Install
$ agentstack add skill-mehtab78-skills-agency ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Running a service agency
Handle the operational load (intake, pricing, projects, deliverables, team) so the user can spend their time on clients and strategy. Works for any service agency: marketing, development, design, consulting, content, automation.
Where things live
Keep agency data under ~/agency/:
~/agency/
├── clients/ # one file per client (+ index.md)
├── projects/ # active project tracking
├── templates/ # reusable proposals, briefs, reports
├── knowledge/ # SOPs, case studies, learnings
└── config.md # rates, margins, team
The core loops
- Intake: a brief arrives (email, audio, notes) → extract scope, budget,
timeline → produce a structured brief → flag red flags → open a client folder. See references/onboarding.md.
- Pricing: take the scope → apply the rate card and complexity multipliers →
build a proposal → sanity-check against similar past projects. See references/pricing.md.
- Projects: one board of every active project → alert on deadlines → catch
stalls → weekly status per client. See references/projects.md.
- Deliverables: turn rough input into a reviewed, on-brief deliverable, in
the right formats. See references/deliverables.md.
Rules that keep an agency healthy
- Nothing goes to a client without the user's approval: proposals, messages,
deliverables are all drafts for review.
- Track cost against estimate and speak up the moment a project starts losing
money.
- Learn from corrections: fold them back into templates and the knowledge
base (references/feedback.md).
- Carry context across sessions: refer to each client's history, don't start
cold.
References
| Area | File | |------|------| | Client intake & discovery | references/onboarding.md | | Pricing, estimates, proposals | references/pricing.md | | Project board & deadlines | references/projects.md | | Client communication | references/communication.md | | Producing deliverables | references/deliverables.md | | Team & subcontractor coordination | references/team.md | | Specifics per agency type | references/by-type.md | | Learning & improvement system | references/feedback.md |
Set up ~/agency/config.md with your rates, team, and margins first; the pricing and project files read from it. Format is in references/pricing.md.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mehtab78
- Source: mehtab78/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.