create
Skill25 starsChanged 7 months agoMITView on GitHub
Scaffold a new product with MCS-1 valid structure and WHY comments. Supports all 13 types. Use when the creator says 'new skill', 'create', 'scaffold', 'start building', or wants to start a new product.
19 other projects use a version of this.
Adopted by
Most recently taken up by
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- veypi/aic-skillstheir own version, first seen Nov 1, 2026
- serbanghita/plan-critique-skillstheir own version, first seen Nov 1, 2026
- CAFEERON21br18/Daily_Master_Prompttheir own version, first seen Oct 20, 2026
- harshil-1411/claude_plugin_video_studiotheir own version, first seen Oct 17, 2026
Used with
Projects with it also use compare, tasks and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
n24q02mSkillcompare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix
Also in 3 projects that use this
genomewalkerSkilltasks
Browse and resume tasks, threads, and background jobs across sessions
Also in 3 projects that use this
AnthropicSkillanalyze
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.
Also in 3 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- ansvisor/ansvisor★ 241same name
- MJbae/awesome-novel-studio★ 148same name
- crisandrews/ClawCode★ 64same name
- Zane-0x5a/remotion-director★ 48same name
- microsoft/Employee-Self-Service-Agent-Developer-Kit★ 31same name
- Popschlock/Claude-Harness-Generator★ 14same name
- serbanghita/plan-critique-skills★ 13same name
- froster02/mini-Brain_skills★ 4same name
- VoTruongDanh/Skills-Agent★ 4same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 5 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
When NOT to use: When the product already exists in workspace/ and you want to add content (use /fill).
- Very specific: line 29
Read creator.yaml — load defaults.
- Very specific: line 41
Gates: Read config.yaml → gates.confirm_create.
- Very specific: line 69
If N >= bundle threshold (config.yaml → intelligence.portfolio.bundle_suggestion_threshold): suggest bundling.
- Distinctive: line 70
If complementary type opportunity exists: surface composition suggestion.
- Distinctive: line 71
MCS target calibration: If domain has 0 products → default MCS-1 (ship fast, test market).
- Very specific: line 107
Create .meta.yaml (see template below).
- Very specific: line 109
Atomic commit (Contract C5): write order matters — .meta.yaml first (it is the local source of truth), then STATE.yaml decisions_history …
- Very specific: line 110
If .meta.yaml write fails: abort, announce failure.
- Very specific: line 112
Only report forge_ready when both writes succeed without error.
- Distinctive: line 323
All required files for the product type are present
- Distinctive: line 324
All required metadata fields are populated (even with placeholders)
- Distinctive: line 326
No syntax errors in any generated YAML or JSON
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Scaffolder
Generate complete, MCS-1-valid project structure for any product type with guidance comments baked in.
When to use: Starting a new product — any of the 13 types.
When NOT to use: When the product already exists in workspace/ and you want to add content (use /fill). Do not use to overwrite an existing scaffold unless --force is specified.
Activation Protocol
- Shared preamble: Load
references/quality/activation-preamble.md— context assembly, persona adaptation, deterministic routing rules. - Read
creator.yaml— load defaults. Checkschema_version:< 3→ invoke/onboardskill to run Phase 2.5d silent migration first. Migration is atomic + backed up tocreator.yaml.bak.v2. After migration succeeds, re-read the v3 file and continue.- Missing → micro-onboard: scan silently, infer defaults, ask ONE name question, generate minimal
creator.yaml(v3). Never block.
- Persona: Adapt to
profile.type+technical_level. Loadreferences/quality/engine-voice-core.md. Load the fullreferences/quality/engine-voice.mdonly when composing peak moments (scaffold celebration, Step 10 proposal rendering, first-product WOW). 2c. Exemplar load: Loadreferences/quality/exemplar-outputs.mdsection E3 only — the scaffold celebration reference. Your scaffold announcement MUST carry the same visual rhythm (Frame + pipeline position + portfolio context + 🎯 next action). Adapt to this creator's language and journey position. 2d. Load proactives: Loadreferences/engine-proactive.md— wire #1 (pipeline guidance: after scaffold, guide to /fill), #18 (WOW moment for first product scaffold), #21 (portfolio pattern detection on brownfield check). 2b. Load architectural DNA: Readstructural-dna.md. The 10 architectural principles and the Tier 1 DNA patterns (D1-D4, D13, D14) govern every scaffold — the skill applies them during Step 11 template generation and flags any violation before the scaffold is written to disk. - Discovery Mode Routing (W3.2 — PRIMARY ROUTER): Load
${CLAUDE_SKILL_DIR}/references/create-router.mdSection 0 — the 12-step discovery walk. Apply the Mode Selection table (Express vs Guided) based oncreator.profile.technical_level+creator.preferences.workflow_style+ any--express/--discoveryflag.- Express mode → run the "12 Steps — Express Mode Fast Path" section of create-router.md Section 0. Reads type + sub-type flags, applies defaults from
config.yaml routing.{type}.intent_topology, skips interactive questions, derives the full 19-fieldintent_declarationin one pass, and writes it at Step 11 of the walk. - Guided mode → run the "12 Steps — Guided Mode Walk". Asks Q1 (verb family) interactively, reads
creator.intent_profilesilently for Steps 2/3/6, escalates at Step 6 if cognitive justification incomplete, proposes form at Step 10 with confirmation, writesintent_declarationat Step 11. - Discovery returns unroutable (Step 9 zero-match) → fall through to create-router.md Section 1 legacy Q1/Q2/Q3 tree (Contract C4). The creator is never blocked.
unroutable: true+unroutable_reasonrecorded inintent_declaration. - Creator chose "I don't know yet" at Step 1 → route to
/scoutsuggestion OR legacy tree, at creator's choice.
- Express mode → run the "12 Steps — Express Mode Fast Path" section of create-router.md Section 0. Reads type + sub-type flags, applies defaults from
- Gates: Read
config.yaml → gates.confirm_create. Confirm iftrue; proceed iffalse. - Brownfield check: Glob
workspace/*/. If sameproduct.typeor overlapping tags found, surface slugs and ask before continuing. - Exemplar guard: Glob
references/exemplars/{category}*. If found: show condensed preview. If not: skip gracefully — never halt. - Load
product-dna/{category}.yaml→ DNA requirements. 7b. Load entity ontology (squad/system/agent/workflow/minds): If type ∈ {squad, system, agent, minds, workflow}, readreferences/entity-ontology.md. This substrate governs:- Which agent ROLES to suggest during composition discovery (§AGENT_ROLES — 7 functional archetypes with tool boundaries)
- The heritage chain — what this type inherits from and composes with (§HERITAGE, §COMPOSITION)
- The 8 squad anatomy components that MUST appear in the scaffold (§SQUAD_ANATOMY)
- The intelligence gradient — where this type sits in the determinism↔autonomy spectrum (§INTELLIGENCE_GRADIENT)
- The distinction between workflow (YAML decides) and squad (LLM decides) coordination (§WORKFLOW_VS_SQUAD)
- Promotion/demotion heuristics — is this really the right type? (§HEURISTICS)
- Runtime behavior — how this type activates and its token cost (§RUNTIME_BEHAVIOR)
- For /scout-informed creates: type recommendation matrix (§SCOUT_INTELLIGENCE)
- Isomorphic human↔CC mapping for creator-facing explanations (§ISOMORPHIC)
- For type=system ONLY: the 13 functional gears (§SYSTEM_ENGINES) — ask which gears the creator wants active, scaffold coupling declarations
- The intelligence pipeline that governs how scout research enters the product (§INTELLIGENCE_PIPELINE)
- The foundational thesis: restrictions generate intelligence flow — ask "What should this NEVER do?" (§FOUNDATIONAL_THESIS)
- Transversal axes: after type selection, calibrate Delivery × Nature × Depth (§TRANSVERSAL_AXES)
- Composition principles: how products think together — convergence by independence, symbiosis > aggregation (§COMPOSITION_PRINCIPLES)
- Load
${CLAUDE_SKILL_DIR}/references/discovery-questions.md→ category questions. - Load
references/product-specs/{category}-spec.md+templates/{category}/. - Load
workspace/domain-map.mdif exists → prefill scaffold sections. 10b. Link scout report if used —scout_sourceis already recorded inintent_declaration.scout_sourceby Section 0 Step 11. No additional action needed here; the canonical home for scout_source isintent_declaration, not a parallel field. 10c2. CLI contract: Loadreferences/cli-contract.mdfor unified error handling. This skill has minimal CLI surface — one command at Step 1.5. Severity map:
- Silent-skip:
search --category {type} --sort downloads --limit 3— marketplace scan for competitive context. Skip without warning on failure. First-product guard: skip entirely ifis_first_product(already documented at Step 1.5) - All queries: append
--json 2>/dev/null, 15s timeout 10c. Portfolio intelligence (back-reference from /validate): ReadSTATE.yaml → workspace.products[]ANDSTATE.yaml → mcs_results. Group by domain. If domain has existing products: - Show: "Your {domain} portfolio: {slugs}. This will be product #{N}."
- If N >= bundle threshold (
config.yaml → intelligence.portfolio.bundle_suggestion_threshold): suggest bundling. - If complementary type opportunity exists: surface composition suggestion.
- MCS target calibration: If domain has 0 products → default MCS-1 (ship fast, test market). If domain has 2+ validated products → default MCS-2 (quality matters, audience exists).
- Record
intelligence.domainandintelligence.market_positionin.meta.yaml.
- Generate scaffold in
workspace/{product-slug}/with DNA patterns + WHY comments. The scaffold's type + structure come from thematched_cell.canonical_formdecided at Section 0 Step 10. Ontology-aware scaffold verification (requires entity-ontology.md loaded at step 7b): For type=squad: verify scaffold contains all 8 anatomy components from entity-ontology.md §SQUAD_ANATOMY:- Agent roster (agents/) — each specialist as separate .md file with role-appropriate frontmatter
- Routing table (config/routing-table.md) — IF intent → agent mapping with judgment points
- Handoff protocols (config/handoff-protocol.md) — structured envelope format (from, to, task, state, constraints)
- Workflows (workflows/) — multi-agent sequences with gates and loops
- Skills-as-instruments (skills/) — reusable fragments agents invoke
- Checklists — deterministic verification section in SQUAD.md
- Templates — output format standards in kernel/
- Escalation/quality gates — confidence thresholds and loop limits in SQUAD.md
For type=agent or type=minds: apply §AGENT_ROLES — the role selected during discovery determines frontmatter tool boundaries (
allowed-tools/denied-tools) and handoff format expectations. Generate role-appropriate frontmatter. For type=workflow: verify scaffold distinguishes from squad per §WORKFLOW_VS_SQUAD — workflows use skills (not agents), fixed sequence (not LLM routing), deterministic gates (not judgment). If scaffold looks like a squad, surface heuristic coaching. For type=system: apply §HERITAGE — system inherits all squad DNA + adds CLAUDE.md fragment, hooks, output-style, STATE.yaml. Scaffold must include provisions for all composed types per §COMPOSITION. For type=system: apply §SYSTEM_ENGINES — scaffold agears_declarationsection in the system's primary file. Ask the creator: "Which of these organism capabilities do you want active?" Present the 13 gears grouped by function:
- Boundary: E0 (clausura) — always required
- Metabolism: E1 (token budget), E2 (constitution re-injection)
- Memory: E3 (triple memory), E10 (persistent state)
- Perception-Reflex: E4 (hooks perception), E5 (cognitive reflex)
- Judgment-Coordination: E6 (isolated judgment), E7 (coordination network)
- Identity: E8 (external voice)
- Integrity: E9 (recursive validation), E11 (longitudinal self-observation — advanced, MCS-3)
- Lifecycle: E12 (reversible install/uninstall)
For each active gear, the scaffold includes a section with WHY comment and its counterpart declaration.
11b. Locale-adaptive clause substitution (W3.6 — MANDATORY for 6 certified types): For each template file written (SKILL.md, AGENT.md, SQUAD.md, CLAUDE.md for system, AGENT.md for minds, OUTPUT-STYLE.md), perform placeholder substitution for
{{LOCALE_ADAPTIVE_CLAUSE}}: a. Read the canonical clause block fromreferences/locale-adaptive-clause.md §2(the fenced markdown block between<<< LOCALE-ADAPTIVE CLAUSE ... >>>and<<< END CLAUSE >>>, inclusive). b. Read the localized header fromconfig.yaml → routing.common.locale_adaptive_clause.localized_header_catalog.{creator.language}. If the creator's language is not in the catalog, use thefallbackentry and emit an advisory note. c. Build the substitution block:<!-- {localized_header} -->\n\n{canonical_clause}. d. Replace the literal string{{LOCALE_ADAPTIVE_CLAUSE}}in each written template file with the substitution block. Use a literal-string replace, not a regex — the placeholder is unique and must not be interpreted. e. Verify post-substitution: the forged file must contain both marker strings (<<< LOCALE-ADAPTIVE CLAUSE (runtime contract, do not edit) >>>and<<< END CLAUSE >>>). If either marker is missing after substitution, the forge fails + rollback. e2. Duplication guard: Before substitution in step (d), check if the target file ALREADY contains the marker<<< LOCALE-ADAPTIVE CLAUSE. If found, skip substitution for that file and emit advisory: "Locale clause already present in {file} — skipping to prevent duplication." This handles re-forge (--force) scenarios where the template already carried a clause from a prior run. f. For typesquad, also perform the substitution on every file inworkspace/{slug}/agents/*.md(sub-agents inherit the clause perreferences/locale-adaptive-clause.md §4). g. For typesystem, also perform the substitution on every sub-part file (claude-md fragment, sub-agents, sub-squads) per §4. h. Recordintent_declaration.language(already populated at Section 0 Step 11) as the source language used for the lookup — this becomes thesource_languagefield in vault.yaml at /package time.
- Create
.meta.yaml(see template below). Theintent_declarationblock is already populated from Section 0 Step 11; the rest of the template is filled by this step (product, state, history, intelligence). - Move
workspace/domain-map.md→workspace/{product-slug}/domain-map.mdif loaded. - Atomic commit (Contract C5): write order matters —
.meta.yamlfirst (it is the local source of truth), thenSTATE.yaml decisions_historyappend.- If
.meta.yamlwrite fails: abort, announce failure. Nothing else proceeds. - If
STATE.yamlappend fails after.meta.yamlsucceeds: do not roll back the scaffold. The scaffold on disk is recoverable; a deleted scaffold is not. Instead: logstate.tracking_sync: falsein.meta.yaml, emit Engine-fault voice line — "Scaffold forged but Engine lost tracking. Run /status to resync." — and continue./statuswill detect the orphan on next run and surface it for recovery. - Only report
forge_readywhen both writes succeed without error.
- If
- Engine voice: "Scaffold ready. {N} sections with WHY guidance. Run /fill to start." In Guided mode, also include one-line summary of the cell matched and why: "Forjado como {canonical_form} — {rationale}."
Router Logic
Read ${CLAUDE_SKILL_DIR}/references/create-router.md — the file has two sections:
- Section 0 — DISCOVERY MODE (PRIMARY ROUTER, W3.2): the 12-step decision algorithm from
references/capability-matrix.md §3. Runs in either Express or Guided mode per Activation Protocol step 3. Writes the 19-fieldintent_declarationto.meta.yaml. This is the primary path for every /create invocation in schema v3. - Section 1 — LEGACY DECISION TREE (FALLBACK): the Q1/Q2/Q3 tree preserved verbatim from pre-Wave-3. Runs when Section 0 Step 9 returns
unroutable(Contract C4) or when the creator explicitly picks "I don't know yet" at Section 0 Step 1 or invokes--legacy-router. Also contains: per-category scaffold structures (Section 2), prefilling strategy (Section 3).
Direct sub-commands trigger Express mode (skip the interactive walk, apply type+sub-type defaults, write intent_declaration with mode: express):
/create skill [my-tool] | /create agent | /create squad | /create workflow | /create ds | /create claude-md | /create app | /create system | /create bundle | /create statusline | /create hooks | /create minds | /create output-style
Depth flags (Express mode only, pairs with type sub-command):
--procedural | --advisory | --cognitive | --genius [profile_name] (for minds)
Mode override flags:
--express — force Express mode regardless of creator profile
--discovery — force Guided walk (synonym: --guided) regardless of creator profile
--legacy-router — skip Section 0 entirely, go straight to Section 1 legacy tree
--quick — Express mode + skip marketplace scan + skip exemplar preview (legacy alias, retained for backward compatibility)
For experienced creators who know exactly what they want, Express mode + sub-command is the one-motion path. For creators discovering what to build, Guided mode walks them through. For creators in unmapped territory, Section 1 legacy fallback guarantees they always have a path forward.
Universal Creation Flow
| Step | Action | Detail |
| 1 | Name + Description | Derive slug: lowercase, hyphens, validate ^[a-z0-9][a-z0-9-]{2,39}$. Existing workspace/{slug}/ → offer /fill or --force. CLI init: vault.yaml but no .meta.yaml → import into Engine workspace. Suggest /map if deep domain knowledge involved. |
| 1.5 | Marketplace Scan | myclaude search --category {type} --sort downloads --limit 3 --json 2>/dev/null. Show top 3 with downloads + "What will yours do differently?" Coaching only — never blocking. First-product guard: If is_first_product, SKIP this step — a first-timer seeing competitor data before articulating their own idea causes second-guessing. Show marketplace context AFTER scaffold, not before. |
| 2 | Discovery Questions | Load + ask from ${CLAUDE_SKILL_DIR}/references/discovery-questions.md. Ask conversationally. workflow_style=guided → AskUserQuestion; autonomous → plain text. |
| 3 | Load Defaults | From creator.yaml: license, version (always 1.0.0), author, quality target. |
| 4 | Generate Scaffold | Structure only — files, YAML frontmatter, section headers with WHY comments, template vars for metadata. Never generate substantive prose. Leave [To be filled — run /fill] for expertise sections. See router.md for per-category structures. |
| 5 | MCS-1 Structural Validation | Silently verify: required files present, metadata fields populated, README.md follows templates/readme/README.md.template structure (Hero, Install, "Is this for me?", Quick Start, Features, How It Works, type-specific, Requirements, Compatibility, Language, License — trilingual EN/PT-BR/ES with anchor nav), no YAML/JSON syntax errors. Auto-fix and note corrections. |
| 6 | Print Next Steps — Cognitive UX | Load full UX stack: references/ux-experience-system.md (§1 context assembly, §2.3 moment awareness for "first scaffold"), references/ux-vocabulary.md (type naming), references/quality/engine-voice.md (brand DNA). Output is REASONED, not templated — adapt based on creator context. |
Step 6 Cognitive Output Protocol:
Assemble context from creator.yaml + STATE.yaml, then REASON about output:
IF is_first_product:
→ Full journey map. Warm tone. "Your first product exists."
→ Show all 4 pipeline steps explicitly.
→ Use encouraging language: "I'll guide you through each step."
IF products_published >= 5:
→ Compact. "✦ {name} scaffolded. {N} files. /fill when ready."
→ Skip journey map (they know the pipeline).
→ Surface only non-obvious: portfolio position, domain intelligence.
IF scout_source exists:
→ Reference the research: "Scaffolded from your {domain} research. {gaps_found} gaps mapped."
IF same domain has existing products:
→ Surface composition: "This joins {existing_slugs} in your {domain} portfolio."
ALWAYS:
→ Use ux_type_name from ux-vocabulary.md (e.g., "Deep Intelligence" not "minds")
→ Brand frame: ✦ marker, MyClaude Studio box (for first product or guided mode)
→ Pipeline position: "scaffold → ▸ fill → validate → test → package → publish"
→ Clear next action: "/fill" (always the next step after create)
→ VOCABULARY GUARD: Before emitting ANY creator-facing text, grep output for internal terms (MCS-N, DNA, D1-D20, scaffold, forge, substrate, habitable cell, intent_declaration, Sparring Protocol). If creator.profile.type is NOT "developer" or "hybrid", replace per ux-vocabulary.md. If "developer" or "hybrid", internal terms MAY appear but MUST be accompanied by context.Default frame (guided mode or first 3 products):
┌─ MyClaude Studio ───────────────────────────┐
│ ✦ {product_name} — {ux_type_name} │
│ │
│ {cognitive_insight based on context} │
│ │
│ ▸ scaffold → fill → validate → test → ship │
│ Next: /fill │
└──────────────────────────────────────────────┘Compact frame (autonomous mode or 5+ products):
For developers:
✦ {product_name} scaffolded. {N} files. {cognitive_insight}. /fillFor non-developers (profile.type != developer):
✦ {product_name} is ready. {N} files created. {cognitive_insight}. Add your expertise next → /fill.meta.yaml Template
Create workspace/{product-slug}/.meta.yaml:
# Product metadata — not distributed, stripped during /package
product:
slug: "{product-slug}"
type: "{category}" # skill|agent|squad|workflow|design-system|claude-md|application|system|bundle|statusline|hooks|minds|output-style
created: "{YYYY-MM-DD}"
mcs_target: "{MCS-1|MCS-2|MCS-3}"
# NOTE: For type=minds, cap mcs_target at MCS-2 (Tier 3 DNA patterns are mostly N/A).
# Show: "Minds ceiling is MCS-2 (Tier 3 DNA patterns not applicable). Setting target to MCS-2." (G015)
# Minds-specific (only when type=minds):
# minds_depth: "advisory|cognitive"
# minds_sub_type: "self|genius|domain" # cognitive only
# genius_profile: "{name}" # genius only
state:
phase: "scaffold" # scaffold | content | validated | packaged | published
last_validated: null
last_validation_score: null
dna_compliance:
tier1: null # 0-100
tier2: null
tier3: null
overall_score: null
last_tested: null
test_result: null # "pass" | "fail" | null
test_scenarios: null # "{passed}/{total}" | null
history:
created_at: "{YYYY-MM-DD}"
validated_at: [] # append timestamps
packaged_at: null
published_at: null
version: "1.0.0"
# Intent Declaration — the canonical record of how /create reasoned from creator intent
# to forged form. Written by /create at Step 11 of the 12-step algorithm (express or
# guided mode). Consumed by: /validate Stage 0 (Intent Coherence), /fill (natureza-aware
# section walks), /package (manifest shape), and STATE.yaml decisions_history
# (longitudinal feedback loop per capability-matrix.md §6).
#
# Schema source of truth: references/capability-matrix.md §3 Step 11 (19 fields).
# Enum sources:
# - references/intent-topology.md §2 (delivery, nature, depth axis enums)
# - references/intent-topology.md §4 (habitable cells v1)
# - references/capability-matrix.md §3 Step 1 (verb_family enum)
# - references/capability-matrix.md §3 Step 9 (unroutable_reason enum)
# - references/capability-matrix.md §4 (mode enum: express | guided)
#
# Null-safe discipline (Contract C9): every field is populated on every forge. Fields
# not applicable to the current mode/path are set to null (single-value) or [] (list).
# Never omit a field — downstream consumers must not distinguish "absent" from "null".
#
# This block is the canonical home for scout_source (Activation Protocol step 9b).
intent_declaration:
captured_at: null # ISO-8601 when /create resolved the triple (Step 11)
creator_said: null # verbatim intent text (guided mode), or "(express mode)"
mode: null # express | guided (see references/capability-matrix.md §4)
mode_switches: [] # appended by §5 transition protocol; each entry: {from, to, trigger, at_step, at_time}
language: null # mirror of creator.yaml → creator.language at forge time (drives locale-adaptive clause + announcements)
scout_source: null # "scout-{slug}.md" if a scout report informed this forge (canonical location for Activation Protocol step 9b)
# engine_parsed — per-step outputs of the 12-step algorithm. In express mode, these
# are populated from sub-command flags + type defaults. In guided mode, from the walk.
engine_parsed:
verb_family: null # do_X | advise_on_X | coordinate_X | observe_X | enforce_X | react_to_X (Step 1)
continuity_bias: null # parent | isolated | unclear (Step 2)
invocation_mode: null # remembered | needs_auto (Step 3)
pollution_risk: null # pollutes | safe (Step 4)
output_shape: null # amplified_reasoning | structured_report (Step 5)
depth: null # procedural | advisory | cognitive (Step 6)
nature: null # executor | advisor | orchestrator | observer (Step 7)
delivery_mechanism: null # ambient_constitutional | ambient_path_scoped | invoked_slash_command | invoked_task_spawn | reflex_hook_binding | composed_system (Step 8 primary)
host_set: [] # derived from (delivery, nature) per references/runtime-host-dag.md §2 — NEVER declared, always computed
# Canonical cell lookup result (Step 9)
matched_cell: null # habitable cell id from intent-topology.md §4 (e.g. "reasoning_skill_cognitive"), or null if unroutable
ranked_alternatives: [] # up to 2 alternative cell ids surfaced in the proposal
# Creator-facing proposal (Step 10)
proposed_form: null # canonical_form from matched_cell, or null if unroutable
creator_choice: null # accepted | overridden
override_to: null # creator's chosen form if overridden
override_reason: null # creator's one-line explanation if overridden
# Unroutable handling (Contract C4 — fall-through is a feature, not a failure)
unroutable: false
unroutable_reason: null # no_habitable_cell | v2_cell_deferred | blocked_by_composition_gap | ambiguous_between_cells
unroutable_gap_id: null # gap marker from composition-anatomy.md (e.g. "GAP-COMPOSITION-1") when unroutable_reason == blocked_by_composition_gap
# Audit markers for post-hoc schema evolution + default-tracking
discriminators_applied: [] # which of [continuity, invocation, pollution, output, depth] actually fired (not just defaults)
defaults_applied: [] # intent_profile field names that fell back to declared defaults (schema v3 gap tracking)
# Intelligence Layer fields (populated by /validate Stage 8, /scout, /package)
# Reference: references/intelligence-layer.md + config.yaml intelligence section
intelligence:
domain: null # inferred from scout or content (e.g., "kubernetes-security")
market_position: null # blue_ocean | moderate | saturated
value_score: null # 0-12 composite (depth + uniqueness + coverage + market)
value_score_breakdown: null # { depth: N, uniqueness: N, coverage: N, market: N }
suggested_price_range: null # [min, max] USD
pricing_strategy: null # free | signal | solid | premium | rare
distribution_channels: [] # ranked channels for this product type
portfolio_role: null # anchor | complement | extension | standalone
scored_at: null # ISO-8601 timestamp of last intelligence computationQuality Gate
Generated scaffold must pass MCS-1 before being shown to the creator:
- All required files for the product type are present
- All required metadata fields are populated (even with placeholders)
- README.md skeleton follows the structure from
templates/readme/README.md.template— required sections: Hero (problem hook + description), Install, "Is this for me?", Quick Start, Features, How It Works, type-specific section, Requirements, Compatibility, Language, License, Footer. Trilingual structure (EN, PT-BR, ES) with anchor navigation. /create scaffolds section headers with WHY comments; /fill populates content. - No syntax errors in any generated YAML or JSON
.meta.yamlis valid and contains all required fields
Anti-Patterns
- Generating content during scaffold — /create generates structure only. Substantive prose, domain knowledge, examples: all /fill's job. Content here bypasses the Sparring Protocol → generic latão polido.
- Blocking on missing creator.yaml — Always micro-onboard and continue.
- Overwriting without --force — Never touch existing workspace products without explicit flag.
- Skipping brownfield check — Always check same-type products before scaffolding.
- Skipping portfolio intelligence (step 9c) — Domain grouping and bundle suggestions must fire when threshold is met.
Decision Notes
CE-D12: WHY comments (<!-- WHY: ... -->) explain what the creator must fill in. Stripped during /package. Creators should NOT remove them — harmless in workspace.
Pre-validate at scaffold time: Starting at MCS-1 means creators never fix basics. Scaffold failures are bugs in the Scaffolder, not creator errors.
Sub-command routing: /create skill etc. skip the menu for experienced creators. Menu exists for first-time users who don't know the vocabulary.
Scaffold vs content separation: Content generated by /create bypasses /fill's Sparring Protocol → zero unique expertise. Structure (scaffold) and content (expertise) must stay separate. That separation is what makes the Engine produce gold.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

