Doc Coauthoring
aws-samples/sample-strands-agent-with-agentcore
Guide users through a structured workflow for co-authoring documentation.
Structure an internal proposal that gets a decision — the problem-cost-options-recommendation-ask spine, the objection pre-handling that shortens the meeting, and the reversibility framing that…
Install Proposal Skeleton
$ npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills proposal-skeleton --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/proposal-skeleton .claude/skills/proposal-skeleton && rm -rf skills-srcUse ~/.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/
Install the "proposal-skeleton" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeleton into .claude/skills/proposal-skeleton/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proposal-skeleton", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeletonType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills proposal-skeleton --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/proposal-skeleton .agents/skills/proposal-skeleton && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "proposal-skeleton" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeleton into .agents/skills/proposal-skeleton/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proposal-skeleton", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills proposal-skeleton --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/proposal-skeleton .cursor/skills/proposal-skeleton && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "proposal-skeleton" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeleton into .cursor/skills/proposal-skeleton/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proposal-skeleton", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/proposal-skeleton--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills proposal-skeleton --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/proposal-skeleton .gemini/skills/proposal-skeleton && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "proposal-skeleton" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeleton into .gemini/skills/proposal-skeleton/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proposal-skeleton", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills proposal-skeletonInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/proposal-skeleton .github/skills/proposal-skeleton && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "proposal-skeleton" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeleton into .github/skills/proposal-skeleton/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proposal-skeleton", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills proposal-skeleton --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/proposal-skeleton .opencode/skills/proposal-skeleton && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "proposal-skeleton" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/proposal-skeleton into .opencode/skills/proposal-skeleton/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proposal-skeleton", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
proposal-skeleton- GitHub stars
- 1.4k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 691 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Structure an internal proposal that gets a decision — the problem-cost-options-recommendation-ask spine, the objection pre-handling that shortens the meeting, and the reversibility framing that…
- Works in 5 steps: Price the problem first: "we spend ~11… → Options are steelmanned or they're… → Recommend with reasons that touch the… → …
- Asked write a proposal for the new tool
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Spine Rules and Output Format, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Proposal Skeleton is an agent skill from mohitagw15856/pm-claude-skills. Structure an internal proposal that gets a decision — the problem-cost-options-recommendation-ask spine, the objection pre-handling that shortens the meeting, and the reversibility framing that makes yes easier. Use when asked write a proposal for the new tool or process or hire, how do I pitch this internally, structure my case for the change, or my proposals keep dying in review. Produces the proposal skeleton filled from the actual case, the objections table, the decision-sized ask, and the one-page discipline.
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.
It sits in Sales & Support, covering Proposals and quotes. 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 write a proposal for the new tool
- How do I pitch this internally
- Structure my case for the change
- My proposals keep dying in review
Example prompts
- “/proposal-skeleton”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Price the problem first: "we spend ~11 hours/week on manual reconciliation (≈ $2.9k/month)" converts the proposal from a preference into…
- Options are steelmanned or they're theater: 2–3 real options, each with its genuine best case — including do-nothing's ("zero switching…
- Recommend with reasons that touch the comparison: "Option B, because it fixes the cost at 40% of Option C's price and reverses in a month…
- Concede risks before the reader finds them: the objections table — likely objection → honest answer or mitigation — signals the thinking…
- The ask is decision-sized and reversibility-framed: "Approve a 6-week pilot for one team at $X, success = [metric], full rollout decided…
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
Proposal Skeleton loads about 1.4k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 691 words of instructions outside code blocks.
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). 691 words, ~1,356 tokens.
Download SKILL.mdSave it as
.claude/skills/proposal-skeleton/SKILL.md (or your agent's skills folder).- name
- proposal-skeleton
- description
- Structure an internal proposal that gets a decision — the problem-cost-options-recommendation-ask spine, the objection pre-handling that shortens the meeting, and the reversibility framing that makes yes easier. Use when asked write a proposal for the new tool or process or hire, how do I pitch this internally, structure my case for the change, or my proposals keep dying in review. Produces the proposal skeleton filled from the actual case, the objections table, the decision-sized ask, and the one-page discipline.
Proposal Skeleton Skill
Internal proposals die of three causes: the problem arrived unpriced (so the status quo stayed free), the options section was a strawman parade (so the reader felt managed), or the ask was unsized (so "interesting" substituted for a decision). The working spine is old and undefeated: the problem with its cost → real options fairly stated → the recommendation with reasons → risks conceded with mitigations → a decision-sized ask with a reversibility line. One page, because proposals are read in the gap between meetings.
What This Skill Produces
- The filled skeleton — problem-with-cost, options, recommendation, risks, ask — from the actual case
- The objections table — the three likely objections, pre-answered in the reader's dialect
- The ask, decision-sized — what exactly, costing what, decided by whom, reversible how
- The one-page version — with the appendix rule for everything that overflows
Required Inputs
Ask for these if not provided:
- The change and the evidence — what's being proposed and what supports it (the pilot data, the incident, the quote comparisons); skeletons organize evidence, not enthusiasm
- The cost of the status quo — the number or consequence that makes "do nothing" a choice with a price; without it, inertia wins by default and deserves to
- The decision-maker and their dialect — who says yes, and what they weigh (money? risk? team health?) — the recommendation argues in their currency (executive-summary audience rules apply)
- The honest alternatives — including the strongest version of "do nothing" and the rival option a smart skeptic would raise
Framework: The Spine Rules
- Price the problem first: "we spend ~11 hours/week on manual reconciliation (≈ $2.9k/month)" converts the proposal from a preference into arithmetic — and do-nothing from the safe default into the most expensive option on the page. Honest numbers only; one inflated cost discounts the whole case.
- Options are steelmanned or they're theater: 2–3 real options, each with its genuine best case — including do-nothing's ("zero switching cost, no adoption risk"). Readers detect strawmen instantly, and a fairly-stated rival makes the recommendation more credible, not less.
- Recommend with reasons that touch the comparison: "Option B, because it fixes the cost at 40% of Option C's price and reverses in a month if wrong" — the recommendation cites the dimensions the options table established, in the decision-maker's currency.
- Concede risks before the reader finds them: the objections table — likely objection → honest answer or mitigation — signals the thinking survived contact with skepticism. A proposal with no stated risks reads as either naive or salesy; both lose.
- The ask is decision-sized and reversibility-framed: "Approve a 6-week pilot for one team at $X, success = [metric], full rollout decided after" — small enough to say yes to today, with the exit named. Big irreversible asks get deferred forever; pilots get approved this week. The one-page rule: spine on page one, everything else (the vendor matrix, the data) appendixed and referenced.
Show full SKILL.md (222 more words)Show less
Output Format
Proposal: [the change] — for [decision-maker]
The Problem, Priced
[Two sentences + the honest number/consequence of continuing]
Options (steelmanned)
| Option | Its best case | Cost | Risk |
|---|---|---|---|
| [Do-nothing included, fairly] |
Recommendation
[The option + the reasons in the reader's currency + the reversibility line]
Objections, Pre-Handled
| They'll ask | The honest answer |
|---|
The Ask
[Exactly what · costing what · decided by whom, by when · pilot-sized with the success metric and exit]
(Appendix: the overflow — referenced, not inlined)
Quality Checks
- The status quo carries an honest price
- Every option including do-nothing got its best case
- The recommendation argues in the decision-maker's stated currency
- Risks are conceded with mitigations before the reader raises them
- The ask is pilot-sized, dated, and names its reversal path
Anti-Patterns
- Do not propose against an unpriced status quo — free inertia beats every paid change
- Do not strawman the alternatives — the detected strawman costs more credibility than the rival option ever would
- Do not ask for the end-state — ask for the smallest decidable step toward it
- Do not hide the risks — the reader's discovered objection beats your conceded one, in their favor
- Do not exceed a page in the body — the appendix exists so the spine can breathe
Example Trigger Phrases
- "Write a proposal for the new tool."
- "How do I pitch this internally?"
- "Structure my case for the change."
- "My proposals keep dying in review."
© 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/proposal-skeleton of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Proposal Skeleton 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Proposal Skeleton this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore | 195 | 41 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Audit Onboarding Proposalhoangnb24/repository-harness | 1.2k | — | ~4k | Automated safety check: Pass | MIT | |
| No Negative EchoLB623/no-negative-echo | 897 | — | ~965 | Automated safety check: Pass | MIT | |
| GEO Service Proposal Generatorzubair-trabzada/geo-seo-claude | 11k | — | ~3k | Automated safety check: Notes | MIT | |
| Architectural ProposalsFritzAndFriends/SharpSite | 145 | 2 repos | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
- Official
Audit Onboarding Proposal
hoangnb24/repository-harness
Use only when the user explicitly invokes $audit-onboarding-proposal.
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.
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.
Architectural Proposals
FritzAndFriends/SharpSite
How to write comprehensive architectural proposals that drive alignment before code is written
Counter Proposal Generator
zubair-trabzada/ai-legal-claude
Generates specific counter-proposals for every unfavorable clause, with replacement language, negotiation talking points, and a ready-to-send email template
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar 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…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
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.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
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.
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.
Related
Categories
Questions about Proposal Skeleton
What does Proposal Skeleton do?
Structure an internal proposal that gets a decision — the problem-cost-options-recommendation-ask spine, the objection pre-handling that shortens the meeting, and the reversibility framing that…. Proposal Skeleton is an agent skill from mohitagw15856/pm-claude-skills. Structure an internal proposal that gets a decision — the problem-cost-options-recommendation-ask spine, the objection pre-handling that shortens the meeting, and the reversibility framing that makes yes easier.
When should I use Proposal Skeleton?
Proposal Skeleton fits situations like: asked write a proposal for the new tool; how do I pitch this internally; structure my case for the change; my proposals keep dying in review.
How do I install Proposal Skeleton in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a claude-code`. Or copy the skill folder (skills/proposal-skeleton in mohitagw15856/pm-claude-skills) into .claude/skills/proposal-skeleton in your project. Claude Code loads it when a task matches its description.
How do I install Proposal Skeleton in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill proposal-skeleton -a codex`. Or copy the skill folder (skills/proposal-skeleton in mohitagw15856/pm-claude-skills) into .agents/skills/proposal-skeleton in your project. Codex loads it when a task matches its description.
Can I use Proposal Skeleton 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 proposal-skeleton -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proposal-skeleton, .gemini/skills/proposal-skeleton, .github/skills/proposal-skeleton and .opencode/skills/proposal-skeleton in your project.
What does Proposal Skeleton need to run?
SKILL.md names no scripts, command-line tools or credentials: Proposal Skeleton is instructions for the agent only.
Does Proposal Skeleton 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 Proposal Skeleton 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 Proposal Skeleton use?
Proposal Skeleton 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 Proposal Skeleton use?
About 1.4k tokens (SKILL.md is roughly 5.4k 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 Proposal Skeleton?
Skills that share tags, products or a category with Proposal Skeleton: 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 Proposal Skeleton?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,433 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 8, 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.