Add context-hygiene tip to deep-review (and other token-heavy skills)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 0
- Forks
- 1
- Avg merge
- 1d 3h
- Merged PRs (30d)
- 7
Description
Background
Per the findings in #158, the harness can't auto-clear context before a skill runs, so we reinforce a /clear-before-work habit via a one-line tip in the skill hand-off. PR #159 added that tip to start-work and the team standard.
Ask
Extend the same one-line context-hygiene tip to other skills that rarely need prior conversation history and benefit from a clean slate — primarily deep-review, and consider improve-stories, self-review, and tfvc-search.
Keep it to a single closing-line nudge per skill (matching the start-work wording), not a behavioral change. The skill cannot clear context itself (self-clearing paradox, see #158) — the tip just trains the user habit.
Acceptance
-
deep-reviewhand-off ends with the context-hygiene tip. - Decide per-skill whether the others warrant it; document the call.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the hand-off text for deep-review and compare its wording with the tip added to start-work and the team standard in PR #159. Add the single closing-line context-hygiene tip to deep-review, review improve-stories, self-review, and tfvc-search, and document which skills warrant it; done means the acceptance items are addressed without behavioral changes.
Written by the indexing model from the issue text.
Assessment
- Domain
- developer-experience, documentation
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 68/100