Manage Coding Agent Workflows
Coding-agent projects can drift when tasks, scope, and checks are vague. This skill gives PM templates and review rules that keep Claude, Codex, and Claude Code work bounded and verifiable.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "coding-agent-pm" from https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm.md and its manifest at https://skillstore.io/api/skills/kiwi-phantomworks-coding-agent-pm/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "coding-agent-pm". A founder wants an agent to add a small checkout improvement without touching unrelated pages.
Expected outcome:
Using "coding-agent-pm". A product manager needs to decide whether to accept an agent-completed bug fix.
Expected outcome:
The skill produces a review checklist covering scope, behavior, code quality, verification, security, privacy, and remaining risks.
Using "coding-agent-pm". A product engineer wants to split a larger feature across several agent sessions.
Expected outcome:
The skill outlines separate assignments with owned files, expected outputs, validation steps, and review gates for each agent task.
All 19 static findings are false positives after context review. The hidden-directory entries are documented installation paths, the backtick hits are Markdown filename formatting, and the reconnaissance hits are benign marketing or review checklist text.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/kiwi-phantomworks-coding-agent-pm/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/kiwi-phantomworks-coding-agent-pm.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Bridge AI Labs. (2026). coding-agent-pm security audit report (audit version 4) [Author version 1.0.1]. Skillstore. https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm/audits/4@techreport{bridge-ai-labs-kiwi-phantomworks-coding-agent-pm-2026,
author = {Bridge AI Labs},
title = {coding-agent-pm security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm/audits/4},
note = {Author version 1.0.1}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "coding-agent-pm security audit report (audit version 4)"
version: "1.0.1"
type: report
authors:
- name: "Bridge AI Labs"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/kiwi-phantomworks-coding-agent-pm/audits/4"
identifiers:
- type: other
value: "skillstore:kiwi-phantomworks-coding-agent-pm:audit:4"
description: "Skillstore immutable audit report identifier"
Create a clear brief with scope, context, acceptance criteria, and validation steps before a coding agent starts work.
Check whether a completed agent change stayed in scope, met requirements, ran checks, and reported remaining risks.
Split implementation work into bounded tasks with separate file ownership, expected outputs, and review checkpoints.
Use coding-agent-pm to turn this request into a short agent brief. Include the outcome, in-scope files, out-of-scope files, acceptance criteria, and validation commands.
Use coding-agent-pm to prepare an implementation plan for this feature. Keep the plan limited to the named modules, identify required context, and define checks the agent must run before final delivery.
Use coding-agent-pm to review this agent result. Put findings first, compare the change against the original acceptance criteria, and list any missing checks, scope drift, or security and privacy risks.
Use coding-agent-pm to split this project into independent coding-agent assignments. Give each task a disjoint write scope, expected output, acceptance criteria, validation commands, and a human review checkpoint.
Author
Bridge AI LabsLicense
MIT
Author version
v1.0.1
Skillstore revision
r1
Ref
b8ca75d2c0a7e7102978993058777d82b8ab2610
Maintenance freshness
7/18/2026
Usage
2 downloads · 0 views
File structure
Audit NestJS Code with Evidence-Backed Findings
by amirtaherkhani
NestJS repositories can hide boundary flaws and runtime risks that lint results alone cannot reveal. This skill combines local evidence collection and semantic review into one prioritized report.
Review Code with Structured Quality Checks
by alirezarezvani
Code reviews can miss quality, security, and maintainability issues. This skill guides structured reviews with scripts, checklists, and report generation.
Build Firecrawl Search Workflows
by firecrawl
Teams need reliable source discovery before scraping or answering questions. This skill guides Firecrawl search integration, result selection, and follow-up extraction decisions.
Create Verifiable Agent Loop Specs
by zhangzeyu99-web
Vague coding-agent tasks drift, repeat work, and report success without evidence. Ariadne Loop turns them into bounded loop specs with verifiers, stop rules, and human gates.
Review GitHub Pull Requests with CLI Utilities
by Bind
Pull request reviews require repeated eligibility checks, guideline discovery, and precise feedback. This skill documents a consistent CLI workflow for those tasks.
Optimize React and Next.js Code
by vercel-labs
React and Next.js applications often lose performance through waterfalls, large bundles, and avoidable re-renders. This skill gives Claude, Codex, and Claude Code concrete review rules for faster frontend work.