Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
User has an outcome and gap (per role-design.md) and is deciding how to fill it. Or an FTE that isn't working and wonders about converting to contractor. Or is pitched an agency and isn't sure if it beats hiring.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
66 lines · 862 words
User has an outcome and gap (per role-design.md) and is deciding how to fill it. Or an FTE that isn't working and wonders about converting to contractor. Or is pitched an agency and isn't sure if it beats hiring. Load when the question is "FTE or contractor" or "agency or in-house."
Four work-structures, one decision matrix, one onboarding plan.
User has an outcome and gap (per role-design.md) and is deciding how to fill it. Or an FTE that isn't working and wonders about converting to contractor. Or is pitched an agency and isn't sure if it beats hiring.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Hiring structure skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
What it covers
When to load this mode
Procedure
Decision rules
Anti-patterns
Before / after
Full-time employee (FTE). Highest commitment, slowest to start (60-120 days to ramped), highest exit cost. Total cost typically 1.25-1.4× salary in the US once benefits, taxes, equipment, and overhead are counted. Right when the outcome is ongoing, requires deep business context, and warrants a permanent owner.
Contractor. Low commitment, fast (1-3 weeks), low exit cost. Hourly or project-based, typically 1.5-2× equivalent FTE hourly rate. Right when work is bounded, deliverable-defined, and doesn't require sitting inside the business.
Fractional. A senior practitioner one-to-two days a week, usually as a contractor. Mid commitment, fast (2-4 weeks), $4-12k/month. Right when work is judgment-heavy and needs a senior person but volume doesn't warrant a full seat. Common for CFO, CMO, head of people, head of product early-stage.
Agency. A team behind one point of contact. Low founder-time, fast (1-4 weeks), retainer or project. Right for known playbooks (paid acquisition, SEO content, design systems, accounting close). Wrong when work needs deep product context.
2. Run the decision matrix. Three questions, in order:
Ongoing or bounded? Ongoing → FTE or fractional. Bounded → contractor or agency.
Judgment-heavy or execution-heavy? Judgment → FTE (senior) or fractional. Execution → contractor, agency, or FTE (mid/junior).
Does it require sitting inside the business and accumulating context? Yes → FTE or fractional. No → contractor or agency.
The matrix gives a default; cash constraint and risk tolerance adjust from there.
3. Affordability sanity check before sourcing. Loaded twelve-month cost versus expected outcome contribution. Not breakeven math (that's Coin) — if this seat delivers, does the math work? If not, you have the wrong work-structure or outcome, not the wrong candidate.
4. Stage the structure as the company grows. Common arc: contractor or agency for a new function; fractional once ongoing but sub-full-seat; FTE once core; then a team under that FTE at scale. Skipping straight to FTE on a new function is the most common founder mistake. The early contractor or fractional teaches the founder what the seat actually is before the long commitment.
5. Build an onboarding plan that mirrors the outcome doc. Same one-pager, three time horizons:
Days 1-7. Meet dependencies and dependents. Read docs. Ship one small thing. Goal: proof of arrival, not a project.
Days 8-30. Own one named outcome end-to-end. Not all; one. Weekly founder 1:1s — agenda is the outcome doc, not vibes.
Days 31-90. Own full scope. Day 90: structured review against the doc. Which outcomes are tracking, which aren't, and what does the seat need from the team. Day 90 is also the latest acceptable point to recognize a miss-hire — past it, correction cost rises sharply.
First instance of a new function: contractor or agency. Almost always. The founder doesn't yet know enough to define the FTE.
Fractional beats unfilled FTE. A senior fractional two days a week now beats a six-month search.
Don't convert contractor-to-FTE without re-running role design. Bounded work and the FTE seat have different shapes. Treat as a new hire.
Day 90 review is non-negotiable. Scheduled at offer-signing. Missing it costs months.
Onboarding plan ships with the offer. Day-one shouldn't be a question of what to do.
FTE-first for unknown work. Twelve-month commitment to a seat the founder hasn't pressure-tested.
Agency for context-heavy work. Six months of context-building that walks out at contract end.
Endless contractor extensions for ongoing work. Higher rate, less commitment, no context — eventually just a worse FTE.
Fractional as permanent at scale. Once full-seat, fractional is a bottleneck. Convert or hire under them.
No onboarding because "they're senior." Senior hires fail without onboarding at the same rate as juniors — just more expensively.
Before: Founder needs paid-acquisition work. Posts an FTE growth marketer role. Four-month search, hires at $140k loaded. Three months in, realizes the work was a $4k/month agency engagement.
After: Same founder runs the matrix: bounded, execution-heavy, no deep product context required. Engages an agency at $4k/month for six months. Learns what the function actually is and what an in-house seat would need to own. Twelve months later, hires an FTE — with a real outcome doc — to own what the agency taught them was full-seat work.
SKILL.md
66 lines · 862 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Hiring structure bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for