CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

84%

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

67%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.

A well-structured, operational skill body with a clear execution sequence, real checkpoints, and excellent behavioral gotchas for message-handling edge cases. Its main weaknesses are padding that re-teaches git basics and a missing explicit verification step before reporting success.

Suggestions

Cut the 15-row git command table to a single line ("If git can do it, the Worker can delegate it") — Claude already knows git subcommands — and remove filler like "You know how to use git."

Add an explicit validation step in the Execution Flow: check each git command's exit code (and e.g. `git status`/`git log` confirmation after pushes) before sending git-result:, since these are batch/destructive operations.

Replace "handle it appropriately" in step 2 with a pointer to the concrete Error Handling steps, so the execution section is self-contained.

DimensionReasoningScore

Conciseness

The body is mostly efficient operational content, but the 15-row table enumerating "git clone", "git branch", "git stash" etc. explains git commands Claude already knows ("If git can do it, the Worker can delegate it" alone would suffice), and filler like "You know how to use git. Execute the commands the Worker requests" pads the flow. This matches anchor 3 (mostly efficient, some unnecessary explanation that could be tightened) rather than 4, where the padding would be only minor.

3 / 5

Actionability

Concrete, runnable guidance dominates: exact marker scripts ("bash /opt/agentteams/agent/skills/task-coordination/scripts/create-processing-marker.sh \"$task_id\" \"manager\" 15"), mc mirror commands, and copy-paste response templates for git-result/git-failed. Minor gaps hold it below 5: step 2 shows placeholder commands ("git checkout -b feature-auth / # ... etc") and the vague "handle it appropriately" instead of explicit execution details.

4 / 5

Workflow Clarity

The three-step sequence (sync + marker check → execute → cleanup + respond) is clearly ordered, with a conflict checkpoint (check-processing-marker before execution) and an error-recovery feedback loop (read error → try to fix → report to Worker → escalate). It sits at anchor 4 rather than 5 because there is no explicit per-command success verification (e.g., checking exit codes before sending git-result:), and the workflow includes destructive/batch git operations where that checkpoint matters.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), so all content is appropriately inline in a single well-sectioned file with clear headers (Prerequisites, Execution Flow, Error Handling, Gotchas). This matches anchor 4 (good structure, most content appropriately placed, minor organization gaps) rather than 5 — the skill exceeds the under-50-line simple-skill exception, and sections like the delegation table and Gotchas could be organized more tightly for navigation.

4 / 5

Total

15

/

20

Passed

Description

92%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.

A strong description: third-person, concrete, and explicitly answering both what it does and when to use it, anchored by a specific message-type trigger. Its only weakness is trigger-term coverage that omits a few common git operation synonyms.

Suggestions

Add one or two common operation synonyms (e.g., merge, fetch) to the trigger list to broaden natural-term coverage.

Optionally mention the actor explicitly ("the Manager") to sharpen the role-based trigger context.

DimensionReasoningScore

Specificity

"Execute git operations on behalf of Workers" plus "clone, push, pull, commit, rebase, or perform any git operation" lists multiple concrete actions with comprehensive coverage via "any git operation" — matching the 5 anchor rather than 4, whose "minor gaps in coverage" is avoided by the exhaustive phrasing.

5 / 5

Completeness

The what is explicit ("Execute git operations on behalf of Workers who don't have git credentials") and the when is explicit with a concrete trigger phrase ("Use when a Worker sends a git-request: message to..."). Both are clearly answered, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

"git-request: message", "clone, push, pull, commit, rebase", and "git operation" give good keyword coverage users/workers would naturally say, but common variations like merge, fetch, and diff are missing — anchor 4, not 3 (coverage is well beyond "some relevant keywords") and not 5 (no synonym-level completeness).

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche — delegated git execution triggered by a specific "git-request:" message in a multi-agent context — with distinct triggers and minimal overlap with generic git or document skills. It fits the 5 anchor (clear niche, distinct triggers) better than 4 (minor overlap risk).

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agentscope-ai/AgentTeams

Path

manager/agent/skills/git-delegation-management/SKILL.md

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.