Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hamzabellouch/agent-skills --skill prd-feature-specificationgit clone --depth 1 https://github.com/hamzabellouch/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hamzabellouch/agent-skills/prd-feature-specification)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/prd-feature-specification"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/prd-feature-specification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/prd-feature-specification"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/prd-feature-specification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.01058 |
| Opus 5.5 | $0.00030 | $0.00423 |
| Sonnet 5.5 | $0.00015 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
prd-feature-specification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Requirements Document (PRD) Specification Skill Guide
This skill standardizes the formulation of rigorous, unambiguous, and engineer-ready Product Requirements Documents (PRDs).
1. The Anatomy of an Actionable PRD
+------------------------------------------------------------------------+
| 1. Context & Why: Problem statement, customer evidence, business value|
+------------------------------------------------------------------------+
|
v
+------------------------------------------------------------------------+
| 2. Objectives & Measurable Success: Primary OKRs & North Star KPIs |
+------------------------------------------------------------------------+
|
v
+------------------------------------------------------------------------+
| 3. User Personas & Core Journeys: Step-by-step user workflow |
+------------------------------------------------------------------------+
|
v
+------------------------------------------------------------------------+
| 4. Functional Scope: Detailed requirements (P0 must-have, P1, P2) |
+------------------------------------------------------------------------+
|
v
+------------------------------------------------------------------------+
| 5. Non-Functional, Security & Edge Cases: Latency, scale, failures |
+------------------------------------------------------------------------+
2. Standard Production PRD Template
# [PRD] Automated Merchant Payout Reconciliation
| Metadata | Value |
|---|---|
| **Author** | Principal Product Manager |
| **Status** | In Review / Approved |
| **Target Release** | 2026-Q4 |
| **Engineering Lead**| Staff Backend Engineer |
---
## 1. Problem Statement & Opportunity
Merchants currently spend an average of 4.2 hours per week manually matching bank deposit summaries with daily settled orders. This friction leads to support escalations, billing disputes, and delayed monthly closing. Providing real-time, automated payout reconciliation will eliminate manual bookkeeping and increase 30-day merchant retention by 15%.
---
## 2. Measurable Goals & Success Metrics
- **Primary KPI:** Percentage of monthly transactions reconciled automatically without human manual intervention (> 98.5%).
- **Secondary KPI:** Reduction in payout-related support tickets (target: -60% within 60 days of launch).
- **Guardrail Metric:** Zero false-positive ledger balances or undetected discrepancies > $0.01.
---
## 3. User Personas & Scenarios
- **Persona:** Sarah, Finance Lead at a mid-market e-commerce brand (Processing $500k/mo).
- **Core Workflow:**
1. Sarah opens the Financial Dashboard every Monday morning.
2. The system displays a single unified card: "All 1,420 transactions from last week reconciled with Chase deposit #9821."
3. Sarah downloads an audited CSV export formatted directly for QuickBooks Online.
---
## 4. Functional Requirements & Prioritization
### P0 (Must Have for MVP Launch)
- **FR-101 (Automatic Matching Engine):** Match payouts against banking feed records using deterministic reference IDs and amount equality.
- **FR-102 (Discrepancy Triage UI):** If an amount does not match, flag the specific fee deduction or chargeback item and highlight variance in red.
- **FR-103 (Audit Export):** One-click download of reconciliation records with cryptographic SHA-256 batch hash.
### P1 (Post-MVP Fast Follow)
- **FR-201 (Webhook Alert):** Notify accounting software via Webhook on completed daily reconciliation.
### Out of Scope (Explicit Non-Goals)
- Multi-currency forex hedging calculation (handled in Phase 2).
- Automatic tax filing submission to tax authorities.
---
## 5. Non-Functional Requirements & Security
- **SLA & Latency:** Automated reconciliation batch must complete within 120 seconds of receiving banking webhook.
- **Security & Privacy:** All banking account identifiers must be masked (e.g., `****1234`).
- **Auditability:** Every manual override by a user must log user ID, timestamp, and rationale.
---
## 6. Release Checklist & Rollout Strategy
- [ ] Internal Dogfooding (Alpha: 2 weeks with 10 design partners)
- [ ] Feature Flag Canary Release: 5% -> 25% -> 100% over 10 business days
- [ ] Runbook verified with Support & Operations teams
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 118 lines · 75 tokens per session scan A c4d929f27675
prd-feature-specification is a skill published in the GitHub repository hamzabellouch/agent-skills (8 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,058 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
Other skills, from other repositories
spec-create
Create a structured feature specification with self-contained task files organized into parallel execution batches. Use this skill when the user says "create a spec", "plan this feature", "write up an implementation plan", "break this into tasks", or after any planning conversation where the user wants to capture…
polya-plan
Phase 2 of the Pólya Heuristic Coder: Devising a Plan, Land and Expand Strategy, Vertical Tracer Bullets, Expand-Contract Pattern, Contingency Plan B, Task Sizing, and The Pause Rule (docs/plan/{slug}-plan.md).
to-prd
Optional Phase 0.5 of the Pólya Heuristic Coder: Product Requirements Document (PRD) detailing User Stories, SMART Acceptance Criteria, Personas, and Business Goals.
architectural-engineering-manager
Use when a task needs the judgment of an Architecture/Engineering firm or department manager — pricing a project fee (lump sum vs. hourly vs. % of construction cost), staffing a project against backlog, evaluating scope creep on a fixed-fee job, managing professional liability exposure, or deciding whether to pursue a…
compensation-benefits-manager
Use when a task needs the judgment of a Compensation and Benefits Manager — designing or evaluating a pay structure/leveling system, benchmarking compensation against market, deciding on a benefits package tradeoff, or auditing for pay equity issues. Narrower and more specialized than the broader hr-people-manager…
computer-systems-analyst
Use when a task needs the judgment of a Computer Systems Analyst — running requirements elicitation and gap analysis against a target system, writing a feasibility study for a build-vs-buy-vs-customize decision, designing a system integration approach (point-to-point vs middleware vs API-led), scoping data-migration…