Daily Dev Tools: 6 Skills That Read Your Repo / أدوات المبرمج اليومية
Six tamam skills for the jobs a developer does every week. Each one reads your project's own files with a bundled Python script that only reads, makes no network calls and runs none of your code. Every fact names its source (the file and line, the commit, or the plan line), what the files do not say becomes a question for the team instead of a guess, and every result can be written in English or in Arabic.
- Upgrade Impact Report: what breaks if you update your dependencies. A plan ordered by risk from your lockfiles, with where each package is used, what to test and how to roll back.
- File Backstory: why a file is the way it is, from its git history and blame. Every reason quoted from a commit or marked as unknown.
- Slow Query Report: why a PostgreSQL or MySQL query is slow, from its execution plan, with a rewrite, a suggested index with its costs and how to confirm on a copy.
- Team Decision Records: this week's meeting notes and chats into decision records you commit, with who decided, when, and the exact words.
- CLI Reference Page: your command-line tool's reference page from its code, with examples that use only real flags.
- On-Call Runbook Builder: an on-call runbook for a service from its repository files, every command with its source.
$22 for the six instead of $32 one by one.
بالعربي: ست مهارات من تمام لشغل المبرمج اليومي. كل مهارة تقرأ ملفات مشروعك بسكربت بايثون يقرأ فقط، بلا اتصال بالشبكة ولا تشغيل لكودك. كل معلومة تذكر مصدرها (الملف والسطر، أو الإيداع، أو سطر خطة التنفيذ)، وما لا تقوله الملفات يصير سؤالًا للفريق بدل التخمين، وكل نتيجة تُكتب بالإنجليزي أو بالعربي: خطة تحديث المكتبات، وقصة ملف من git، وتقرير استعلام SQL بطيء، وسجلات قرارات الفريق، وصفحة وثائق أوامر CLI، ودليل المناوبة. 22$ للست بدل 32$ لكل واحدة على حدة.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 6 skills unlock instantly in your library.
What's included
6 skillsFor developers: point your agent at your project and get a dependency upgrade plan ordered by risk, from your own lockfiles and imports, with where each package is used, what to test and how to roll back, every point with its file and line. خطة تحديث المكتبات مرتبة بالمخاطر من ملفات مشروعك.
For developers: point your agent at one file or folder and get its backstory from git, the changes that shaped it, what was undone and which commits wrote today's lines, every reason quoted from a commit or marked inferred or unknown. قصة ملف واحد من git، وكل معلومة بمصدرها.
For developers: paste a slow PostgreSQL or MySQL query and its execution plan, and get a report with the diagnosis, each point citing its plan or query line, a rewrite, a suggested index with its costs, and how to confirm on a copy. No database connection. تقرير استعلام SQL بطيء، وكل نقطة بسطرها.
For team leads: give your agent the week's meeting notes and chat exports, and get decision records ready to commit, one per decision with who decided, when and the exact words from the notes, plus an action list with owners and due dates. قرارات الأسبوع من المحاضر، بصاحب كل قرار وموعده.
For developers: point your agent at the repo and get your CLI's reference page from its own code, every command and option with its default and choices, examples using only real flags, exit codes and error messages with clearer suggestions, each with file and line. وثائق أوامر CLI من الكود نفسه.
For developers, freelancers and agencies who run a service or hand one over: point your agent at the repo and get an on-call runbook where every command names its effect and the file and line it came from. دليل المناوبة لخدمتك من ملفات مستودعها، بالإنجليزي أو بالعربي.
See it in action
Upgrade Impact Report: What Breaks If You Update
Example session with this skill installed
We are behind on our npm and Python packages. What breaks if we update? Plan it from our lockfiles, with a way back for each step.
- Read your context and instructions
- Compiled the upgrade impact report
Step 2 (careful): express 4.19.2 -> 5.1.0
Packages
express4.19.2 -> 5.1.0 (major, runtime)@types/express4.17.21 -> 5.0.0 (major, dev): the type definitions ofexpress, moved in the same step so the types match the code.
npm install express@5.1.0
npm install -D @types/express@5.0.0
Where used
src/app.ts:1: creates the app, parses JSON bodies and mounts every router.src/routes/health.ts:1,src/routes/labels.ts:1,src/routes/parcels.ts:1:Router.src/middleware/auth.ts:1,src/middleware/errors.ts:1: types only (import type).
What could break
- Question: the Express 5 release notes and migration guide were not read in this session. Who reads them and checks them against the lines in this step before merging?
What to test
npm run typecheck(package.json:14): the type definitions move in this step.npm run build(package.json:11)npm test(package.json:13):test/parcels.test.tsandtest/labels.test.tscall the API throughcreateApp.- By hand, on a staging copy:
/healthanswers, and an unknown parcel route such as/parcels/a/bstill gets the JSON 404 fromsrc/app.ts:17.
Rollback
git checkout -- package.json package-lock.json
npm ci
- Confirm:
npm ls express @types/expressshows 4.19.2 and 4.17.21, andnpm testpasses.
$ python3 scripts/plan_check.py upgrade/upgrade-plan.md --facts upgrade/facts.json --project .
summary: 0 FIX, 0 ADVICE in upgrade-plan.md (7 steps: 1 batch, 6 careful; 14 packages; 22 open questions). It checks evidence and structure against the lockfiles, manifests and source; it does not tell whether the upgrade is safe: run each step's tests on a branch.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.