pre-goal
chenwei791129/agent-skills/skills/pre-goal/SKILL.md
Use when the user is about to launch /goal (or any long-running autonomous agent task) and the task is still vaguely defined, mentions "pre-goal" / "define the goal" / "write a goal prompt", or complains that a previous /goal run drifted off course, wrapped up too early, or produced unsatisfying results. Guides the user to pin down the definition of done before launching.
No licence file, so all rights are reserved — read it at the source. Read it on GitHub.
More agent context in chenwei791129/agent-skills
29 other files this repository gives its agents.
CLAUDE.md
Skill
- acli-jiraskills/acli-jira/SKILL.md
- buffett-investment-strategyskills/buffett-investment-strategy/SKILL.md
- chrome-devtoolsskills/chrome-devtools/SKILL.md
- deep-researchskills/deep-research/SKILL.md
- evaluate-skillskills/evaluate-skill/SKILL.md
- facebook-scraperskills/facebook-scraper/SKILL.md
- find-claude-sessionskills/find-claude-session/SKILL.md
- finmindskills/finmind/SKILL.md
- gh-actions-permissionsskills/gh-actions-permissions/SKILL.md
- glab-cliskills/glab-cli/SKILL.md
- go-concurrency-patternsskills/go-concurrency-patterns/SKILL.md
- grafanaskills/grafana/SKILL.md
- grillingskills/grilling/SKILL.md
- gws-gmailskills/gws-gmail/SKILL.md
- malware-repo-analysisskills/malware-repo-analysis/SKILL.md
- ndc-lightscoreskills/ndc-lightscore/SKILL.md
- newcityskills/newcity/SKILL.md
- postgresskills/postgres/SKILL.md
- powershell-style-guideskills/powershell-style-guide/SKILL.md
- prompt-engineeringskills/prompt-engineering/SKILL.md
- reimburse-requestskills/reimburse-request/SKILL.md
- sap-leave-requestskills/sap-leave-request/SKILL.md
- shell-style-guideskills/shell-style-guide/SKILL.md
- slack-notifyskills/slack-notify/SKILL.md
- stylingskills/styling/SKILL.md
- tw-trading-agentsskills/tw-trading-agents/SKILL.md
- web-browsingskills/web-browsing/SKILL.md
- youtube-transcribeskills/youtube-transcribe/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.