Record Knowledge
SkillDev toolsThis skill lets your AI control screen recordings for you. It can start, stop, and pause recordings, and mark important moments while recording. Finished recordings are saved as organized files so they are easy to find later.
Use Record Knowledge in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Record Knowledge and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Record Knowledge skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add the skill, then ask your AI to record your screen and tell it when to pause, stop, or mark a moment. Your recordings will be saved as files you can open later.
What your AI can do with it
- Start a screen recording when you ask
- Pause and resume a recording in progress
- Stop a recording when you are finished
- Mark moments during a recording so they are easy to find later
- Save recordings as organized files
What this skill tells your AI
The instructions your AI receives, as published by kdlbs/kandev in .agents/skills/record/SKILL.md and read by Ahel’s review.
Record significant decisions for future work. Reconcile the affected requirements and system designs after the decision.
Record a decision
Create an ADR when all statements are true:
- The choice creates a durable constraint, boundary, contract, ownership rule, operational invariant, or repository-wide convention.
- Meaningful alternatives have different trade-offs.
- Future work must follow or supersede the choice.
- A requirement, system design, test, or work order does not preserve enough rationale.
Do not create an ADR for a simple feature, local refactor, routine dependency change, plan sequence, or temporary migration step.
ADR procedure
- Choose an ID in the form
YYYY-MM-DD-short-title. - Make sure that
docs/decisions/<id>.mddoes not exist. - Create the ADR with the template below.
- Run
python3 scripts/list-docs.py decisions --format pathsto confirm the new ADR is discoverable. Do not edit a catalog row. - Reconcile affected specifications.
Existing numeric ADR IDs remain valid. Do not rename them.
# ADR-YYYY-MM-DD-short-title: Short title
**Status:** accepted | superseded by <adr-id> | deprecated
**Date:** YYYY-MM-DD
**Area:** backend | frontend | infra | protocol | workflow
## Context
Explain the situation and the need for a decision.
## Decision
State the selected rule, boundary, or contract.
## Consequences
State benefits, costs, and follow-up constraints.
## Alternatives Considered
State each meaningful alternative and why it was not selected.
Reconcile specifications
Read docs/specs/README.md, the owning system README.md, and the relevant
files in docs/specs/guide/. Use the catalog command to locate the owning
requirements and designs.
Apply these rules:
- Confirm the owning system from the durable contract. Do not assign ownership to UI only because users observe the decision there.
- If the decision changes observable behavior, update the owning requirement
and its
REQ-*orAC-*criteria. - If the decision changes technical boundaries or contracts, update the owning system design.
- If both change, update both artifacts and preserve their references.
- If the decision is internal and does not change a documented design, the ADR is sufficient.
- If no product system applies, state that fact in the ADR.
Do not copy the ADR into requirements or system design. Link the ADR from the affected design. Requirements contain observable outcomes, not decision rationale.
During legacy migration, use this command to locate existing sources:
python3 scripts/list-docs.py specs --kind legacy --format paths
Do not create a new generic spec.md file.
Validation
Run:
python3 scripts/lint-spec-files.py --all
python3 scripts/list-docs.py validate
git diff --check -- docs/decisions docs/specs
Report the ADR, affected requirement IDs, affected system designs, and the validation result.
Signals
- GitHub stars
- 880
- Forks
- 139
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
record- Source
- github.com/kdlbs/kandev