Gemini CLI PR improves /skill-name activation prompt and finally documents manual skill invocation
lostmartian · ghdev · 2026-10-19
- A PR to Gemini CLI (#29818) improves manual skill activation: previously, invoking /<skill-name> with no arguments sent the model only "Use the skill <name>", leaving no clear task and forcing follow-up prompts. The model is now told to continue the in-progress task with the skill, or ask the user what it's for.
- The second fix is documentation: skills docs never mentioned manual activation, so users didn't know it existed. The PR adds an "Activating a skill manually" section to docs/cli/skills.md, noting built-in skills aren't exposed as slash commands.
- Implementation adds an exported getSkillPostSubmitPrompt(skillName, args) helper; explicit args pass through unchanged, whitespace-only args count as none. It doesn't overlap PR #29546 (non-interactive -p support) and can merge independently.
More from coding & agent
- Laude Institute launches FrontierCS 2: agents must beat deleted paper contributions blind — lateinteraction · 2026-10-23
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23