skill-fusion

GitHub

将两个技能融合为单一混合简报,解决跨领域任务。通过确定主导技能、合并结构、解决冲突及合并质量标准,生成精简且逻辑统一的输出,避免简单拼接导致的文档冗余和风格割裂。

exports/openclaw/skill-fusion/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

需要同时满足两种不同技能要求(如PRD兼路演稿)的任务 单独运行两个技能会导致产生两份独立文档的场景

Install

npx skills add mohitagw15856/pm-claude-skills --skill skill-fusion -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/skill-fusion -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@skill-fusion

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill skill-fusion -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "skill-fusion",
    "homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/skill-fusion.html",
    "metadata": {
        "openclaw": {
            "emoji": "🎛"
        }
    },
    "description": "Fuse two skills from this library into one hybrid brief for a task that sits between them — the meta-skill. Use when a task straddles two skills (a PRD that's also a pitch; a postmortem that must double as a board update) and running them separately would produce two documents where one is needed. Produces the fused operating brief: combined structure, merged quality bar, precedence rules for where the parents disagree, and the fused output itself if input was provided."
}

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.

Quality Checks

  • The dominant parent was chosen by audience analysis, stated in one sentence — not by which skill came first
  • Every parent section is dispositioned (keep/merge/drop) with a reason — no silent omissions
  • The fused structure is shorter than the sum of parents — fusion compresses or it's stapling
  • At least one ⚗️ hybrid-only quality check exists — if none, the task probably needed one parent, and the output should say so
  • The staple test ran: no section sequence alternates parent voices without a merge

Anti-Patterns

  • Do not fuse more than two skills — three-parent hybrids are committees; run fusion twice if truly needed
  • Do not fuse when one parent covers 90% — the honest output is "use X, borrow one section from Y", and it should say exactly that
  • Do not average conflicting rules — precedence means one wins per conflict, visibly
  • Do not inherit boilerplate from both parents (two intros, two summaries) — the classic staple smell
  • Do not let the fusion drop both parents' verification sections in the compression — the quality bar merges; it never thins

Version History

  • 54fad50 Current 2026-07-19 12:33

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-hiring-panel/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-severance/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/agm-in-a-box/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/behavior-intervention-plan/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bennett-time-audit/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-game-designer/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md

Metadata

Files
0
Version
e4def4c
Hash
721fb007
Indexed
2026-07-19 12:33

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-31 03:28
浙ICP备14020137号-1 $방문자$