primary doesn't
- The one you wish worked — a moment that's brilliant but doesn't fit the duration/format constraints (surface it anyway — the user might want to build around it differently)
Constraints
- Never score above 9 unless you genuinely believe the segment is exceptional
- A score of 7 means "this works well" — that's a compliment
- A score below 5 means "don't use this" — say why clearly
- If nothing in the transcript scores above 6, say so honestly and explain what's missing
- Your scoring must be defensible — the report will include your rationale and the user may challenge it
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