Engineering Advanced DocumentationHistoryWorkflow

Project History

Track development history across AI sessions. Maintains worklog, changelog, feature-log, and implementation-docs in .project/ files.

AI tools lose context between sessions. This skill maintains .project/ files as the source of truth for goals, decisions, cross-project dependencies, and effort history. Works for single-repo, mono-repo, and multi-repo workspaces with slash commands for quick updates.

Added Mar 19, 2026

$npx skills add johnefemer/skillfish --skill project-history

Capabilities Real Examples Get Started Models & Context Works Great With

What This Skill Can Do

Concrete capabilities you get when you install this skill.

Maintain daily changelogs with goal-driven entries and commit references

Track daily worklog with T-shirt sizing and outcome tracking

Create and update living feature-log documents for each feature

Generate implementation docs for large tasks with decisions and trade-offs

Adapt to single-repo, mono-repo, and multi-repo project structures

Integrate with github-project-manager for velocity calibration

Real Conversations

See how the Project History skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

I just finished the WhatsApp channel integration across backend-api, frontend-app, and proxy-service. Can you update the project history?

Agent

I'll update all 4 file types. First, let me collect today's commits:

git -C backend-api log --oneline --since="today"
git -C frontend-app log --oneline --since="today"
git -C proxy-service log --oneline --since="today"

Updated .project/changelog/2026-03-19.md:

## [backend-api, frontend-app, proxy-service]

**Goal:** Enable self-service WhatsApp channel setup — reduce setup from 45 min to 2 min

### Added
- WhatsApp channel configuration API endpoints
- Self-service setup wizard in dashboard
- Webhook routing for WhatsApp messages

### Commits
- backend-api: `abc1234`, `def5678`
- frontend-app: `ghi9012`
- proxy-service: `jkl3456`

Updated .project/worklog/2026-03-19.md with task entry, Size L (5 pts), and daily summary table.

Created .project/feature-log/whatsapp-channels.md with overview, current state, cross-project dependencies, and integration history.

All files written with goal-driven entries and commit references.

You

/worklog

Agent

Running worklog update for today.

Collecting commits: git log --oneline --since="today"

Found 3 tasks completed today. Here's the generated worklog:

# Worklog — 2026-03-19

## Goals
- [x] Fix cart persistence bug
- [x] Update API rate limiting
- [ ] Deploy monitoring dashboard (blocked)

## Tasks

### Fix cart persistence bug
- **Goal:** Stop users losing cart items on refresh
- **Outcome:** Implemented localStorage persistence, tested across browsers
- **Size:** S (2-4 hours, 2 pts) — actual: ~2 hours
- **Projects:** [root]
- **Issue:** #142

### Update API rate limiting
- **Goal:** Prevent abuse without affecting legitimate users
- **Outcome:** Sliding window rate limiter, 100 req/min per API key
- **Size:** M (4-8 hours, 3 pts) — actual: ~5 hours
- **Projects:** [backend-api]

## Summary
| Metric | Value |
|--------|-------|
| Tasks completed | 2 |
| Total effort | S + M = 5 pts |
| Blocked items | 1 |

Written to .project/worklog/2026-03-19.md.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Works with any model that can read/write files. No special reasoning requirements — the skill is template-driven.

Context Window

SKILL.md is ~15KB. Fits comfortably in 32K context. For mono-repo projects with many feature-logs, 100K+ context helps.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Works Great With

These skills complement Project History for end-to-end coverage. Install them together for better results.

GitHub Project Manager

AI project manager for GitHub Issues & Projects v2 boards.

GitHubIssues

Changelog Generator

Generate structured changelogs from conventional commits.

ChangelogReleases

Git Commit Hygiene

Install a commit-msg hook that auto-strips AI tool attribution from git commits.

GitHooks

Release Manager

Changelog generation, semantic versioning, and readiness checking.

ReleasesVersioning

$ skillfish add johnefemer/skillfish --all # install all skills at once

Ready to try Project History?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.