CtrlK
BlogDocsLog inGet started
Tessl Logo

git-delegation-management

Execute git operations on behalf of Workers who don't have git credentials. Use when a Worker sends a git-request: message to clone, push, pull, commit, rebase, or perform any git operation.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced skill body with real validation checkpoints and error feedback loops; its main gaps are mild verbosity in the git-command reference table and a lack of any progressive disclosure into separate reference files.

Suggestions

Trim or move the "What Operations Can Be Delegated" command table to a reference file, since the "If git can do it, the Worker can delegate it" sentence plus a few examples already convey scope.

Consider extracting the detailed Gotchas list into a referenced file so the SKILL.md body stays a lean overview while edge cases remain discoverable one level deep.

DimensionReasoningScore

Conciseness

It is mostly efficient and explicitly assumes Claude's competence ("You know how to use git"), but the comprehensive git-command table under "What Operations Can Be Delegated" restates git verbs Claude already knows and could be trimmed, placing it at level 2 rather than the lean level 3.

2 / 3

Actionability

Provides copy-paste-ready bash with concrete paths, real referenced scripts (check-processing-marker.sh, create-processing-marker.sh, remove-processing-marker.sh), exact mc mirror commands, and complete message templates, matching the level-3 fully-executable anchor.

3 / 3

Workflow Clarity

A clear three-step sequence (sync + marker check → execute → cleanup + respond) with an explicit validation checkpoint (processing marker, $? check) and a read/fix/report/escalate feedback loop for failures, satisfying the level-3 anchor including for destructive git operations.

3 / 3

Progressive Disclosure

The body is well-organized into clear sections, but at ~167 lines it exceeds the under-50-line simple-skill exemption and keeps everything inline in one monolithic file (e.g., the command table and detailed Gotchas) rather than splitting to reference files, so it sits at level 2.

2 / 3

Total

10

/

12

Passed

Description

85%Weight 40%Scale 1-3

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

A strong, specific description with an explicit Use-when trigger and a clear niche; its only weakness is that the trigger mechanism relies on an internal message protocol rather than natural user phrasing.

Suggestions

Add a more user-natural trigger phrasing alongside the protocol trigger (e.g., "Use when the user or a Worker needs to run git commands") so it fires on plain language, not only the git-request: message format.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "clone, push, pull, commit, rebase, or perform any git operation" — which matches the level-3 anchor of multiple specific concrete actions, not level 2's partial list.

3 / 3

Completeness

Clearly answers both what ("Execute git operations on behalf of Workers who don't have git credentials") and when via an explicit "Use when..." clause, matching the level-3 anchor for both what AND when.

3 / 3

Trigger Term Quality

It names common git operation verbs (clone, push, pull, commit, rebase) but the actual trigger condition is a system-internal protocol ("a Worker sends a git-request: message") rather than language a user would naturally say, so it sits at level 2 with relevant-but-jargon-bound keywords.

2 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to delegated git execution triggered by a specific git-request: message protocol, making it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/AgentTeams
Reviewed

Table of Contents

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.