CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

multi-agent-coding

Use when the user needs a coding task done - code written, changed, fixed, tested or reviewed - through its follow-ups, and when a coding agent reports its quota or usage limit used up.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./raven/memory_engine/skills/multi-agent-coding/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is a tight, highly actionable policy document: it gives exact handles, a copy-paste dispatch prompt, explicit preconditions, and a fully specified quota-failover procedure. Its only weaknesses are minor wordiness and the absence of explicit outcome-verification checkpoints.

DimensionReasoningScore

Conciseness

Dense, purposeful prose that explains only non-obvious constraints ("one agent's `git stash` or `checkout` wipes the other's work") rather than concepts Claude already knows; a few long compound sentences and filler like "in whatever words or language" could be trimmed.

4 / 5

Actionability

Fully concrete for an instruction skill: copy-paste-ready dispatch prompt (the worktree blockquote), exact handles (`instance`, `node_id`, `{{ <node_id>.output_path }}`), a branch-name example, and specific graph actions (`replan`, not `continue`) covering the common cases of new task, follow-up, parallel work, and quota takeover.

5 / 5

Workflow Clarity

Rules are clearly sequenced with explicit gates ("Send a follow-up only once the instance's running dispatch has returned"; "ask the user before dispatching" when uncommitted changes matter) and a complete error-recovery loop for quota exhaustion, but there is no checklist-style verification of outcomes beyond instructing the agent to report them.

4 / 5

Progressive Disclosure

A single self-contained ~75-line policy file with numbered sections and working cross-references ("section 3", "section 5"); no external references exist, and none are needed — the structure makes navigation trivial.

5 / 5

Total

18

/

20

Passed

Description

48%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 trigger guidance is explicit and unusually rich, covering both initial coding requests and the distinctive quota-exhaustion scenario, but the description never says what the skill actually does, and the broad coding wording invites overlap with general coding skills.

Suggestions

State the 'what' explicitly, e.g. "Delegates coding tasks to sub-agent coding instances, routes follow-ups to the same instance, and hands the task to another agent when one reports its quota or usage limit used up."

Add natural trigger synonyms users would say: "fix a bug", "implement a feature", "write tests", "refactor", "out of credits", "hit the limit".

Narrow the coding trigger to delegation contexts (e.g. "when a coding task should go to a sub-agent") to reduce conflict with direct coding, testing, and review skills.

DimensionReasoningScore

Specificity

Names the coding domain and enumerates concrete task variants ("code written, changed, fixed, tested or reviewed", "quota or usage limit used up"), but never states what the skill itself does, so coverage of the skill's actions is not comprehensive.

3 / 5

Completeness

The description consists entirely of "Use when..." clauses: the 'when' is explicit and multi-part, but no 'what' — the skill's actual action (delegating coding work to sub-agents and failing over on quota exhaustion) is never stated.

2 / 5

Trigger Term Quality

Natural phrases users would say ("coding task", "code written, changed, fixed, tested or reviewed", "quota or usage limit used up") are present, though common synonyms like "fix bugs", "refactor", "implement", or "out of credits / hit the limit" are missing.

4 / 5

Distinctiveness Conflict Risk

"Code written, changed, fixed, tested or reviewed" overlaps with nearly any coding, test, or review skill, but the agent-quota-exhaustion trigger ("reports its quota or usage limit used up") is a distinct niche that reduces conflict risk.

3 / 5

Total

12

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

EverMind-AI/Raven

Path

raven/memory_engine/skills/multi-agent-coding/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.