agentleFS
itseffiitseffi/agentic-os/.agents/skills/davci/SKILL.md

davci

Skill114 starsChanged 10 months agoMITView on GitHub

Define clear decision rights - Decider, Approver, Veto, Consulted, Informed. Use when clarifying who decides.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When you need to clarify who decides, approves, and must be consulted on a decision.

    line 12
  2. Distinctive:

    Must be one person only

    line 37
  3. Distinctive:

    If yes, name person one level up

    line 41
  4. Distinctive:

    Keep targeted to those who need it

    line 54
  5. Distinctive:

    Escalation: If blocked 24h, escalate to whom?

    line 59
  6. Distinctive:

    Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

DAVCI Decision Rights

Define clear decision rights using the DAVCI framework.

When to Use

When you need to clarify who decides, approves, and must be consulted on a decision.

The Framework

RoleDefinitionRules
D - DeciderSingle person accountable for outcomeExactly one per decision
A - ApproverCan override the DeciderOptional; cannot be the D
V - VetoCan block for specific domainOne per domain; time-boxed
C - ConsultedHas input before decisionKeep to 5 or fewer
I - InformedNeeds to know after decisionKeep targeted

The Process

1. Define the Decision Object

Be specific about what's being decided:

  • Clear title
  • Concrete deadline
  • Decision type (Strategy, Scope, Design, Technical, Process, Risk, Commercial)

2. Assign Roles

Decider (D):

  • Who is accountable for the outcome?
  • Must be one person only

Approver (A):

  • Does D need air cover for risk/budget/politics?
  • If yes, name person one level up

Veto (V):

  • Which domains apply? (Security, Legal, Privacy, Brand, Compliance)
  • One person per domain
  • Set veto window (default: 48 hours)

Consulted (C):

  • Who has unique information to improve the decision?
  • Cap at 5; merge by role if needed

Informed (I):

  • Who must act after or needs awareness?
  • Keep targeted to those who need it

3. Add Decision Metadata

  • Deadline: Date and time
  • Escalation: If blocked 24h, escalate to whom?
  • Success test: One checkable sentence
  • Comms plan: Channel, audience, timing

Output Format

Decision: [title]
Deadline: [date/time]
Type: [Strategy/Scope/Design/Technical/Process/Risk/Commercial]

D: [name, role]
A: [name, role] or None
V: [Domain - name, window hours]
C: [role/name]; [role/name]
I: [role/name]; [role/name]

Escalation: [name, role]
Success test: [single checkable sentence]
Comms: [channel + audience + timing]

When Not to Use

Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.