New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Report A Hazard

by mohitagw15856 in mohitagw15856/pm-claude-skills

Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right…

MITAuto-check passed

Install Report A Hazard

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill report-a-hazard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills report-a-hazard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/report-a-hazard .claude/skills/report-a-hazard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
report-a-hazard
GitHub stars
1.4k
Token cost
~1.4k tokens
SKILL.md length
663 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right…

  • Works in 5 steps: Triage danger first. If it's an… → Route to the owner. Potholes/roads,… → Write the report that gets actioned.… → …
  • Someone says how do I report a pothole/hazard/violation
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework and Output Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Report A Hazard is an agent skill from mohitagw15856/pm-claude-skills. Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right department, the details that get it actioned, a tracking reference, and an escalation path if it's ignored. Use when someone says 'how do I report a pothole/hazard/violation', 'the council won't fix X', or 'who do I call about Y'. Produces a report ready to submit, the right channel, and a follow-up plan.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Someone says how do I report a pothole/hazard/violation
  • The council wont fix X
  • Who do I call about Y

Example prompts

  • “s ignored. Use when someone says”
  • “the council won”
  • “who do I call about Y”
  • “/report-a-hazard”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Triage danger first. If it's an immediate threat to life — gas leak, live wire,
  2. Route to the owner. Potholes/roads, streetlights, fly-tipping, drainage,
  3. Write the report that gets actioned. Precise location beats everything (an exact
  4. Capture the reference and set the clock. Get a tracking/reference number, note
  5. Escalate when ignored. If nothing happens: re-contact with the reference,

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Report A Hazard loads about 1.4k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 663 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~129
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 663 words, ~1,399 tokens.

Download SKILL.mdSave it as .claude/skills/report-a-hazard/SKILL.md (or your agent's skills folder).
name
report-a-hazard
description
Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right department, the details that get it actioned, a tracking reference, and an escalation path if it's ignored. Use when someone says 'how do I report a pothole/hazard/violation', 'the council won't fix X', or 'who do I call about Y'. Produces a report ready to submit, the right channel, and a follow-up plan.

Report A Hazard Skill

Reporting a public problem should be simple and usually isn't: the report goes to the wrong department, lacks the details needed to action it, or vanishes with no reference number, so nothing happens and the reporter gives up. Councils and agencies do fix things — they fix the reports that land in the right queue with a precise location, evidence, and a hazard framing that raises the priority. This skill writes that report, routes it to the channel that owns it, captures a tracking reference, and sets up the escalation for when the first report is ignored.

What This Skill Produces

  • The right channel: which department/agency owns this problem and the best way to reach them (the official app/portal/line — many places have a dedicated report-it system)
  • A submit-ready report: precise location, what/when/how-bad, a safety framing where genuine, and a photo checklist — the details that move it from "logged" to "scheduled"
  • A tracking plan: getting a reference number and what response time is reasonable before chasing
  • An escalation path: what to do if it's ignored or bounced — re-report with the reference, go to the supervisor/councillor, and the safety-emergency line for anything actually dangerous now

Required Inputs

Ask for (if not already provided):

  • The problem and exactly where it is (an address, cross-streets, a what3words/pin — vague location is the #1 reason reports stall)
  • How dangerous it is right now (a live gas smell or downed power line is an emergency, not a report) and who's affected
  • Where they are (country/area — channels are local) and whether they've reported it before
  • Any evidence they have (photos, dates, recurrence)

Framework

  1. Triage danger first. If it's an immediate threat to life — gas leak, live wire, structural collapse, active flooding — that's an emergency line, not a hazard report. The skill separates "report it" from "call emergency services now" before anything else.
  2. Route to the owner. Potholes/roads, streetlights, fly-tipping, drainage, building/code violations, environmental hazards each have a different owner (roads authority vs council vs utility vs environmental agency). Reporting to the wrong one is the classic dead end; identify the owner and its official report channel.
  3. Write the report that gets actioned. Precise location beats everything (an exact address or pin, not "near the shops"); then what it is, how long it's been there, how bad, who's at risk, and photos. Frame genuine safety impact honestly — a "hazard to cyclists/children" is prioritized over a cosmetic complaint, but don't inflate.
  4. Capture the reference and set the clock. Get a tracking/reference number, note the channel's stated response time, and diarize a chase date. A report you can't reference is a report you can't escalate.
  5. Escalate when ignored. If nothing happens: re-contact with the reference, escalate to a supervisor or your local councillor ([[elected-rep-letter]]), and for persistent public-safety issues, add visibility. Multiple neighbors reporting the same thing raises priority — say so.
Show full SKILL.md (185 more words)Show less

Output Format

## Is it an emergency? (check first)
[If immediate danger → the emergency line, not this. Otherwise, proceed.]

## The right channel
[Department/agency that owns it · the official report route for your area]

## Your report (submit this)
Exact location: … · What/when/severity: … · Who's at risk: … · Photos: [checklist]

## Track it
[Get a reference number · reasonable response time · when to chase]

## If it's ignored
[Re-report with reference → supervisor/councillor → visibility · neighbors reporting too]

Quality Checks

  • Immediate-danger cases are diverted to emergency services before anything else
  • The report is routed to the department that actually owns the problem
  • The report leads with a precise, unambiguous location
  • Getting and keeping a tracking reference is built in
  • An escalation path exists for the ignored report

Anti-Patterns

  • Do not treat a live emergency as a routine report — triage danger first
  • Do not assert a specific area's channels or response times as fact — route to the official report system and verify
  • Do not inflate severity to jump the queue — an honest safety framing works; crying wolf burns credibility
  • Do not submit without a precise location — it's the difference between fixed and filed
  • Do not stop at one ignored report — the escalation is where stubborn problems get fixed

[[elected-rep-letter]] and [[speak-at-the-council]] for escalation; [[permit-navigator]] for the other side of local government; [[scam-message-decoder]] if a "pay to fix your report" message appears.

Example Trigger Phrases

  • "How do I report a pothole?"
  • "Who do I call about a broken streetlight?"
  • "Report illegal dumping on our street."
  • "The council won't fix this: what now?"

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/report-a-hazard of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Report A Hazard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Report A Hazard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Report A Hazard this skillmohitagw15856/pm-claude-skills1.4k—~1.4kAutomated safety check: PassMIT
Hermes Agent Skill AuthoringNousResearch/hermes-agent252k—~3.6kAutomated safety check: PassMIT
Configuring Oauth2 Authorization Flowmukul975/Anthropic-Cybersecurity-Skills34k—~1.7kAutomated safety check: PassApache-2.0
Authoring Skillsvercel/next.js143k—~1kAutomated safety check: PassMIT
Abp Authorizationabpframework/abp14k—~1.3kAutomated safety check: PassLGPL-3.0
Is This A Problemanthropics/claude-for-legal9.6k2 repos~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • Hermes Agent Skill Authoring

    NousResearch/hermes-agent

    Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~3.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Configuring Oauth2 Authorization Flow

    mukul975/Anthropic-Cybersecurity-Skills

    Configures secure OAuth 2.0 authorization flows, including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant, covering flow selection, PKCE implementation, token…

    34k GitHub stars~1.7k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Authoring Skills

    vercel/next.js

    Official

    How to create and maintain agent skills in .agents/skills/. An agent skill from vercel/next.js.

    143k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Abp Authorization

    abpframework/abp

    ABP permission system - PermissionDefinitionProvider, [Authorize] attribute, CheckPolicyAsync, IsGrantedAsync, ICurrentUser, IPermissionManager, multi-tenancy side.

    14k GitHub stars~1.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Is This A Problem

    anthropics/claude-for-legal

    Official

    Fast "is this a problem?" answer for the quick Slack question — pattern-matches against your calibration.

    9.6k GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed

  • Implementing GCP Binary Authorization

    mukul975/Anthropic-Cybersecurity-Skills

    Implements GCP Binary Authorization end to end, including creating KMS-backed attestors, Container Analysis notes, deploy-time policies, and signing image attestations, so that only trusted…

    34k GitHub stars~2k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo

  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Report A Hazard

What does Report A Hazard do?

Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right…. Report A Hazard is an agent skill from mohitagw15856/pm-claude-skills. Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right department, the details that get it actioned, a tracking reference, and an escalation path if it's ignored.

When should I use Report A Hazard?

Report A Hazard fits situations like: someone says how do I report a pothole/hazard/violation; the council wont fix X; who do I call about Y.

How do I install Report A Hazard in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill report-a-hazard -a claude-code`. Or copy the skill folder (skills/report-a-hazard in mohitagw15856/pm-claude-skills) into .claude/skills/report-a-hazard in your project. Claude Code loads it when a task matches its description.

How do I install Report A Hazard in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill report-a-hazard -a codex`. Or copy the skill folder (skills/report-a-hazard in mohitagw15856/pm-claude-skills) into .agents/skills/report-a-hazard in your project. Codex loads it when a task matches its description.

Can I use Report A Hazard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill report-a-hazard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/report-a-hazard, .gemini/skills/report-a-hazard, .github/skills/report-a-hazard and .opencode/skills/report-a-hazard in your project.

What does Report A Hazard need to run?

SKILL.md names no scripts, command-line tools or credentials: Report A Hazard is instructions for the agent only.

Does Report A Hazard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Report A Hazard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Report A Hazard use?

Report A Hazard is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Report A Hazard use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Report A Hazard?

Skills that share tags, products or a category with Report A Hazard: Hermes Agent Skill Authoring (NousResearch/hermes-agent, 252k stars), Configuring Oauth2 Authorization Flow (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Authoring Skills (vercel/next.js, 143k stars) and Abp Authorization (abpframework/abp, 14k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Report A Hazard?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.