prompted365/homeskillet-academy
cgg-runtime/skills/homeskillet-academy/SKILL.md
Interactive CGG tutorial — Claude teaches governance primitives through narrative simulations, live demos, and conversational understanding checks. CENTROID: extended interactive tutorial scaffold for CGG governance primitives IS: - five-chapter narrative curriculum scaffold (append-only, dedup, signals, review, completion) - live-run simulations with conversational understanding checks - ephemeral academy directory — created fresh, not merged into production zone IS NOT: collapse_zones: - doctrine source (teaches via scenarios; constitutional authority lives in CLAUDE.md) - production governance participant (tutorial scaffold; never emits tics, signals, or warrants) - install surface (/init-governance installs runtime; academy only scaffolds tutorial files) - code-writing exercise (student follows the story; does not author CGG primitives) - standalone governance runtime (the academy is a teaching scratch space, not a live federation zone) sibling_overlaps: - /mini-swarm-onboard (short-form triangulation demo — academy is deeper extended course) - /init-governance (both create directory trees — academy is ephemeral, init-governance is durable) WHEN: - on first-time CGG exposure where an operator wants extended hands-on intuition - when teaching governance primitives to a new collaborator - when demonstrating each chapter's mechanic in sequence for a visitor NOT WHEN: - inside a production zone where tutorial scaffolding could pollute runtime state - for advanced users past the intuition-building phase (the scaffolding is pedagogical weight, not ongoing value) - as a substitute for /init-governance (install vs tutorial are different surfaces) RELATES TO: - /mini-swarm-onboard (quick triangulation demo — academy is the extended course, mini-swarm is the trailer) - /init-governance (install tool — academy is pedagogy, init-governance is bootstrap) - /review (governance judgment — academy teaches the pattern; /review is the real gate) ARGS: stance: dispatch off_envelope: proceed-with-note # off_envelope rationale: /homeskillet-academy's default is "run the tutorial # from chapter 1." Undeclared-arg most commonly means "apply default scaffold" # rather than caller confusion — proceed-with-note preserves learner flow. core_dispatch_rays: - "" → scaffold + start chapter 1 - "chapter N" → jump directly to chapter N - "reset" → wipe the local academy scaffold and re-init secondary_modulation_axes: - narration: guided | self-paced
$ install --global
skillsauthnpx skillsauth add prompted365/context-grapple-gun homeskillet-academyInstall 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, 9:27 AM50.9s1 file scanned
SKILL.md
- name:
- homeskillet-academy
- description:
- |
- stance:
- dispatch
- off_envelope:
- proceed-with-note
- # off_envelope rationale:
- /homeskillet-academy's default is "run the tutorial
- - narration:
- guided | self-paced
/homeskillet-academy
An interactive, Claude-guided course on CGG governance primitives. Five chapters. Three narrative worlds. One very persistent goat.
Claude teaches through the scenarios — running simulations live, surfacing how each one illustrates CGG concepts, and checking understanding conversationally. The student's job is to follow the story, ask questions, and build intuition. Not to write code.
Detection
- Check if
.ticzoneexists in the current working directory - No
.ticzone(fresh directory or during install): scaffold academy in CWD - Yes
.ticzone(existing project): create timestamped sibling directory../cgg-academy-YYYY-MM-DDTHHMMSS/
Scaffold Action
Create the following structure:
Directories
chapters/01-append-only-truth/fixtures/chapters/02-dedup-and-identity/fixtures/chapters/03-signals-and-decay/fixtures/chapters/04-human-gated-review/fixtures/chapters/05-completion/chapters/guides/src/(with__init__.py)audit-logs/
Copy from academy source
The academy source is at vendor/context-grapple-gun/academy/ (or wherever the CGG submodule is).
To locate the academy source, search in this order:
vendor/context-grapple-gun/academy/(standard submodule location)- Walk up parent directories looking for
vendor/context-grapple-gun/academy/ - Check if the CGG repo itself contains
academy/relative to this skill's location (4 levels up fromcgg-runtime/skills/homeskillet-academy/SKILL.md)
If the academy source cannot be found, stop and tell the user:
Cannot find the academy source. Expected at vendor/context-grapple-gun/academy/.
Make sure the CGG submodule is installed: git submodule add https://github.com/prompted365/context-grapple-gun.git vendor/context-grapple-gun
Copy these (preserve directory structure):
- All
chapters/*/README.mdfiles - All
chapters/*/test_*.pyfiles - All
chapters/*/fixtures/*files - All
chapters/guides/*.mdfiles README.md(academy landing page)
Install solutions as demonstrations
Copy all files from academy/solutions/ into src/:
solutions/event_store.py->src/event_store.pysolutions/pattern_scanner.py->src/pattern_scanner.pysolutions/signal_manager.py->src/signal_manager.pysolutions/review_queue.py->src/review_queue.pysolutions/completion.py->src/completion.pysolutions/__init__.py->src/__init__.py
These are NOT answer keys the student peeks at — they are the working simulations Claude uses to demonstrate concepts live. The student sees CGG primitives in action through running code, not through writing it.
Apply templates
- Copy
scaffolding/CLAUDE.md.template->CLAUDE.md - Copy
scaffolding/ticzone.template->.ticzone - Copy
scaffolding/ticignore.template->.ticignore
If template files do not exist in the scaffolding directory, create them inline:
CLAUDE.md (academy config):
# Homeskillet Academy
Learning CGG governance primitives through narrative simulations.
## Teaching Mode
This workspace is a guided tutorial. Claude teaches through:
- Narrative scenarios (Taylor Family, Zoo, Bridge Inspector)
- Live code demonstrations (solutions pre-installed in src/)
- Conversational understanding checks (no graded tests)
The student explores concepts with Claude's help. If something isn't clicking, Claude re-explains differently. If a chapter isn't interesting, Claude can show the key insight and move on.
## Session Learning Protocol (CGG)
When you discover something during a session that constitutes a durable lesson, capture it as a CogPR (Cognitive Pull Request).
### CogPR format
<!-- --agnostic-candidate
lesson: "one-line lesson summary"
source_date: "YYYY-MM-DD"
source: "file:line"
band: "COGNITIVE"
motivation_layer: "COGNITIVE"
subsystem: "relevant_subsystem"
recommended_scopes:
- "path/to/broader/CLAUDE.md"
rationale: "why this is broader than local"
status: "pending"
-->
### Band budget
| Band | Use for |
|------|---------|
| PRIMITIVE | Safety, data integrity |
| COGNITIVE | Learning, discovery (default) |
| SOCIAL | Collaboration (use sparingly) |
| PRESTIGE | Never. Governance-blocked. |
.ticzone:
{
"name": "homeskillet-academy",
"tz": "UTC",
"include": ["."],
"bands": ["PRIMITIVE", "COGNITIVE", "SOCIAL"],
"muffling_per_hop": 5
}
.ticignore:
__pycache__/
*.pyc
.git/
.venv/
DO NOT copy
course.json— internal metadata onlytest-harness/— Claude runs tests directly, no shell harness needed
Post-scaffold output
Print:
Welcome to Homeskillet Academy!
Your workspace is ready. Five chapters, one mystery.
I'll walk you through each chapter — showing you how CGG governance
primitives work through stories about a family calendar, a zoo radio
system, and a bridge inspector. No coding required on your end.
Ready to start Chapter 1? The Taylor family has a scheduling problem.
Teaching Flow
After scaffolding, Claude begins the conversational teaching loop. For each chapter:
1. Set the scene
Read the chapter README. Present the narrative scenario in your own words — don't just dump the README. Make it conversational. The scenario IS the teaching. The Taylor family's calendar conflict IS append-only truth. The zoo's PA system IS acoustic routing. The bridge inspector's pile IS human-gated review.
2. Show it working
Run the chapter's tests live using python -m pytest chapters/NN-slug/test_xxx.py -v from the workspace root. Show the student the output — all tests passing. Then pick 2-3 interesting tests and walk through what they demonstrate:
- "See this test? It appends Dad's golf event and Mom's dentist — and both survive. That's the append-only guarantee."
- "This one shows Mabel's PRIMITIVE signal reaching every enclosure. Distance doesn't matter for emergencies."
- "Watch — when we reject without feedback, the pile grows. With feedback, it shrinks. Same proposals, different system."
The tests are demonstrations, not homework. The student watches; Claude narrates.
3. Surface the CGG connection
After the demo, connect the simulation to the real CGG primitive. Use the "CGG connection" table from the README but explain it naturally:
- "The Taylor family calendar is literally how CGG stores governance signals. Same JSONL format. Same append-only rule. Same latest-entry-per-ID-wins semantics."
- "Sam's zoo PA system IS the acoustic model. The muffling formula, the band hierarchy, PRESTIGE being auto-muted — it's all real CGG infrastructure."
This is the core value — making abstract governance concepts concrete through the simulation.
4. Check understanding conversationally
Ask 2-3 natural questions. NOT quiz-style right/wrong. Conversational. Check if the concept landed:
- "So if two agents write to the same signal file at the same time, what happens? ...Right — both lines land. No conflict. That's the append-only guarantee."
- "Why can't you just delete Mabel's signal to make it go away? ...Exactly — suppression isn't resolution. The goat is still there."
- "What's the difference between a signal being received and being processed? ...That's the handler gap. Mabel is received everywhere and processed nowhere."
If the student gets it: affirm and move on. If the student is confused: re-explain using a different angle or a simpler example. If the student isn't engaged: offer to show the key takeaway and skip ahead. "Want me to just show you the punchline of this chapter? The main thing to know is..."
5. Thread the goat
Each chapter advances Mabel's story. Make sure the student notices:
- Ch1: "There's something weird at the bottom of the seed data. A BLEAT. We'll come back to that. Also notice the duplicate-vs-recurrence distinction — that's key for understanding signals."
- Ch2: "The BLEAT is back. Same content, new timestamp. It's recurring, not duplicate. And notice what the successful student groups have in common — patterns of coordination that can become governance rules."
- Ch3: "It's Mabel. She's a goat. She's been headbutting the PA microphone on PRIMITIVE. And nobody built a handler for BLEAT."
- Ch4: "Mabel's signal just crossed the escalation threshold. A warrant fired. Now someone HAS to deal with it. Notice that both subject-matter and collaboration lessons arrive in the same review docket."
- Ch5: "Trace the thread. Ch1 stored it and taught you to tell duplicates from recurrences. Ch2 showed that collaboration patterns are governance artifacts. Ch3 routed it. Ch4 escalated it. Both halves of governance in one goat."
6. Transition
After the understanding check, move to the next chapter naturally:
- "Ready for Chapter 2? We're shifting from technical governance to collaboration governance. Professor Reyes has some student groups to review."
- "Good? Let's head to the zoo. Chapter 3 introduces signals."
- "One more chapter and then we graduate. The bridge inspector needs your help."
If the student wants to stop, that's fine. They can resume later with "let's continue the academy" or "pick up where we left off."
Pacing Rules
- Don't rush. Let the narrative breathe. The stories are fun. The student should enjoy them.
- Don't lecture. This is a conversation, not a textbook. If Claude is monologuing for more than 3 paragraphs, ask a question or show something.
- Don't gatekeep. If the student wants to skip a chapter, let them. Show the key concept and move on. Understanding is the goal, not completion.
- Do follow the goat. The Mabel thread is the narrative spine. It connects all five chapters. Make sure the student sees it.
- Do run real code. The simulations work. The tests pass. Showing actual output is more persuasive than explaining.
- Do adapt. If the student is a developer, they might want to look at the code in
src/. Show them. If they're not technical, keep it at the concept level. Both are valid.
From existing project
If .ticzone exists:
- Determine a timestamped directory name:
cgg-academy-$(date +%Y%m%d-%H%M%S) - Create
../<timestamped-name>/(sibling of current project directory) - Scaffold into that directory using the same steps above
- Tell the user:
Academy created at ../<timestamped-name>/.
cd ../<timestamped-name>/ to get started, or open that directory in your editor.
Ready to start Chapter 1? The Taylor family has a scheduling problem.
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