Review — Report-only audit. No files created or modified.

Prompt History Backfill — Full Audit

Generated 2026-06-04 • Mode: report-only • Repo: agentic-skills

Table of Contents

Scope & Sources

Repository: /Users/georgele/projects/tools/agentic-skills

Date range: All history (no date filter applied)

Mode: Report-only (no files written)

Sources Read

SourceStatusSize
~/.claude/history.jsonlOK9,964 lines
~/.codex/history.jsonlOK6,543 lines
~/.codex/sessions/**/*.jsonlOK2,676 session files

Sources missing: None

Summary Statistics

15
Existing prompt dirs
67
Existing prompt files
13
Skills missing dirs
~700
Total invocations found

Invocations by Source

SourceUnique High-ConfidenceDistinct SkillsDate Range
Claude Code54 (115 skill×session pairs)182026-04-07 – 2026-06-04
Codex599 (604 skill×session pairs)202026-04-07 – 2026-06-03

Existing prompt files cover May 30 – Jun 4 only. April – late May invocations are almost entirely uncaptured.

Skills Missing Prompt Directories

These skills were invoked in conversation history but have no prompts/ directory at all. Running --apply would create directories and backfill prompt files for high/medium confidence matches.

SkillClaude InvocationsCodex InvocationsTotalPriority
run107585High
targeted-skill-builder35659High
benchmark-agent-review13233High
provision-agentic-config202Medium
skill-interview213Medium
code-review101Medium
youtube-audit101Medium
review033Medium
idea-scope-brief011Medium
expert-review011Medium
verify011Medium
simplify011Medium
schedule011Medium

Backfill would create: 13 new prompts/ directories and an estimated 192 prompt files for these skills.

Gap Analysis — Existing Directories

These skills already have prompt directories but are missing earlier invocations (mostly April – late May). The "gap" column shows uncaptured invocations.

SkillExisting FilesTotal InvocationsGapCoverage
ship4~307~3031%
benchmark-test-skill2~85~832%
session-triage3~37~348%
analyze-sessions2~34~326%
ship-end5~32~2716%
exec24~28~486%
pack8~18~1044%
sync2~15~1313%
investigate14~15~193%
skills1~87~861%
init-agentic-skills2~20100%
devtool-docs-audit1~10100%
commit-and-push-by-feature1~10100%
skill-creator3~30100%
positioning1~10100%

Note on bare invocations: Many /ship, /run, /sync, /skills, and /ship-end invocations are bare commands with no substantive prompt text. Backfilling bare /ship (prompt = just "/ship") may add volume without value. The --apply run would still capture them per the convention, but consider filtering to substantive prompts only.

Representative Uncaptured Prompts

High-value uncaptured prompts with substantive user context (not bare commands):

SkillDateSourcePrompt (excerpt)Confidence
analyze-sessions2026-04-11Claude"when we are doing the run and ship loops, I notice that there are pre-existing issues identified after a run..."High
analyze-sessions2026-04-28Claude"determine if based on conversation history and past plan-interviews... if there are any issues from the par..."High
analyze-sessions2026-04-29Claude"analyze the recent bismarck-v5 attempt to parallel work using codex..."High
analyze-sessions2026-04-30Claude"how are the codex sessions running gpt 5.5 low vs gpt 5.5 xhigh doing?..."High
analyze-sessions2026-05-01Claude"we have some holes in our skills where recommendations for next steps are broken..."High
analyze-sessions2026-05-07Claude"audit and compile a report on how we've been using the ux-variations skill and ui-interview..."High
investigate2026-04-19Claude"Do you agree with these recommendations? Do not implement anything..."High
investigate2026-05-27Claude"evaluate our skills to ensure we can properly support branching research..."High
investigate2026-06-03Claude"audit all of the skills to determine if there any language inconsistency..."High
investigate2026-06-03Claude"evaluate our skills list and determine if we should have a skill called repo glossary..."High
skill-interview2026-05-20Claude"we need a skill to help migrate an existing project to our new workflow..."High
skill-interview2026-05-20Claude"create a quiz me skill which will interrogate the user as to their understanding..."High
targeted-skill-builder2026-05-20Claude"desk-flip benchmark artifact-reference false-negative"High
benchmark-test-skill2026-05-20Claude"desk-flip"High
benchmark-agent-review2026-05-20Claude"desk-flip"High

Coverage Checkpoint Gate

Gate: Coverage Checkpoint

The audit found ~700 high-confidence invocations across 28 distinct skills, but only 67 prompt files exist covering ~5 days of a 2-month history window. The bulk of uncaptured invocations are bare commands (/ship, /run, /sync) with minimal prompt text.

Q1: Should bare command invocations (prompt text ≤ 20 chars, e.g. just "/ship") be backfilled?

Gate: Backfill Scope

13 skills have zero prompt history. 10 skills have directories but significant gaps.

Q2: Which skills should be prioritized for backfill?

Approval Gate

Gate: Proceed to Apply

Q3: Ready to run /prompt-history-backfill --apply with the selected scope?

Verification Notes

Compile Section

3 required questions unanswered

Copied!