commit-assisted-by

Add an `Assisted-by: <agent-name>/<model-id>` git trailer to commits made during an AI-assisted coding session. Trigger on any `git commit` activity visible in the session — either commits you make yourself, or commits the user makes outside your tool calls that surface in the conversation — even without an explicit request. Also trigger when the user explicitly asks to tag existing commits in a branch (e.g. "add assisted-by to commits in this branch").

Quality

85%

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

Quality

Content

92%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 a tight, highly actionable guide with executable commands in all three modes and strong validation checkpoints around destructive history rewrites. Only minor conciseness trims would move it from excellent to maximal.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with no padding about basic git/trailer concepts; a few sentences ('provides transparency about AI involvement', 'clean path and avoids amend noise') could be trimmed, keeping it at anchor 4 rather than 5.	4 / 5
Actionability	Every mode ships copy-paste-ready, executable commands (the `git commit --trailer` form, the `--amend --no-edit --trailer` form, the rebase `--exec` one-liner) with placeholder substitution flagged, matching anchor 5.	5 / 5
Workflow Clarity	Three modes are clearly sequenced with explicit validation checkpoints (safety-check before amend; show-plan-then-confirm, upstream rev-list check, merge-commit stop, conflict surfacing in Mode 3), satisfying the destructive/batch validation requirement and matching anchor 5.	5 / 5
Progressive Disclosure	The single bundle file `scripts/safety-check.sh` is referenced one level deep with clear path-resolution guidance, and the body is well-sectioned into modes and anti-patterns, matching anchor 5 for a skill of this size.	5 / 5
	Total	19 / 20 Passed

Description

77%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 clearly states a single concrete action and provides explicit, natural trigger guidance covering both self-made and external commits, giving strong completeness and distinctiveness. The only notable weakness is second-person voice, which triggers the rubric's specificity penalty.

Suggestions

Rewrite in third person (e.g., 'Adds an `Assisted-by:...` trailer to commits made during an AI-assisted session') to avoid the second-person voice penalty on specificity.

Consider enumerating a couple more natural trigger synonyms (e.g., 'attribute commits', 'mark AI-assisted commits') to push trigger term quality toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Add an `Assisted-by: <agent-name>/<model-id>` git trailer to commits'), which is anchor 3, but the description uses second person ('commits you make yourself', 'your tool calls') so the rubric's voice penalty reduces it by one to 2.	2 / 5
Completeness	Explicitly answers both what (add the Assisted-by trailer) and when ('Trigger on any git commit activity...', 'Also trigger when the user explicitly asks...') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('git commit activity', 'tag existing commits in a branch', 'add assisted-by to commits in this branch'), giving good coverage, but synonyms are not comprehensively enumerated so it stops short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Assisted-by trailer on commits) with distinct, specific triggers and minimal overlap with other skills, matching anchor 5.	5 / 5
	Total	16 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fluxcd/agent-skills
Path: internal/skills/commit-assisted-by/SKILL.md
Commit: 88fb00c

Reviewed: 3 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.