developer
Implement Code Step by Step from a Plan
Large coding plans often fail when an agent edits too much at once. This skill implements one approved plan step at a time, keeps edits scoped, and reports a clear status when the step is done.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "developer" from https://skillstore.io/skills/zhaobolun-code-developer.md and its manifest at https://skillstore.io/api/skills/zhaobolun-code-developer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "developer". Act as the developer role and implement Step 2 from the plan.
Expected outcome:
- DONE
- Changed: order service and its unit test
- Build: 0 errors, 0 warnings
- Self-check note written for the Express lane
Using "developer". Implement Step 4, but the tests fail after your change.
Expected outcome:
- BLOCKED
- Root cause: empty cart returns an undefined price
- Repair round: 0 to 1, next round opens at a higher model tier
- Needs: a decision from the planning role before more edits
Using "developer". Implement Step 6 and confirm the tests pass.
Expected outcome:
- DONE_WITH_CONCERNS
- Changed: request validation module
- Command run: test suite, result 42 passed, 1 skipped
- Concern: one test path needs a real device and was not run
Security Audit
SafeAll 36 static findings are false positives. The scanner flagged Markdown inline-code backticks as JavaScript/shell execution, relative documentation links as path traversal, and dense Chinese prose as high entropy. The two scanned files contain only UTF-8 text with no executable code, network access, or credential handling.
Risk Factors
⚙️ External commands (13)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/zhaobolun-code-developer/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/zhaobolun-code-developer?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/zhaobolun-code-developer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zhaobolun-code-developer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/zhaobolun-code-developer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
zhaobolun-code. (2026). developer security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhaobolun-code-developer/audits/1BibTeX citation
@techreport{zhaobolun-code-zhaobolun-code-developer-2026,
author = {zhaobolun-code},
title = {developer security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/zhaobolun-code-developer/audits/1},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "developer security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "zhaobolun-code"
date-released: "2026-09-17"
url: "https://skillstore.io/skills/zhaobolun-code-developer/audits/1"
identifiers:
- type: other
value: "skillstore:zhaobolun-code-developer:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Work Through a Personal Coding Plan
Turn an approved plan into working code one step at a time and get a clear status after each step.
Add a Developer Role to an Agent Pipeline
Slot a disciplined implementation stage into a multi-agent workflow that already has planning and review stages.
Standardize Automated Code Changes
Apply the same approval gates, scoping rules, and status format to every automated code change.
Try These Prompts
Implement Step 3 from the approved plan. Only edit the files listed in that step and report your status.
Act as the developer role and implement Step 2 from the plan. End your reply with a status line.
Implement Step 5 from the plan. Run the step self-check and include the command and result for each verified item.
The last attempt at Step 4 failed. Write the root cause in one sentence, then open a new higher-tier repair round and report the outcome.
Best Practices
- Confirm an approval marker exists before editing any code.
- Keep every change inside the files listed in the current step.
- Attach a real command and exit code whenever you claim a task is done.
Avoid
- Editing several plan steps in a single pass.
- Changing code before the approval gate has passed.
- Claiming a task is validated without a command and exit code.
Frequently Asked Questions
Does this skill write code without a plan?
Which AI tools support this skill?
What does the skill output?
Can it review code by itself?
What language are the skill and its reports in?
Does it work on its own?
Developer Details
Author
zhaobolun-codeLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
9be34bdd3e1cb2f1280ccd11fa00419204fc4d81
Maintenance freshness
9/18/2026
Usage
0 downloads · 0 views
File structure