Add whatidid skill — turn your Copilot sessions into proof of impact

[shailendrahegde]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.

---

Description

This PR adds a skill that turns local Copilot session logs into
a branded HTML impact report — answering "what did I accomplish this
week and what was it worth?"

Why this belongs here

Most awesome-copilot contributions help you use Copilot better.
This one helps you show the value of using Copilot — a gap no
existing skill addresses. It gives individuals, managers, and
organizations a concrete artifact to justify their Copilot investment.

What it does

Capability	Detail
Harvest	Reads ~/.copilot/session-state/ — zero config, fully local
Analyze	AI groups raw sessions into business goals using GitHub Models API, with a deterministic heuristic fallback when API is unavailable
Estimate	Multi-signal effort estimation grounded in 13 peer-reviewed sources (Cambon et al. 2023, Alaswad et al. 2026, SPACE framework)
Report	Self-contained HTML with KPI cards, ROI metrics, collaboration patterns, skill distribution, and transparent estimation evidence
Share	Optional Outlook email delivery

What makes the estimation novel

The skill doesn't guess hours from token counts. It extracts enriched
signals that don't exist in raw logs — substantive turns (filtering
trivial approvals), weighted tool calls (reads vs edits vs runs),
active engagement time (gap-based), and iteration depth (re-edits per
file) — then fuses them via a max() base + capped complexity
multipliers + additive lines-of-code. Every design decision traces to
a specific research finding.

Full methodology:
effort-estimation-methodology.md

Privacy

Fully local-first. No telemetry, no cloud uploads, no external data
collection. AI analysis uses the user's own GitHub token. The report
includes a privacy banner by design.

Structure

skills/whatidid/
└── SKILL.md    # Skill manifest with quick start and methodology link

The skill references the
microsoft/What-I-Did-Copilot
repo where the full tool lives — keeping the skill lightweight while
giving users the complete pipeline.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.
• Other (please specify):

---

By submitting this pull request, I confirm that my contribution
abides by the Code of Conduct and will be
licensed under the MIT License.

[github-actions]

🔍 Skill Validator Results

2 resource(s) checked | ✅ All checks passed

Full output

Found 1 skill(s)
[whatidid] 📊 whatidid: 456 BPE tokens [chars/4: 492] (detailed ✓), 9 sections, 1 code blocks
[whatidid]    ⚠  No numbered workflow steps — agents follow sequenced procedures more reliably.
�[32m✅ All checks passed (1 skill(s))�[0m

[Copilot]

Pull request overview

Adds a new whatidid skill to the awesome-copilot catalog, providing guidance to generate an HTML “impact report” from local GitHub Copilot session logs (via an external tool repo), and registers the skill in the skills index.

Changes:

• Added skills/whatidid/SKILL.md describing the skill, quick start, requirements, privacy, and research basis.
• Added the whatidid entry to docs/README.skills.md so it appears in the skills list.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
skills/whatidid/SKILL.md	New skill manifest and usage guidance for generating an impact report from Copilot session logs.
docs/README.skills.md	Registers the new whatidid skill in the central skills README table.