performance-review
Skill8 starsChanged 4 months agoMITView on GitHub
Read how the posted videos actually did and turn it into lessons for the next ones — import the analytics CSV a creator exports from TikTok Studio, Meta Business Suite or YouTube Studio (or pull public YouTube numbers), match each post to the video the kit made, and report which genre, length, hook shape and posting hour beat this channel's own median. Use when the user says "video nào hiệu quả", "xem số liệu", "phân tích kênh", "tuần này thế nào", uploads an analytics export, or once a week before planning.
- Reads credentials
27 other projects use a version of this.
Adopted by
Most recently taken up by
- Cure-Consulting-Group/ProductEngineeringSkillstheir own version, first seen Nov 12, 2026
- Smaui94/ClaudeSkillCollectiontheir own version, first seen Nov 8, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- frnkgns/Overgeared-Skillstheir own version, first seen Nov 8, 2026
- flopperj/dotfiles-coretheir own version, first seen Nov 4, 2026
- nledford/engineering-review-boardtheir own version, first seen Nov 3, 2026
Used with
Projects with it also use ci-cd-pipeline, architecture-review and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
nanvixSkillci-cd-pipeline
Guide for Nanvix CI and GitHub Actions workflow behavior, including local pipeline execution and matrix coverage. Use this when asked about CI checks, workflow failures, or release flow.
Also in 3 projects that use this
SentrySkillarchitecture-review
Staff-level codebase health review. Finds monolithic modules, silent failures, type safety gaps, test coverage holes, and LLM-friendliness issues.
Also in 7 projects that use this
SentrySkillsecurity-review
Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.
Also in 9 projects that use this
MicrosoftSkillapi-design
Guide for designing and documenting RESTful APIs. Use when asked to design an API, create endpoints, or document an API.
Also in 3 projects that use this
OpenAISkillsystematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Also in 3 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- anthropics/knowledge-work-plugins★ 36ksame name
- genspark-ai/genoffice★ 12ksame name
- microsoft/intelligent-terminal★ 2.2ksame name
- borgbase/vykar★ 722same name
- ShipSecAI/studio★ 380same name
- nledford/engineering-review-board★ 11same name
- bis-code/claude-toolkit★ 8same name
- frnkgns/Overgeared-Skills★ 7same name
- Sagargupta16/agent-recipes★ 4same name
- vikisingh23/neuraforge-ai★ 4same name
17 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ads-comment-triageSkill
- ads-creative-labSkill
- ads-fatigue-watchSkill
- ads-policy-checkSkill
- ads-reportSkill
- audience-planSkill
- audit-and-fixSkill
- bootstrap-content-agentSkill
- brand-lessonsSkill
- catalog-feed-auditSkill
- competitor-analysisSkill
- crawl-and-queueSkill
- create-videoSkill
- creator-startSkill
- daily-runSkill
- daily-topic-videoSkill
- design-campaignSkill
- freshness-checkSkill
- geo-optimizeSkill
- localize-videoSkill
- motion-craftSkill
- new-templateSkill
- promo-calendarSkill
- repurposeSkill
- research-and-captureSkill
- review-gateSkill
- story-videoSkill
- talking-head-editSkill
- topic-radarSkill
- ugc-koc-briefSkill
- video-and-postSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 47
Report honestly: Only what findings holds — each has n on both sides.
“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Performance review — video nào hiệu quả, và vì sao
Hướng dẫn từng bước cho người dùng
Chạy lệnh
node scripts/…ở thư mục gốc của kit — thư mục cóAGENTS.md, hai cấp trên file này (nếu skill được cài bằnginstall-skills.mjs --kit, đường dẫn nằm trong file.kit-rootcạnh file này).
Kit làm và đăng video, nhưng tới giờ chưa biết video nào được xem. Skill này đọc số liệu thật của kênh và chỉ ra điều gì đang hiệu quả với chính kênh này, không phải lời khuyên chung chung.
Dẫn người dùng theo các bước dưới, đầu mỗi bước báo "Bước n/N — <tên bước>".
| Bước | Agent làm gì | Người dùng cần làm |
| 1. Lấy số liệu | Hướng dẫn xuất file CSV (bên dưới), hoặc lấy số YouTube bằng API key | Xuất file từ app và đưa vào chat/thư mục |
| 2. Nhập | node scripts/analytics/perf.mjs import <file.csv> --platform tiktok | — |
| 3. Phân tích | node scripts/analytics/perf.mjs learn → brain/insights.md | — |
| 4. Đọc kết quả | Kể lại 3–5 điều số liệu nói, kèm số bài làm căn cứ | Quyết định thử gì tiếp |
| 5. Thử có chủ đích | Đề xuất 2–3 video tới để kiểm chứng một phát hiện (ví dụ cùng chủ đề, hai kiểu hook) | Duyệt kế hoạch |
Xuất CSV ở đâu (tên menu có thể đổi theo phiên bản app):
- TikTok: TikTok Studio (web) → Analytics → Content → Export (hoặc Tải xuống dữ liệu).
- Facebook: Meta Business Suite → Insights → Content → Export data.
- YouTube: YouTube Studio → Analytics → Advanced mode → Export → CSV. Hoặc không cần xuất:
perf.mjs youtube --channel <UC…>vớiYOUTUBE_API_KEY(chỉ số liệu công khai).
Hay vướng:
- "no row with a views number" → file không phải bản xuất số liệu, hoặc xuất nhầm bảng tổng quan.
- "Chưa đủ dữ liệu" là câu trả lời đúng khi kênh còn ít video: cần ≥ 3 bài mỗi nhóm.
- Bài không khớp với video nào của kit → tiêu đề đăng khác hẳn tiêu đề lúc làm; vẫn được tính theo nền tảng/giờ đăng, chỉ không tính theo thể loại/hook.
Quy trình chi tiết (cho agent)
- Get numbers. CSV via
perf.mjs import(columns are matched by meaning, English or Vietnamese; "1,2K", "12,5%", "0:42" all parse). YouTube:perf.mjs youtube --channel …. Re-importing later updates the same posts. - Learn.
perf.mjs learn(default metricviews;--metric completionwhen the export has a "watched full video" column — retention is the better signal for hooks). Each post is divided by its platform's median ("lift" — ×2 = twice the channel's usual), matched by title to the video the kit made (brain/**/script.json— set"genre"in every script so it can be grouped — and talking-head*.cuts.json). - Report honestly. Only what
findingsholds — each hasnon both sides. Say it is correlation: one hot topic can lift a whole genre. Name the top and bottom 3 with their hooks; hooks are what the user can copy or avoid tomorrow. - Feed it forward.
brain/insights.mdis read bycreate-video(genre, length, hook shape),topic-radar(which angles travelled) andreview-gate(a hook shape that keeps losing). Propose 2–3 next videos that TEST one finding rather than assuming it. - Weekly is enough. Numbers of a post from the last 48 h are not settled — say so.
Method and tests: scripts/analytics/lib/perf.mjs, tests/analytics.test.mjs.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

