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

Document Comparison

by heypinchy in heypinchy/pinchy

Evaluate several documents against a shared set of criteria — proposals against requirements, contracts against each other, policies against a standard, candidates against a role.

AGPL-3.0Auto-check passedSales & Support

Install Document Comparison

skills CLI
$ npx skills add heypinchy/pinchy --skill document-comparison -a claude-code

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

GitHub CLI
$ gh skill install heypinchy/pinchy document-comparison --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/heypinchy/pinchy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/web/src/lib/skills/document-comparison .claude/skills/document-comparison && 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
document-comparison
GitHub stars
182
Token cost
~1.2k tokens
SKILL.md length
707 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Evaluate several documents against a shared set of criteria — proposals against requirements, contracts against each other, policies against a standard, candidates against a role.

  • Works in 7 steps: Fix the criteria before you read. Write… → Extract the same fields from every… → Record "not stated" as its own value. A… → …
  • The answer is a comparison
  • SKILL.md covers When to use, When NOT to use, Workflow and Safety (must hold), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Document Comparison is an agent skill from heypinchy/pinchy. Evaluate several documents against a shared set of criteria — proposals against requirements, contracts against each other, policies against a standard, candidates against a role. Use whenever the answer is a comparison, a ranking, a scoring, or a gap analysis. Covers fixing the criteria before reading, keeping the evaluation symmetric, separating "not stated" from "no", and presenting the result so a reader can check it.

Its SKILL.md is about 1.2k 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 Sales & Support, covering Proposals and quotes. The repository describes itself as: Self-hosted AI agent platform built on OpenClaw. Enterprise-ready, offline-capable, open source. 🦞. The licence is AGPL-3.0.

When your agent uses it

  • The answer is a comparison
  • Tasks that involve Proposals and quotes

Example prompts

  • “not stated”
  • “/document-comparison”

Workflow steps

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

  1. Fix the criteria before you read. Write down the list of criteria first — from the user's stated requirements, the standard being applied…
  2. Extract the same fields from every document. Go criterion by criterion, document by document. Never stop early because one document…
  3. Record "not stated" as its own value. A document that is silent on a criterion has not declined it and has not agreed to it. Absence of a…
  4. Cite where each value came from. Every cell in your comparison traces to a document and a location inside it (section, clause, article…
  5. Compare like with like. Normalize before you rank: different currencies, different terms (monthly vs annual), different scopes (with or…
  6. Score only against stated criteria, and show the scale. If you rank or score, say what the scale is and what each level means, and apply…
  7. Flag vague and non-committal language. "Industry-standard", "best effort", "as required", "typically", "up to" — record what was actually…

What it can do on your machine

Read from SKILL.md and the folder at commit 5159959. 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

Document Comparison loads about 1.2k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 707 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 heypinchy/pinchy at commit 5159959, republished under its AGPL-3.0 licence (© heypinchy). 707 words, ~1,222 tokens.

Download SKILL.mdSave it as .claude/skills/document-comparison/SKILL.md (or your agent's skills folder).
name
document-comparison
description
Evaluate several documents against a shared set of criteria — proposals against requirements, contracts against each other, policies against a standard, candidates against a role. Use whenever the answer is a comparison, a ranking, a scoring, or a gap analysis. Covers fixing the criteria before reading, keeping the evaluation symmetric, separating "not stated" from "no", and presenting the result so a reader can check it.

Comparing documents against criteria

Comparison work fails in a characteristic way: the criteria drift while you read. The first document sets the vocabulary, later documents get judged on whatever it happened to mention, and a vendor who simply wrote more looks better than one who wrote less. This skill exists to keep the evaluation symmetric.

When to use

  • Comparing several documents to each other (proposals, quotes, contracts, candidate profiles)
  • Checking one or more documents against an external standard (a regulation, a policy, a job description, a requirements list)
  • Any ask phrased as "which is better", "rank these", "where are the gaps", "does this meet X"

When NOT to use

  • A question about a single document with no yardstick — that's ordinary reading, not comparison
  • A recommendation the user has not asked for. Compare when asked to compare; recommend when asked to recommend

Workflow

  1. Fix the criteria before you read. Write down the list of criteria first — from the user's stated requirements, the standard being applied, or the role being filled. If the user gave none, derive a list from the documents' shared subject matter and state it explicitly at the top of your answer so they can correct it. Criteria chosen after reading are criteria fitted to a winner.
  2. Extract the same fields from every document. Go criterion by criterion, document by document. Never stop early because one document already looks like the answer.
  3. Record "not stated" as its own value. A document that is silent on a criterion has not declined it and has not agreed to it. Absence of a commitment is a finding in its own right — often the most important one — and it must never be rendered as a "no", as a zero, or as a blank cell the reader will read as either.
  4. Cite where each value came from. Every cell in your comparison traces to a document and a location inside it (section, clause, article, page label — whatever the document itself provides). A comparison nobody can check is an opinion in a table.
  5. Compare like with like. Normalize before you rank: different currencies, different terms (monthly vs annual), different scopes (with or without support, with or without VAT), different units. State every normalization you performed. An unstated normalization is indistinguishable from an error.
  6. Score only against stated criteria, and show the scale. If you rank or score, say what the scale is and what each level means, and apply it identically to every document. Do not invent a weighting the user never gave; if weighting matters, ask or present the ranking under the unweighted criteria.
  7. Flag vague and non-committal language. "Industry-standard", "best effort", "as required", "typically", "up to" — record what was actually promised, not the impression the wording leaves.
Show full SKILL.md (246 more words)Show less

Safety (must hold)

  • Never fill a gap by inference. If a document doesn't state a price, a date, a certification, or a qualification, the value is "not stated" — not the value a comparable document had, and not what is customary.
  • Judge the document, not the author. Evaluate the stated content against the criteria; do not weigh presentation quality, writing style, or personal characteristics.
  • Keep the criteria visible. If you drop or add one mid-analysis, say so; silently changing the yardstick invalidates every earlier row.

Output format

Where your own persona instructions prescribe a shape for an answer — findings ordered by severity, one heading per clause category, a scorecard — follow them. They are more specific than this shared skill, and this section is only the default for when they say nothing.

  • Lead with the comparison table: one row per criterion, one column per document. Criteria down the side keeps rows comparable when a document is added later.
  • Use a consistent marker set and define it once — for example: the stated value, — for not stated, and ? for could not be read. Never let those three collapse into one symbol.
  • Follow the table with the differences that actually matter, in prose: where the documents genuinely diverge, and what a decision would turn on.
  • Give a recommendation only when asked, and make its basis explicit: which criteria drove it, and what would change it.
  • End with what you could not evaluate — criteria no document addressed, documents you could not read.

© heypinchy, AGPL-3.0. 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 packages/web/src/lib/skills/document-comparison of heypinchy/pinchy.

Open the folder on GitHubat commit 5159959

Compare with similar skills

Document Comparison 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.

Document Comparison compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Document Comparison this skillheypinchy/pinchy182—~1.2kAutomated safety check: PassAGPL-3.0
Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore19540 repos~3.2kAutomated safety check: PassMIT
Audit Onboarding Proposalhoangnb24/repository-harness1.2k—~4kAutomated safety check: PassMIT
No Negative EchoLB623/no-negative-echo897—~965Automated safety check: PassMIT
GEO Service Proposal Generatorzubair-trabzada/geo-seo-claude11k—~3kAutomated safety check: NotesMIT
Architectural ProposalsFritzAndFriends/SharpSite1452 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    195 GitHub starsUsed in 40 repos~3.2k tokens
    Sales & SupportAuto-check passed

  • Audit Onboarding Proposal

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $audit-onboarding-proposal.

    1.2k GitHub stars~4k tokensUpdated 4 days ago
    Sales & SupportAuto-check passed

  • No Negative Echo

    LB623/no-negative-echo

    Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs.

    897 GitHub stars~965 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed

  • GEO Service Proposal Generator

    zubair-trabzada/geo-seo-claude

    Builds a client-ready AI-search-optimization proposal from an existing GEO audit, with pricing tiers, an ROI estimate and a markdown document ready to send.

    11k GitHub stars~3k tokensUpdated yesterday
    Sales & SupportAuto-check: notes

  • Architectural Proposals

    FritzAndFriends/SharpSite

    How to write comprehensive architectural proposals that drive alignment before code is written

    145 GitHub starsUsed in 2 repos~1.6k tokens
    Sales & SupportAuto-check passed

  • Task Profile

    techwolf-ai/ai-first-toolkit

    Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction lives, then propose atomic skills that would…

    132 GitHub stars~3.6k tokensUpdated 9 days ago
    Sales & SupportAuto-check passed

More from heypinchy/pinchy

All 18 skills in this repo

  • Knowledge Search

    heypinchy/pinchy

    Answer questions from the organization's indexed documents using knowledgesearch, and cite every claim back to a retrieved passage.

    182 GitHub stars~1.4k tokensUpdated 17 days ago
    Auto-check passed

  • Odoo Read

    heypinchy/pinchy

    Query and summarize data from a connected Odoo instance with the odoo read tools (describe, count, read, aggregate).

    182 GitHub stars~965 tokensUpdated 17 days ago
    Auto-check passed

  • Review Docs

    heypinchy/pinchy

    Use before opening a PR that changes docs/ or a user-visible surface (an API route, the tool registry, an agent template, the audit event catalogue, the settings navigation, plugin tools), and when…

    182 GitHub stars~1.3k tokensUpdated 17 days ago
    Auto-check passed

  • Update Dependencies

    heypinchy/pinchy

    A skill your agent uses when bumping general npm/pnpm dependencies across the Pinchy workspace (root, packages/web, packages/plugins/, docs), when the user asks to "update dependencies," "check for…

    182 GitHub stars~1.5k tokensUpdated 17 days ago
    Auto-check passed

  • Update Ollama Cloud Models

    heypinchy/pinchy

    A skill your agent uses when a new Ollama Cloud model is announced or available (e.g.

    182 GitHub stars~3.9k tokensUpdated 17 days ago
    Auto-check: notes

  • Update Openclaw

    heypinchy/pinchy

    A skill your agent uses when bumping the pinned OpenClaw core version (openclaw npm package), when preparing a Pinchy release, or when the user asks to "update OpenClaw" / "upgrade OpenClaw" / check…

    182 GitHub stars~2.8k tokensUpdated 17 days ago
    Auto-check passed

Categories

Questions about Document Comparison

What does Document Comparison do?

Evaluate several documents against a shared set of criteria — proposals against requirements, contracts against each other, policies against a standard, candidates against a role. Document Comparison is an agent skill from heypinchy/pinchy. Evaluate several documents against a shared set of criteria — proposals against requirements, contracts against each other, policies against a standard, candidates against a role.

When should I use Document Comparison?

Document Comparison fits situations like: the answer is a comparison; tasks that involve Proposals and quotes.

How do I install Document Comparison in Claude Code?

Run `npx skills add heypinchy/pinchy --skill document-comparison -a claude-code`. Or copy the skill folder (packages/web/src/lib/skills/document-comparison in heypinchy/pinchy) into .claude/skills/document-comparison in your project. Claude Code loads it when a task matches its description.

How do I install Document Comparison in Codex?

Run `npx skills add heypinchy/pinchy --skill document-comparison -a codex`. Or copy the skill folder (packages/web/src/lib/skills/document-comparison in heypinchy/pinchy) into .agents/skills/document-comparison in your project. Codex loads it when a task matches its description.

Can I use Document Comparison 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 heypinchy/pinchy --skill document-comparison -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/document-comparison, .gemini/skills/document-comparison, .github/skills/document-comparison and .opencode/skills/document-comparison in your project.

What does Document Comparison need to run?

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

Does Document Comparison 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 Document Comparison 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 Document Comparison use?

Document Comparison is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Document Comparison use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Document Comparison?

Skills that share tags, products or a category with Document Comparison: Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Audit Onboarding Proposal (hoangnb24/repository-harness, 1.2k stars), No Negative Echo (LB623/no-negative-echo, 897 stars) and GEO Service Proposal Generator (zubair-trabzada/geo-seo-claude, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Document Comparison?

heypinchy (a GitHub organization) maintains it in heypinchy/pinchy, which has 182 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on September 21, 2026.

Source: heypinchy/pinchy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.