SKILL.md
Recall
On GitHub Copilot, read the platform mapping, including its per-skill notes, before following this skill.
On Muse, read the platform mapping, including its per-skill notes, before following this skill.
Before you start or resume work, you rebuild the user's recent working context and hand back a tight capsule of where things stand now and what to do next.
Keep it tight and on-topic. Read only what the in-scope threads need, then stop.
Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the why skill searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your transcripts alone.
Transcripts live at ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/projects/<encoded-cwd>/<uuid>.jsonl. Every line is one chat message. Run node <plugin>/skills/reflect/scripts/claude-project-dir.mjs to print this session's directory rather than building <encoded-cwd> by hand. Claude Code turns each character other than an ASCII letter or digit into "-" (so /Users/you/my_app.web becomes -Users-you-my-app-web), shortens a name past 200 characters with a hash, and takes CLAUDE_CODE_PROJECT_DIR_NAME in its place when that is set with CLAUDE_CONFIG_DIR.
Recall
On GitHub Copilot, read the platform mapping, including its per-skill notes, before following this skill.
On Muse, read the platform mapping, including its per-skill notes, before following this skill.
Before you start or resume work, you rebuild the user's recent working context and hand back a tight capsule of where things stand now and what to do next.
Keep it tight and on-topic. Read only what the in-scope threads need, then stop.
Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the why skill searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your transcripts alone.
Transcripts live at ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/projects/<encoded-cwd>/<uuid>.jsonl. Every line is one chat message. Run node <plugin>/skills/reflect/scripts/claude-project-dir.mjs to print this session's directory rather than building <encoded-cwd> by hand. Claude Code turns each character other than an ASCII letter or digit into "-" (so /Users/you/my_app.web becomes -Users-you-my-app-web), shortens a name past 200 characters with a hash, and takes CLAUDE_CODE_PROJECT_DIR_NAME in its place when that is set with CLAUDE_CONFIG_DIR.