git-summary

Generates summaries of git activity in a repository.

Quality

55%

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 ./skill-arc-reactor-workspace/evals/files/git-summary/SKILL.md

Quality

Content

57%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 body is concise and cleanly sectioned into a simple 4-step workflow, but it is only partially actionable: the summarization step is vague and the referenced script is never wired into the steps. Additionally, the referenced reference/script files do not actually exist in the bundle, leaving navigation broken.

Suggestions

Add the concrete invocation for `scripts/format_summary.py` into the workflow (e.g. the exact command and where its output goes) so the script is actually used rather than only listed.

Specify Step 2's summarization expectations (what to include, length, grouping) so 'create a summary' becomes actionable guidance.

Either create the referenced `references/git-commands.md` and `scripts/format_summary.py` files, or remove the dangling references, so progressive-disclosure navigation resolves to real files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what git is); the only minor trim is the intro line 'This skill creates summaries of git repository activity' which restates the description, fitting the 'efficient; minor instances of over-explanation' anchor rather than the fully lean score-5 anchor.	4 / 5
Actionability	It provides one concrete executable command (`git log --oneline -20`) but Step 2 ('Read the output and create a summary') is vague and the referenced `scripts/format_summary.py` is never shown with an invocation, so key execution details are missing — matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	The four steps are clearly sequenced, but the script is referenced in a table without being integrated into the steps, and there is no checkpoint verifying the git log succeeded or the summary is well-formed, matching the 'steps listed but checkpoints missing or implicit' anchor rather than the fully-checkpointed score-4 anchor.	3 / 5
Progressive Disclosure	Sections are organized and references are signaled one level deep, but the referenced bundle paths (`references/git-commands.md`, `scripts/format_summary.py`) do not exist in the skill bundle, so navigation is broken — per the guideline to score against the actual bundle structure, this fits the 'some structure but references not reliably usable' band rather than a clean score-4.	3 / 5
	Total	13 / 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 purpose but is generic: it answers 'what' without any 'when' trigger guidance and offers only one action with limited keyword variation. It is reasonably distinct but would benefit from explicit use-when phrasing and more concrete actions.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks for a summary of recent commits, git activity, or repository history.'

List a couple more concrete actions (e.g. 'summarizes recent commits, highlights notable changes, groups activity by author') to lift specificity and completeness.

Include natural keyword variations users say ('commit history', 'git log', 'recent changes') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	"Generates summaries of git activity" names the domain (git) and one concrete action (generates summaries), but lists only a single action rather than comprehensive coverage, matching the anchor for '1-2 concrete actions, not comprehensive'.	3 / 5
Completeness	It gives a clear "what" (generates summaries of git activity) but provides no "when"/"Use when..." clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It includes the natural term "git" and "summaries", but misses common variations a user would say such as "commit history", "git log", or "recent changes", fitting the anchor for 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The git-activity-summary niche is mostly distinct with only minor overlap risk against closely related git skills (e.g. commit-message or diff skills), matching the 'mostly distinct; minor overlap risk' anchor rather than the broader score-3 anchor.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: endor-matt/Arc-Reactor-Skill-Evaluator
Path: skill-arc-reactor-workspace/evals/files/git-summary/SKILL.md
Commit: 95142b6

Reviewed: 1 day 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.