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

Driver Incident Investigation

by mohitagw15856 in mohitagw15856/pm-claude-skills

Investigate a commercial vehicle incident so the record is defensible and the cause is actually found — evidence secured in the first hours, the preventability decision made on stated criteria, and…

MITAuto-check passed

Install Driver Incident Investigation

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill driver-incident-investigation -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills driver-incident-investigation --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/driver-incident-investigation .claude/skills/driver-incident-investigation && 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
driver-incident-investigation
GitHub stars
1.4k
Token cost
~1.7k tokens
SKILL.md length
746 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Investigate a commercial vehicle incident so the record is defensible and the cause is actually found — evidence secured in the first hours, the preventability decision made on stated criteria, and…

  • Works in 7 steps: Secure the perishable evidence first.… → Take the driver's account early and… → Reconstruct from evidence, not… → …
  • Asked to investigate a vehicle accident
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Secure Evidence,… and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Driver Incident Investigation is an agent skill from mohitagw15856/pm-claude-skills. Investigate a commercial vehicle incident so the record is defensible and the cause is actually found — evidence secured in the first hours, the preventability decision made on stated criteria, and corrective action aimed at the system rather than the driver. Use when asked to investigate a vehicle accident, run a post-accident review, decide whether a collision was preventable, or write an incident report for a fleet. Produces the evidence checklist, the sequence reconstruction, the preventability determination…

Its SKILL.md is about 1.7k 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

  • Asked to investigate a vehicle accident
  • Run a post-accident review
  • Decide whether a collision was preventable
  • Write an incident report for a fleet

Example prompts

  • “/driver-incident-investigation”

Workflow steps

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

  1. Secure the perishable evidence first. Telematics and camera footage overwrite on a cycle. Photographs, the load, and the vehicle's…
  2. Take the driver's account early and alone. Before it is discussed with colleagues. Ask what happened, not whether they were at fault — and…
  3. Reconstruct from evidence, not narrative. Speed, following distance, braking, and timing come from data. Use the account to explain the…
  4. Decide preventability against written criteria. Could a reasonably prudent driver have avoided it, given what they could perceive? Record…
  5. Look past the driver. Was the schedule achievable? Was the driver fatigued? Was the fault reported before? Was the training adequate? Most…
  6. Act on the actual contributor. Retraining a driver who was awake for sixteen hours because dispatch built the run that way is a corrective…
  7. Meet the notification deadlines. Insurer and regulator timelines are short and unforgiving.

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

Driver Incident Investigation loads about 1.7k tokens when it runs. Until then it costs about 171 tokens; SKILL.md has 746 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~171
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 746 words, ~1,659 tokens.

Download SKILL.mdSave it as .claude/skills/driver-incident-investigation/SKILL.md (or your agent's skills folder).
name
driver-incident-investigation
description
Investigate a commercial vehicle incident so the record is defensible and the cause is actually found — evidence secured in the first hours, the preventability decision made on stated criteria, and corrective action aimed at the system rather than the driver. Use when asked to investigate a vehicle accident, run a post-accident review, decide whether a collision was preventable, or write an incident report for a fleet. Produces the evidence checklist, the sequence reconstruction, the preventability determination with reasoning, the contributing-factor analysis, and the corrective actions. Not legal advice; involve your insurer and counsel early.

Driver Incident Investigation

The first four hours decide whether an incident can ever be properly investigated — telematics overwritten, the scene cleared, memories consolidated into a story. This gets the evidence secured first, then separates what happened from who was involved, and makes the preventability call against written criteria rather than instinct, because that decision drives insurance, discipline, and whether anyone learns anything.

What This Skill Produces

  • The evidence checklist — what to secure immediately, and what is lost if you wait
  • A sequence reconstruction — what happened, in order, from evidence rather than recollection
  • The preventability determination — decided against stated criteria, with the reasoning recorded
  • Contributing-factor analysis — driver, vehicle, route, scheduling, training, and supervision
  • Corrective actions — aimed at whichever of those factors actually contributed
  • The notification checklist — insurer, regulator, and internal reporting, with their deadlines

Required Inputs

Ask for these if not provided:

  • The incident — date, time, location, vehicle, driver, and what is known so far
  • Available evidence — telematics, dashcam, ELD or tachograph, maintenance records, and photographs
  • The driver's account — taken early, separately, and without leading
  • The context — the schedule that day, hours worked, route, weather, load, and any time pressure
  • Your framework — the company's preventability criteria and reporting obligations in your jurisdiction

Framework: Secure Evidence, Reconstruct, Then Judge Preventability

  1. Secure the perishable evidence first. Telematics and camera footage overwrite on a cycle. Photographs, the load, and the vehicle's condition change within hours. Preserve before you interview.
  2. Take the driver's account early and alone. Before it is discussed with colleagues. Ask what happened, not whether they were at fault — and record it verbatim.
  3. Reconstruct from evidence, not narrative. Speed, following distance, braking, and timing come from data. Use the account to explain the data, not to replace it.
  4. Decide preventability against written criteria. Could a reasonably prudent driver have avoided it, given what they could perceive? Record the reasoning, not just the verdict — this is the part that gets challenged.
  5. Look past the driver. Was the schedule achievable? Was the driver fatigued? Was the fault reported before? Was the training adequate? Most incidents have a systemic contributor and blaming the driver ends the investigation prematurely.
  6. Act on the actual contributor. Retraining a driver who was awake for sixteen hours because dispatch built the run that way is a corrective action aimed at the wrong thing.
  7. Meet the notification deadlines. Insurer and regulator timelines are short and unforgiving.

Output Format

Show full SKILL.md (342 more words)Show less
Incident investigation: [ref] · [date] · [vehicle] · [driver]

Incident: [date, time, location, conditions] · Vehicle: [unit, load] · Driver: [name, licence class, tenure] · Injuries: [yes/no, detail] · Third parties: [detail]

Evidence secured — [item · secured by · when] telematics ☐ · camera footage ☐ · ELD/tachograph ☐ · photographs ☐ · maintenance history ☐ · driver qualification file ☐ · police report ☐ · witness details ☐ Anything lost or unavailable: [what, and why]

Driver account: [taken by, when, verbatim summary]

Sequence reconstruction

TimeWhat the evidence showsSource

Preventability determination: ☐ Preventable ☐ Non-preventable Criteria applied: [the written standard] · Reasoning: [why, referencing the evidence]

Contributing factors

FactorPresentEvidenceSystemic?
Driver behaviour
Fatigue / hours
Vehicle condition
Schedule / dispatch pressure
Training / qualification
Route / environment

Corrective actions: [action · addresses which factor · owner · due]

Notifications: insurer [when] · regulator [if required, when, under what provision] · internal [who]

Not legal advice. Reporting obligations, evidence-retention duties, and the consequences of a preventability determination differ by jurisdiction and by insurer. Involve your insurer and legal counsel early, particularly where there are injuries, and preserve evidence accordingly.

Quality Checks

  • Perishable evidence was secured before interviews
  • The driver's account was taken early, alone, and recorded verbatim
  • The sequence is built from data, with the account used to explain it
  • Preventability cites the written criteria and records the reasoning
  • Systemic factors — scheduling, fatigue, maintenance, training — were examined
  • Corrective actions address the factors actually found
  • Notification deadlines were identified and met

Anti-Patterns

  • Interviewing before preserving footage. The evidence overwrites while you talk.
  • Asking the driver whose fault it was. Produces a defensive account and contaminates the record.
  • A preventability verdict with no recorded reasoning. Indefensible on challenge.
  • Stopping at driver error. The schedule, the fault report nobody actioned, and the training gap all disappear.
  • Retraining as the default corrective action. It is the cheapest action and rarely the right one.
  • Missing insurer notification. Can prejudice cover entirely.
  • Investigating to assign blame. Guarantees you learn nothing usable.

Example Trigger Phrases

  • "Investigate a collision involving one of our trucks"
  • "Was this accident preventable?"
  • "What evidence do I need to secure after an incident?"
  • "Write a post-accident investigation report"
  • "Our driver had an accident — what do I do first?"

© 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/driver-incident-investigation of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Driver Incident Investigation 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.

Driver Incident Investigation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Driver Incident Investigation this skillmohitagw15856/pm-claude-skills1.4k—~1.7kAutomated safety check: PassMIT
Investigating Phishing Email Incidentmukul975/Anthropic-Cybersecurity-Skills34k—~2.8kAutomated safety check: PassApache-2.0
Investigate IncidentMentra-Community/MentraOS2.4k—~1.1kAutomated safety check: PassApache-2.0
Incident Investigationfossasia/eventyay-interpretation1.6k—~1.4kAutomated safety check: PassApache-2.0
Recordingcodewhale-hq/Codewhale41k—~540Automated safety check: PassMIT
Investigating Incidents With AWS Devops Agentaws/agent-toolkit-for-aws2.8k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Investigating Phishing Email Incident

    mukul975/Anthropic-Cybersecurity-Skills

    Investigates phishing email incidents from initial user report through header analysis, URL/attachment detonation, impacted user identification, and containment actions using SOC tools like Splunk…

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Investigate Incident

    Mentra-Community/MentraOS

    Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID.

    2.4k GitHub stars~1.1k tokensUpdated today
    Testing & QAAuto-check passed

  • Incident Investigation

    fossasia/eventyay-interpretation

    A skill your agent uses to diagnose and resolve production incidents in VoxBento.

    1.6k GitHub stars~1.4k tokensUpdated 6 days ago
    Backend & APIsAuto-check passed

  • Recording

    codewhale-hq/Codewhale

    Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures.

    41k GitHub stars~540 tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Incident Responder

    davila7/claude-code-templates

    Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management.

    33k GitHub starsUsed in 7 repos~2.6k tokens
    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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    Auto-check passed

Questions about Driver Incident Investigation

What does Driver Incident Investigation do?

Investigate a commercial vehicle incident so the record is defensible and the cause is actually found — evidence secured in the first hours, the preventability decision made on stated criteria, and…. Driver Incident Investigation is an agent skill from mohitagw15856/pm-claude-skills. Investigate a commercial vehicle incident so the record is defensible and the cause is actually found — evidence secured in the first hours, the preventability decision made on stated criteria, and corrective action aimed at the system rather than the driver.

When should I use Driver Incident Investigation?

Driver Incident Investigation fits situations like: asked to investigate a vehicle accident; run a post-accident review; decide whether a collision was preventable; write an incident report for a fleet.

How do I install Driver Incident Investigation in Claude Code?

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

How do I install Driver Incident Investigation in Codex?

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

Can I use Driver Incident Investigation 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 driver-incident-investigation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/driver-incident-investigation, .gemini/skills/driver-incident-investigation, .github/skills/driver-incident-investigation and .opencode/skills/driver-incident-investigation in your project.

What does Driver Incident Investigation need to run?

SKILL.md names no scripts, command-line tools or credentials: Driver Incident Investigation is instructions for the agent only.

Does Driver Incident Investigation 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 Driver Incident Investigation 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 Driver Incident Investigation use?

Driver Incident Investigation 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 Driver Incident Investigation use?

About 1.7k tokens (SKILL.md is roughly 6.6k 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 Driver Incident Investigation?

Skills that share tags, products or a category with Driver Incident Investigation: Investigating Phishing Email Incident (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Investigate Incident (Mentra-Community/MentraOS, 2.4k stars), Incident Investigation (fossasia/eventyay-interpretation, 1.6k stars) and Recording (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Driver Incident Investigation?

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.