Skip to content

dongshuyan/compass-skills / skills/run-history-skill-builder

run-history-skill-builder

Verified

Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons into a new skill, or produce a plan before writing files. Do not use to upgrade an existing skill or to execute the business workflow itself.

references/open-source-pattern-mining.md

View on GitHub
# Open-Source Pattern Mining

Read this file when local evidence is not enough to choose a strong package structure or validation strategy.

## Search Goals

Use public references to learn packaging patterns, not to outsource judgment.

Good targets:

- official skill frameworks or platform docs;
- first-party or maintained example skill repositories;
- similar public skills with readable `SKILL.md`, clear boundaries, and transparent scripts.

## Search Discipline

Record for each candidate:

- repository or document URL;
- last-updated signal or commit date;
- files actually read;
- patterns adopted;
- patterns rejected and why.

## Screening Checklist

Prefer references that:

- explain when the skill triggers and when it does not;
- keep `SKILL.md` concise and push details into `references/` or `scripts/`;
- show validation, regression, or smoke checks;
- avoid credential handling, opaque installers, or dangerous automation.

Reject or heavily down-rank references that:

- ship hardcoded keys, session exports, or credential readers;
- rely on private paths or environment-specific assumptions;
- replace evidence with marketing claims;
- have no readable source for critical behavior.

## What To Adopt

- trigger wording patterns;
- resource split patterns;
- validator ideas;
- example/eval structures;
- route-hardening techniques.

## What Not To Adopt

- repo branding as proof of quality;
- unexplained heuristics;
- forced `README`, installer, or changelog files when the target ecosystem does not need them;
- local company conventions presented as universal rules.

## Temporary Research Directories

Clone or download references only into a temporary local directory outside the final skill package. Do not ship the research copies unless the user explicitly asks for them.

## Packaging Rule

If public references disagree with the run history, trust the run history for the user's actual workflow and use the public material only to improve packaging quality.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall