trust-ladder-workflow
Per-company trust state procedure (learning / trial / operating).
Skill by petr-royce
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/elophanto-trust-ladder-workflow
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: sales, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/trust-ladder-workflow
What's inside
- Skill name
trust-ladder-workflow- Description
- Per-company trust state procedure (learning / trial / operating). When a live outreach tool refuses, names the canonical draft replacement.
- License
- MIT
- Metadata
- phase: 9 · author: petr-royce · version: 1.1.0
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Trust ladder workflow — DO NOT spam Every ABE company has a 3-state trust ladder gating live outbound communication: | State | Live outreach | Per-call approval | Default | |---|---|---|---| | `learning` | **REFUSED** — draft only | n/a | new companies | | `trial` | allowed | MODERATE | promoted after voice approval | | `operating` | allowed | within budget | mature | ## Triggers - email_send / email_reply / prospect_outreach / twitter_post - send email / send outreach / post on X - can you message / can you reach out - trust state / trust ladder / promote trust ## Procedure 1. Check trust state for active company (`company_report` headline or `[COMPANY] trust=` in snapshot). 2. **If `learning`**: live tool refuses. Call the draft equivalent: - `email_send`/`email_reply` → `email_draft(to, subject, body)` - `prospect_outreach` → `outreach_draft(prospect_id, body, channel)` - `twitter_post` → `post_draft(content)` Drafts land at `companies/<slug>/drafts/<kind>/pending/`. Voice contract lints body before persist (see [[voice-extraction-workflow]] if lint fails). Tell operator what you drafted. 3. **If `trial`**: live tools work but each gates MODERATE. Be deliberate — operator just promoted you. Produce ONE quality send, not a batch. 4. **If `operating`**: full autonomy within budget. Voice contract still lints. ## When a live tool refuses Error message names the replacement and operator action. Example: ``` email_send blocked: company 'acme' in trust state 'learning' — use email_draft. Operator command: elophanto company trust acme trial. ``` - Don't retry the live tool (gate is operator-decided, not transient). - Call the named draft tool. - Tell operator what you drafted + remind them of the promotion command. ## Promotion (operator only) - **Never call `company_trust_set` yourself.** Operator decides via CLI or via the tool with explicit MODERATE approval. - Surface readiness signals: voice.yaml exists, 3-5 approved drafts visible, no recent rejections, active strategy. - After operator promotes to `operating`: live sends become autonomous. Demote with `elophanto company trust <slug> trial` if it goes sideways. ## Hard rules - ❌ Never `company_trust_set` to promote yourself. - ❌ Never re-call a live tool after trust-gate refusal. - ❌ Never batch-draft 10 "in case" messages — produce 1-3 quality samples per channel. - ❌ Never silently swap channels when one refuses. ## Verify - [ ] Trust state checked before any live outbound call - [ ] On gate refusal: draft tool called, not retried - [ ] On promotion request: I did NOT call `company_trust_set`
From elophanto/EloPhanto, MIT.
More from elophanto/EloPhanto
- 0.778score
metaplex
metaplex-foundation
Metaplex development on Solana — NFTs, tokens, compressed NFTs, candy machines, token launches.
SkillAFreshness: A★ 106Claude Code +9 - 0.778score
solana-dev
Solana Foundation
Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana…
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
strategy-foundations
petr-royce
Marketing-strategy foundations distilled from the Phase 11 strategy generator.
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
b2c-marketing-voice
petr-royce
Anti-slop principles for B2C social posts and outreach.
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
12-principles-of-animation
raphael-salaja
Audit animation code against Disney's 12 principles adapted for web.
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
voice-extraction-workflow
petr-royce
Produce a voice contract from operator-curated exemplars (Phase 10).
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
drive-business
petr-royce
Canonical workflow for "drive my business" / "operate this company".
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
strategy-pipeline
petr-royce
Phase 11 procedure — capabilities → set_strategy_inputs → plan → apply → approve, plus 3-path blocker resolution (ask / build / defer).
SkillAFreshness: A★ 106Claude Code +9 - 0.769score
integrating-jupiter
jupiter
Comprehensive guidance for integrating Jupiter APIs (Ultra Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio…
SkillAFreshness: A★ 106Claude Code +9 - 0.636score
pikastream-video-meeting
elophanto
Join a Google Meet or Zoom call as a video meeting agent via PikaStreaming.
SkillAFreshness: A★ 106Claude Code +9 - 0.636score
solana-kit-migration
elophanto
Helps developers understand when to use @solana/kit vs @solana/web3.js (v1), provides migration guidance, API mappings, and handles edge cases for Solana…
SkillAFreshness: A★ 106Claude Code +9 - 0.634score
plan-review-design
elophanto
Use when reviewing the UX/UI portion of a plan before implementation — rate each design dimension 0-10, explain what would make it a 10, and patch the plan to…
SkillAFreshness: A★ 106Claude Code +9
Signals
- Stars
- 106
- Forks
- 9
- Open issues
- 2
- Last commit (this folder)
- May 26, 2026 (5 months ago)
- Last release
- Oct 1, 2026 (27 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.1.0
- License
- MIT
- Repository
- github.com/elophanto/EloPhanto
- Website
- elophanto.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from petr-royce
- 0.777score
b2c-marketing-voice
petr-royce
Anti-slop principles for B2C social posts and outreach.
SkillAFreshness: A★ 106Claude Code +9 - 0.777score
strategy-foundations
petr-royce
Marketing-strategy foundations distilled from the Phase 11 strategy generator.
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
drive-business
petr-royce
Canonical workflow for "drive my business" / "operate this company".
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
strategy-pipeline
petr-royce
Phase 11 procedure — capabilities → set_strategy_inputs → plan → apply → approve, plus 3-path blocker resolution (ask / build / defer).
SkillAFreshness: A★ 106Claude Code +9 - 0.773score
voice-extraction-workflow
petr-royce
Produce a voice contract from operator-curated exemplars (Phase 10).
SkillAFreshness: A★ 106Claude Code +9
Cite this page
trust-ladder-workflow skill. Agent Mart. https://agentmart.dev/skills/elophanto-trust-ladder-workflow (last updated 2026-10-24)