skill-fusion

skill-fusion is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 98 tokens per session (860 once invoked), scanned A, original, MIT.

A method for combining two separate skills into one brief for a task that spans both. It decides which skill leads, merges their structures, and resolves conflicts between their requirements.

In plain words
What is it for?
Use it when a task crosses skill boundaries and needs one coherent output based on two parent skills.
Why use it?
It avoids producing two disconnected documents when one task needs a unified result, such as a postmortem that also serves as a board update.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when a task crosses skill boundaries and needs one coherent output based on two parent skills.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/skill-fusion
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-fusion

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/skill-fusion/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/skill-fusion)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/skill-fusion"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/skill-fusion/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-fusion

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/skill-fusion"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/skill-fusion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 860 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.00860
Opus 5 $0.00049 $0.00430
Sonnet 5 $0.00020 $0.00172
Haiku 4.5 $0.00010 $0.00086

Measured 8d ago against content hash 20b328d31b7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-fusion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

exports/cursor/pm-advanced/skill-fusion/skill-fusion.mdc · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Fusion

Real tasks ignore taxonomy: the investor update that's half postmortem, the launch plan that's half legal review. Running two skills sequentially produces a stapled document. Fusion produces a hybrid — one structure that inherits deliberately from both parents, with explicit rules for their disagreements.

Required Inputs

  • The two parent skills — by name if known; otherwise describe the task and identify the two best parents first (say which and why).
  • The task itself — what's being produced, for whom. The audience decides which parent leads.
  • The actual input material, if the fused skill should run immediately after being forged.

The Fusion Method

  1. Declare the dominant parent — the audience's primary job determines it (a board reads the postmortem-update as an update first). The dominant parent contributes the skeleton; the recessive parent contributes organs.
  2. Merge structures section by section — for each parent section: keep / merge / drop, with one-line reasons. A fused doc is SHORTER than the parents combined or the fusion failed.
  3. Resolve conflicts explicitly — where parents disagree (a PRD wants exhaustive edge cases; a pitch wants momentum), write the precedence rule ("edge cases compress to the risk table; the narrative keeps pitch pacing").
  4. Merge the quality bars — union of both parents' Quality Checks, minus those the fusion made irrelevant, plus 1-2 new checks that only the hybrid needs ("the metrics section satisfies both the update reader who skims and the postmortem reader who audits").
  5. Inherit both anti-pattern sets — hybrids fail in both parents' ways, plus one new way: the staple (sections that alternate voices). Check for the staple explicitly.

Output Format

  1. The fusion header — parents, dominant parent + why, the task it's forged for.
  2. The hybrid structure — the fused outline with per-section parentage marked (📘 parent A / 📗 parent B / ⚗️ new).
  3. The merged quality bar and anti-patterns — deduplicated, with the new hybrid-only entries flagged ⚗️.
  4. Precedence rules — every parent conflict and its resolution, as one-liners.
  5. The fused output — if input material was provided, run the hybrid on it immediately.

Read the full file on GitHub · 48 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 48 lines · 98 tokens per session scan A 20b328d31b7b

Subscribe to this mod's changes

skill-fusion is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 860 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.