Implement planned work
SkillDev toolsImplement work from a spec, ticket, or agreed conversation. Use explicitly when the user wants an existing plan carried through to working code.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Implement planned work skill
What this skill tells your AI
The instructions your AI receives, as published by stevesolun/ctx in .agents/skills/implement/SKILL.md and read by ahel’s review.
Confirm the intended outcome and inspect the relevant code, tests, and repository conventions. Resolve ambiguity only when it would materially change the result; otherwise make a reasonable scoped assumption and proceed.
Implement the smallest coherent change that satisfies the source requirements. Use test-first development when requested or when a focused failing test is the clearest feedback loop. Avoid speculative abstractions and unrelated cleanup.
Validate the changed surface proportionally: start with focused evidence and expand to broader checks when risk or repository contracts justify it. Use a separate review when semantic risk remains or the user requests one.
Report what changed, what was verified, and any remaining uncertainty. Commit, publish, or mutate tracker state only when requested or clearly included in the active workflow.
Signals
- GitHub stars
- 585
- Forks
- 71
- Last commit
- Aug 2026
- Hacker News mentions
- 20
Advanced
- Catalog kind
- skill
- Gateway key
implement-stevesolun- Source
- github.com/stevesolun/ctx