verify-ref
/verify-ref
Comprehension gate before porting, copying, or adapting an existing implementation. Proves understanding of the reference code before any new code is written. Use when the task is "port X", "copy how Y does it", "adapt Z", or reimplementing existing behavior.
- Author
- hiendinhngoc ↗
- Repository
- unknowns ↗
- Licence
- MIT
- Last repository change
- 14.07.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 14.07.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Comprehension gate before porting, copying, or adapting an existing implementation. Proves understanding of the reference code before any new code is written. Use when the task is "port X", "copy how Y does it", "adapt Z", or reimplementing existing behavior.
Triggers from the description
Original author description
Comprehension gate before porting, copying, or adapting an existing implementation. Proves understanding of the reference code before any new code is written. Use when the task is "port X", "copy how Y does it", "adapt Z", or reimplementing existing behavior.
How it works
- Process
- Output format
SKILL.md preview
---
name: verify-ref
description: Comprehension gate before porting, copying, or adapting an existing implementation. Proves understanding of the reference code before any new code is written. Use when the task is "port X", "copy how Y does it", "adapt Z", or reimplementing existing behavior.
version: 1.0.0
author: Hien Dinh
license: MIT
---
# Reference Verification
Prove you understand the reference implementation BEFORE porting it.
Misunderstood references produce confidently wrong ports.
<HARD-GATE>Write no implementation code until the user confirms the
comprehension proof below.</HARD-GATE>
## Process
1. **Locate the reference.** Use the argument or conversation context. If
ambiguous, ask which implementation is the reference — don't guess.
2. **Set a behavioral boundary, then read it fully.** Read the referenced unit,
its direct callers, and direct dependencies that affect observable behavior.
Follow deeper calls only while they change outputs, side effects, errors, or
ordering. List unresolved or external dependencies instead of recursively
expanding without a stop condition.
3. **Produce the comprehension proof**, covering:
- **Data flow:** inputs → transformations → outputs, in order
- **Edge cases handled:** every guard, fallback, retry, and special case,
and what each protects against
- **Invariants:** what must remain true before/after (ordering, uniqueness,
idempotency, transactional boundaries)
- **Hidden dependencies:** globals, config, environment, call-order
assumptions, side effects the signature doesn't show. For UI code, also
name the framework semantics the reference leans on: lifecycle hooks that
fire once vs. per-render, view identity, and task/cleanup-on-teardown
behavior — these are where ports break silently.
Proportionality: for a small same-repo adaptation (roughly ≤30 lines, no
concurrency, no money/auth/persistence), a short proof of just **Data flow**
and **What would break if I got this wrong?** suffices — but step 2's full
read of the reference and its callers is never skipped; that read is where
latent bugs surface.
4. **Self-challenge.** Add a section: "What would break if I got this wrong?" —
name the 2-3 misreadings most likely to cause a subtly wrong port and say
why your reading is correct (cite file:line evidence).
5. **Gate.** Ask the user to confirm the proof or correct it. Only after
confirmation may implementation begin. A plan the user already approved that
names this exact port also counts as confirmation — say the proof is being
accepted under that approval and proceed. Otherwise, if no interactive user
is available, stop after the proof and identify the exact uncertainty that
needs review; do not silently treat the proof as approval.
## Output format
```
## Comprehension proof: <reference name> (<file:line range>)
### Data flow
### Edge cases handled
### Invariants
### Hidden dependencies
### What would break if I got this wrong?
```
Files in this package (2)
- SKILL.md 3 KB
- agents/openai.yaml 1 KB
Versions
The database has no other skills named verify-ref.
Database snapshot: 13.11.2026 · package version 79ad57ec43da (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100write-plan
Use when asked to write, draft or start an implementation plan for a change that already has an intent and a spec, before any code exists. - 100strategic-planning
Use when facing multi-step development work that needs decomposition into tasks, before writing any implementation code - 100port-spec
Turn a complete written specification into working code or a vault artifact. Use when implementing a spec, building from a brief, or porting a spec to code. - 100planning-flow
Use when the user asks for a plan for a coding change — "plan this", "how would we build", "write me a plan for", "/planning-flow <ask>" — before any code is written, especially when the change needs research across a codebase, has open questions only the user can answer, or… - 90port-features
Port a feature from an existing repository by copying its actual code and editing the copy, so its bug fixes and behavioral nuances survive, then naturalizing it to this project's names and environment. Use when asked to copy or port an existing feature (especially an exact… - 100quiz-me
Use right after writing or editing code or files for the user — before ending your turn — to quiz them on what was just built and confirm they actually understand it. Also triggers on "quiz me", "test my understanding", "check what I learned", "comprehension check", or…