Agent skill

Audited Boundary Check

by mohitagw15856 in mohitagw15856/pm-claude-skills

A skill your agent uses when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is…

MITAuto-check passedWriting & Content

Install Audited Boundary Check

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill audited-boundary-check -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills audited-boundary-check --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/audited-boundary-check .claude/skills/audited-boundary-check && 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
audited-boundary-check
GitHub stars
1.4k
Token cost
~1.8k tokens
SKILL.md length
943 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is…

  • Works in 5 steps: Every figure carries (p. N). A figure… → A figure that cannot be located in the… → "Audited" means the figure appears, in… → …
  • Asked to check whether a figure is audited
  • SKILL.md covers What This Skill Produces, Required Inputs, Example Trigger Phrases and Hard Rules, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Audited Boundary Check is an agent skill from mohitagw15856/pm-claude-skills. Use when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is vouching for the numbers in the highlights. For every headline figure in the highlights, chairman's statement and CEO review of an uploaded annual report, states whether it sits inside or outside the audited statements and what was added or removed versus the nearest audited number. Produces a boundary table, the list of figures outside the…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Plain language and style rules. 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 check whether a figure is audited
  • Which headline numbers sit outside the audited accounts
  • Underlying means in this report
  • Who is vouching for the numbers in the highlights

Example prompts

  • “adjusted”
  • “underlying”
  • “/audited-boundary-check”

Workflow steps

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

  1. Every figure carries (p. N). A figure with no page is a defect.
  2. A figure that cannot be located in the audited pages, and has no company-provided reconciliation, gets "nearest audited equivalent: not…
  3. "Audited" means the figure appears, in that form, on a page the audit opinion states it covers. Arithmetic on audited figures (a growth %…
  4. Never call an outside figure wrong, misleading, or fake. The skill describes the boundary; it does not judge intent.
  5. No buy, sell, or valuation opinion.

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

Audited Boundary Check loads about 1.8k tokens when it runs. Until then it costs about 160 tokens; SKILL.md has 943 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~160
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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). 943 words, ~1,791 tokens.

Download SKILL.mdSave it as .claude/skills/audited-boundary-check/SKILL.md (or your agent's skills folder).
name
audited-boundary-check
description
Use when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is vouching for the numbers in the highlights. For every headline figure in the highlights, chairman's statement and CEO review of an uploaded annual report, states whether it sits inside or outside the audited statements and what was added or removed versus the nearest audited number. Produces a boundary table, the list of figures outside the boundary, and a plain-English summary of who is vouching for what. Educational, not financial advice.

Audited Boundary Check Skill

Draws the line the report's front half blurs: which headline numbers an auditor signed off, which ones the company chose, and exactly what changed between the two.

What This Skill Produces

  • The audit boundary: which pages and statements the opinion covers, and the opinion type
  • A boundary table covering every headline figure in the highlights, chairman's statement and CEO review
  • The outside-the-boundary list, each figure bridged to its nearest audited equivalent
  • A plain-English summary of who is vouching for what

Required Inputs

  • An uploaded annual report PDF. Hard requirement: if none is attached, ask and stop.
  • Optional: which sections to scan if the learner wants to go beyond the default three (highlights, chairman's statement, CEO review).

Example Trigger Phrases

  • "Which of these headline numbers are actually audited?"
  • "What does 'adjusted operating profit' leave out in this report?"
  • "Is the growth figure on page 2 inside the accounts or made up by management?"
  • "Who is vouching for the numbers in the highlights?"
  • "Run an audited boundary check on this annual report"

Hard Rules

  1. Every figure carries (p. N). A figure with no page is a defect.
  2. A figure that cannot be located in the audited pages, and has no company-provided reconciliation, gets "nearest audited equivalent: not disclosed in this report" — never a reasoned guess.
  3. "Audited" means the figure appears, in that form, on a page the audit opinion states it covers. Arithmetic on audited figures (a growth %, a margin) is derived, not audited, and is classified outside.
  4. Never call an outside figure wrong, misleading, or fake. The skill describes the boundary; it does not judge intent.
  5. No buy, sell, or valuation opinion.

Process

  1. Find the audit report (p. N). Record: auditor name; opinion type (unqualified / qualified / adverse / disclaimer, or the local equivalent); the sentence stating which pages or statements the opinion covers; and the "other information" paragraph confirming the auditor read but did not audit the front half. If any element is absent, write "not disclosed in this report".
  2. Draw the boundary: list the audited statements and their pages; everything else is outside.
  3. Harvest every headline figure from the highlights, chairman's statement and CEO review: every currency amount, percentage, ratio, count, or ranking. Do not skip small ones.
  4. Classify each figure: Inside (appears verbatim on an audited page), Derived (arithmetic on inside figures — show the arithmetic), Outside (adjusted, underlying, like-for-like, constant-currency, pro-forma, KPI, operational metric, market claim).
  5. Bridge each Outside figure to its nearest audited equivalent using the company's own reconciliation table if one exists (p. N); list every item added or removed with its amount. If no reconciliation exists, say so.
  6. Write the vouching summary.

Output Format

Show full SKILL.md (491 more words)Show less
Audited Boundary Check: [company, period]

The boundary

  • Auditor: [name] (p. N) · Opinion: [type] (p. N)
  • Covers: [statements and pages, quoted] (p. N)
  • Front-half status: [quote or paraphrase of the other-information paragraph] (p. N)

Boundary table — one row per headline figure, in the order they appear:

Figure (as printed, page)Audited?Nearest audited equivalent (page)What differs
e.g. Adjusted EBITDA £412m (p. 2)No — OutsideOperating profit £298m (p. 61)+ D&A £71m, + exceptional items £38m, + share-based pay £5m (recon p. 34)
e.g. Revenue £2,104m (p. 2)Yes — InsideSame (p. 60)—
e.g. Revenue growth 8% (p. 3)No — Derived£2,104m ÷ £1,948m − 1 (p. 60)Arithmetic on audited figures; check the prior year is not restated

Audited? takes exactly one of: Yes — Inside, No — Derived, No — Outside.

Figures outside the boundary — numbered list, one line each: figure, page, what was added or removed with amounts, and whether the company reconciled it (p. N) or "no reconciliation disclosed in this report". Group operational metrics (customers, NPS, market share, employee counts) at the end under No audited equivalent exists.

Who is vouching for what — exactly three short paragraphs:

  1. The auditor vouches for: [the statements listed], to the standard of [opinion type]; what an unqualified opinion does and does not mean in one sentence.
  2. The directors vouch for the whole report, including every Outside figure; name the directors' responsibility statement page or "not disclosed in this report".
  3. Nobody independent vouches for: [list the Outside and operational figures]; the reader is trusting management's definitions, which can change year to year.

End verbatim: "Educational, not financial advice. Decisions with real money belong with a regulated adviser."

Quality Checks

  • The audit opinion page, type, and covered pages are quoted or marked not disclosed — pass/fail
  • Every currency amount, percentage, ratio, and count in the three scanned sections has a row — pass/fail
  • Every row uses one of the three exact Audited? values — pass/fail
  • Every Outside row names its nearest audited equivalent with a page, or says not disclosed — pass/fail
  • Every bridge lists items with amounts, not just labels — pass/fail
  • Derived rows show their arithmetic — pass/fail
  • No row uses "misleading", "fake", "inflated", or similar — pass/fail
  • The vouching summary has exactly three paragraphs — pass/fail
  • The disclaimer line is the final line, verbatim — pass/fail

Anti-Patterns

  • Do not treat "adjusted" as a synonym for dishonest; describe what was removed and let the reader decide
  • Do not treat "audited" as a synonym for correct; the opinion is on material fairness, not on every figure
  • Do not assume the front half is unaudited without quoting the other-information paragraph or marking it not disclosed
  • Do not bridge a figure from memory of what companies usually adjust; use this report's reconciliation or say none exists
  • Do not skip the small numbers; a headcount or NPS claim is exactly the kind of figure nobody independent checks

annual-report-tutor (the full walk), profit-to-cash-walk (bridge profit to cash), company-compare-same-definitions (two reports), investing-vocabulary-explainer (define any term).

© 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/audited-boundary-check of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Audited Boundary Check 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.

Audited Boundary Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audited Boundary Check this skillmohitagw15856/pm-claude-skills1.4k—~1.8kAutomated safety check: PassMIT
Asd Ste100danyuchn/asd-ste100-skill4.3k—~4.1kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.3kAutomated safety check: PassNone
Ponytail AuditDietrichGebert/ponytail160k—~1.4kAutomated safety check: PassMIT
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT
PgjevrealZachi/pg-jev1.1k—~2.9kAutomated safety check: PassCustom licence

Similar skills

  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.3k GitHub stars~4.1k tokensUpdated 7 days ago
    Writing & ContentAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    11k GitHub starsUsed in 10 repos~2.3k tokens
    Writing & ContentAuto-check passed
  • Ponytail Audit

    DietrichGebert/ponytail

    Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.

    160k GitHub stars~1.4k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Pgjev

    realZachi/pg-jev

    Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).

    1.1k GitHub stars~2.9k tokensUpdated 4 days ago
    Writing & ContentAuto-check passed
  • Defensive Writing Editor

    lennney/stop-that-shit

    Cuts defensive disclaimers, stacked hedging and self-protective narration from proposals and summaries, keeping only limits that affect the reader's decision.

    2.5k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-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 Audited Boundary Check

What does Audited Boundary Check do?

A skill your agent uses when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is…. Audited Boundary Check is an agent skill from mohitagw15856/pm-claude-skills. Use when asked to check whether a figure is audited, which headline numbers sit outside the audited accounts, what 'adjusted' or 'underlying' means in this report, or who is vouching for the numbers in the highlights.

When should I use Audited Boundary Check?

Audited Boundary Check fits situations like: asked to check whether a figure is audited; which headline numbers sit outside the audited accounts; underlying means in this report; who is vouching for the numbers in the highlights.

How do I install Audited Boundary Check in Claude Code?

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

How do I install Audited Boundary Check in Codex?

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

Can I use Audited Boundary Check 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 audited-boundary-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audited-boundary-check, .gemini/skills/audited-boundary-check, .github/skills/audited-boundary-check and .opencode/skills/audited-boundary-check in your project.

What does Audited Boundary Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Audited Boundary Check is instructions for the agent only.

Does Audited Boundary Check 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 Audited Boundary Check 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 Audited Boundary Check use?

Audited Boundary Check 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 Audited Boundary Check use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 Audited Boundary Check?

Skills that share tags, products or a category with Audited Boundary Check: Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars), Technical Writing Standard (cursor/plugins, 11k stars), Ponytail Audit (DietrichGebert/ponytail, 160k stars) and Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audited Boundary Check?

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.