prompt-report

prompt-report — End-of-session prompting summary

You produce a one-shot summary from the data that the analyze-prompt skill has persisted this session. You do NOT re-analyze prompts and you do NOT modify any data file (read-only).

GATE

Read the session data first. If it is missing or empty, tell the user no prompts have been analyzed yet this session and to run analyze-prompt first — then stop.

DATA (read-only)

• Data file: ${CLAUDE_PROJECT_DIR}/.prompt-analyzer/${CLAUDE_SESSION_ID}.json

Injected data

!`test -f "${CLAUDE_PROJECT_DIR}/.prompt-analyzer/${CLAUDE_SESSION_ID}.json" && cat "${CLAUDE_PROJECT_DIR}/.prompt-analyzer/${CLAUDE_SESSION_ID}.json" || echo "NO_DATA_YET"`

If NO_DATA_YET, run the GATE fallback above.

List other sessions (for optional cross-session view)

!`ls -1 "${CLAUDE_PROJECT_DIR}/.prompt-analyzer/"*.json 2>/dev/null | grep -v config.json | wc -l`

Computation (from persisted data only)

• avg_score = mean(scores); trend from first_score → latest_score
• requirement_match_rate = requirement_matches / total_prompts × 100
• best prompt = history entry with max score; worst = min score
• focus habit = the focus_habit field (the one habit to build); biggest recurring habit = max key in habit_tally
• improvement curve = the scores[] array rendered as a sparkline (▁▂▃▄▅▆▇█ mapped 1–10)
• self-correction rate = total_self_corrections / total_prompts × 100
• efficiency = (1 − est_wasted_tokens / est_prompt_tokens) × 100, shown as %
• est. tokens spent = totals.est_prompt_tokens; est. wasted on redos = totals.est_wasted_tokens (label both "est." — heuristic, not an exact tokenizer)
• time impact (est.) = frame waste in minutes: each self-correction ≈ 1–2 min of rework; report "≈N min lost to redos" and "≈N min saved by your strong prompts" (label "est.")
• cross-session rollup = if the "other sessions" count > 0, note whether the focus habit is improving across sessions (mention it qualitatively; do not read other files unless asked)