what-did-i-get-done

Summarize authored commits over a user-specified time period into a concise update

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cursor-team-kit/skills/what-did-i-get-done/SKILL.md

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an exemplary lean, single-purpose instruction skill: a clear trigger, a well-sequenced read-only workflow, and sharp guardrails with no padding. The only improvement would be anchoring the git-commit reading step with a concrete example command.

Dimension	Reasoning	Score
Conciseness	The body is lean and information-dense ('Exclude merge commits and uncommitted changes', 'Omit cosmetic-only changes (formatting, imports, minor renames)') with zero padding and no explanation of concepts Claude already knows — every token earns its place.	5 / 5
Actionability	The workflow gives concrete, unambiguous instruction-style guidance ('Read commits authored by the current git user email within that range'), but stops short of an executable command (e.g. a git log invocation with --author/--since/--no-merges), leaving a minor gap.	4 / 5
Workflow Clarity	The 5-step sequence (resolve window, read commits, exclude merges, synthesize, include actual date range) is clear and well-ordered for a read-only, non-destructive task, but there is no explicit checkpoint verifying the resolved window/author matches what the user intended, so it falls just short of the anchor-5 example.	4 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear Trigger/Workflow/Guardrails/Output sections — per the guideline, this earns a 5 for a short single-purpose skill with no bundle files.	5 / 5
	Total	18 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear, specific capability in third person without fluff, but it omits any explicit 'when to use' trigger guidance and lacks the natural vocabulary users would employ when asking for this kind of recap. Adding a trigger clause with synonyms would move it toward the strong examples.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a summary of what they got done, a status update, or a recap of their commits over a time range (yesterday, last week, sprint).'

Add natural user phrasings/synonyms such as 'what did I get done', 'standup update', 'weekly recap', or 'status update' to improve trigger term coverage.

Consider naming a second concrete capability (e.g. 'generates a short bulleted changelog of the user's own commits') to raise specificity beyond 1-2 actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('authored commits') and 1-2 concrete actions ('summarize... into a concise update') with concrete parameters ('user-specified time period'), but does not list several distinct specific actions, so it falls short of the anchor-4 example.	3 / 5
Completeness	The 'what' is clear (summarize authored commits over a time period into a concise update), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Relevant keywords like 'commits', 'summarize', and 'time period' are present, but common natural phrases users would say ('what did I get done', 'status update', 'standup', 'last week's work', 'changelog') are missing.	3 / 5
Distinctiveness Conflict Risk	The commit-summarization niche is mostly distinct with only minor overlap risk against closely related git skills (changelog generation, commit-message writing); trigger phrasing is not distinctive enough for a 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Path: cursor-team-kit/skills/what-did-i-get-done/SKILL.md
Commit: c47b128

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.