Builds versioned system prompt of an artifact (platform-sku, product, diagnostic) from spec + process-map + baseline-cost + Tier 1 helpers. Tier 3 operational — produces prompts/{artifactid}/v{version}/system.md with sha256:16 prompthash, mandatory C6 instrumentation, and zero per-tenant hardcode (C8). Triggers recalcuniteconomics.
EnglishCalculates baseline economics for C3 gate. For agentic (aienabled=true): human cost × volume → minpriceperoutcome via costperoutcome model. For platform (aienabled=false): (infra + support + maintenance) / revenue → platformmargin model. Persists docs/clients/{clientid}/baseline-cost-{processid}.md or docs/modules/{moduleid}/delivery-economics-{moduleid}.md.
EnglishLoads and exposes the organization's DNA (purpose, mission, values, north-star) in compact YAML for Tier 1 strategic context. Caches under foundrycache.dna for downstream skills.
EnglishConducts a guided 10-block Phase 0 diagnostic session with the client decision-maker — qualifies problem, measures human baseline, proposes contractual outcome, validates ICP fit, and persists docs/clients/{clientid}/diagnostic.md. Implements C1 and opens C2.
EnglishGenerates eval cases for an artifact from real human/agent pairs (preferred) or declared synthetic cases (fallback). Persists in evals/{artifactid}/cases/case-{n}.md. Tier 3 — implements C4 (≥30 cases per outcomecategory before SHADOW), C2 (justified ground truth), C6 (traceability to source trace).
EnglishOrchestrates the monthly audit of a Foundry-consuming project against Constitution C1-C8 (+ declared extensions). Loads manifest, primes Tier 1 caches via L0 loaders, parallelizes per-principle checks via task sub-agents, consolidates findings in docs/foundry/audits/{YYYY-MM}.md compatible with reviewer/output-schema.json. Native Deep Agents skill (no Claude Code source).
EnglishLoads and exposes the organization's Ideal Customer Profile (segments, qualification signals, anti-ICP) in compact YAML for Tier 1 strategic context.
EnglishLoads and exposes the organization's offerings catalog (products, platform-SKUs, diagnostics) with lifecyclestage and pricingmodel in compact YAML for Tier 1.
EnglishCoordinates SHADOW mode (C4) — agent runs parallel to human, output NEVER delivered/billed, measures human/agent agreement, produces promotion report. Tier 3 — enforces C4 mechanically (≥14 days, delivered:false, billing:0, prompthash immutable during window) and produces recommendation BUT does not auto-promote.
English
AGENT SKILLS ATLASIncludes Artifact Prompt Builder, Baseline Cost Builder, Company Dna, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Artifact Prompt Builder
Builds versioned system prompt of an artifact (platform-sku, product, diagnostic) from spec + process-map + baseline-cost + Tier 1 helpers. Tier 3 operational — produces prompts/{artifactid}/v{version}/system.md with sha256:16 prompthash, mandatory C6 instrumentation, and zero per-tenant hardcode (C8). Triggers recalcuniteconomics.
Baseline Cost Builder
Calculates baseline economics for C3 gate. For agentic (aienabled=true): human cost × volume → minpriceperoutcome via costperoutcome model. For platform (aienabled=false): (infra + support + maintenance) / revenue → platformmargin model. Persists docs/clients/{clientid}/baseline-cost-{processid}.md or docs/modules/{moduleid}/delivery-economics-{moduleid}.md.
Company Dna
Loads and exposes the organization's DNA (purpose, mission, values, north-star) in compact YAML for Tier 1 strategic context. Caches under foundrycache.dna for downstream skills.
Diagnostic Runner
Conducts a guided 10-block Phase 0 diagnostic session with the client decision-maker — qualifies problem, measures human baseline, proposes contractual outcome, validates ICP fit, and persists docs/clients/{clientid}/diagnostic.md. Implements C1 and opens C2.
Eval Case Author
Generates eval cases for an artifact from real human/agent pairs (preferred) or declared synthetic cases (fallback). Persists in evals/{artifactid}/cases/case-{n}.md. Tier 3 — implements C4 (≥30 cases per outcomecategory before SHADOW), C2 (justified ground truth), C6 (traceability to source trace).
Foundry Auditor
Orchestrates the monthly audit of a Foundry-consuming project against Constitution C1-C8 (+ declared extensions). Loads manifest, primes Tier 1 caches via L0 loaders, parallelizes per-principle checks via task sub-agents, consolidates findings in docs/foundry/audits/{YYYY-MM}.md compatible with reviewer/output-schema.json. Native Deep Agents skill (no Claude Code source).
Icp Loader
Loads and exposes the organization's Ideal Customer Profile (segments, qualification signals, anti-ICP) in compact YAML for Tier 1 strategic context.
Offerings Loader
Loads and exposes the organization's offerings catalog (products, platform-SKUs, diagnostics) with lifecyclestage and pricingmodel in compact YAML for Tier 1.
Shadow Mode Runner
Coordinates SHADOW mode (C4) — agent runs parallel to human, output NEVER delivered/billed, measures human/agent agreement, produces promotion report. Tier 3 — enforces C4 mechanically (≥14 days, delivered:false, billing:0, prompthash immutable during window) and produces recommendation BUT does not auto-promote.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Artifact Prompt Builder skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.