Incremental Implementation
Deliver changes in small verifiable increments. Use when implementing a multi-file feature, refactor, migration, bug fix, or any task that is large enough to become risky if completed in one pass.
Install
$ agentstack add skill-hsienw-ai-agent-engineering-playbook-incremental-implementation ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-hsienw-ai-agent-engineering-playbook-incremental-implementation) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Incremental Implementation
Skill Interface
- Name: incremental-implementation.
- Description: Deliver changes in small verifiable increments for multi-file features, refactors, migrations, bug fixes, or any task that becomes risky when completed in one pass.
- Parameters: Target outcome, affected files or modules, current constraints, risk areas, available tests or checks, and any required compatibility or rollout conditions.
- Instructions: Use this skill when the task is broad or risky. Define the smallest useful slice, implement only that slice, verify it, fix failures before expanding scope, and report completed slices plus remaining work.
Build one complete slice at a time. Each slice should leave the workspace in a working, testable state.
Process
- Define the smallest useful slice.
- Implement only that slice.
- Run the most relevant verification.
- Fix failures before expanding scope.
- Record what changed and what remains.
- Move to the next slice.
Slicing Strategies
- Vertical slice: one path through the stack from input to observable result.
- Contract-first slice: define types, schemas, or API shape before parallel
implementation.
- Risk-first slice: prove the most uncertain technical point early.
- Additive slice: introduce new behavior behind safe defaults before replacing
old behavior.
Scope Rules
- Do not mix feature work with unrelated cleanup.
- Do not rename or reformat files outside the slice.
- Do not add abstractions before repeated use proves they are needed.
- Do not leave broken intermediate states.
- If a feature is incomplete but must coexist with production code, gate it with
an explicit safe default.
Verification
After each slice, run the narrowest meaningful check. At the end, run the full checks required by the changed area. Do not repeat the same passing command without intervening changes.
Handoff
Report:
- Completed slices.
- Commands actually executed.
- Failures and fixes.
- Unverified areas.
- Suggested next slice.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: HsienW
- Source: HsienW/ai-agent-engineering-playbook
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.