CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-parallel-agents

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

Quality

78%

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 ./.claude/skills/skill-parallel-agents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers strongly on execution — every command is concrete, phases are sequenced with real validation gates, and troubleshooting provides feedback loops. However, it is severely bloated for a SKILL.md: the repeated plugin-root prefix, duplicated compliance warnings, and inlined reference material should be factored out, and the referenced orchestrate.sh script is not part of the bundle.

Suggestions

Define the plugin root path once (e.g., 'Run scripts/orchestrate.sh from the plugin root') and strip the ~30 repetitions of the full "${CLAUDE_PLUGIN_ROOT:-...}" prefix from every example, cutting hundreds of tokens.

Move the command reference, agent selection table, provider tier/configuration details, and routing flag examples into a references/ file (e.g., COMMANDS.md, PROVIDERS.md) linked one level deep from a concise overview, keeping SKILL.md to workflow guidance and quick-start examples.

Remove the duplicated 'When NOT to Use' and 'MANDATORY COMPLIANCE' sections that restate the frontmatter trigger block, and condense the 'Force Multi-Provider Mode' section, which repeats trigger examples already listed elsewhere.

DimensionReasoningScore

Conciseness

The body repeats the full "${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-${HOME}/.claude-octopus/plugin}}" prefix roughly thirty times, duplicates the frontmatter's when-not-to-use guidance in a 'MANDATORY COMPLIANCE' section, and pads with ASCII art and provider pricing tables — several clearly padded sections matching anchor 2 rather than merely 'could be tightened' (anchor 3).

2 / 5

Actionability

Commands are copy-paste ready with real arguments (probe/grasp/tangle/ink/embrace/grapple/squeeze examples), options tables with defaults, and even the placeholder pattern ("copy the path the probe phase printed") is explicitly explained, matching 'fully executable; copy-paste ready'.

5 / 5

Workflow Clarity

The Double Diamond phases are clearly sequenced with explicit validation checkpoints (prerequisites check routed on result, tangle quality gates with 75%/90% thresholds, preflight) and error-recovery feedback loops in the troubleshooting section, matching the top anchor; the batch-operation cap does not apply since validation steps are present.

5 / 5

Progressive Disclosure

Section headers and tables give it reasonable structure, but roughly 650 lines inline the full command reference, agent model tables, and provider configuration YAML that belong in separate reference files, and the bundle contains no references/ or scripts/ files at all despite the body pointing to scripts/orchestrate.sh — matching 'some structure; content that should be separate is inline'.

3 / 5

Total

15

/

20

Passed

Description

78%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 concise, well-structured description that clearly states both capability and trigger conditions with natural language users would plausibly say. Its main weakness is limited capability coverage — it names a single action and leans on use-case examples — and slightly broad trigger terms that could overlap with other refactoring or automation skills.

DimensionReasoningScore

Specificity

The description names the domain ("parallel agents") and one concrete action ("Decompose large tasks across parallel agents") but lists use cases rather than additional capabilities, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

It explicitly answers both what ("Decompose large tasks across parallel agents") and when ("use for migrations, multi-file refactors, or batch work") with concrete trigger phrases, matching the top anchor rather than anchor 4 where the when-clause is less specific.

5 / 5

Trigger Term Quality

"migrations", "multi-file refactors", and "batch work" are natural phrases users would say, but common variations like "parallelize", "fan out", or "spawn agents" are missing, matching 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

The parallel-agent orchestration niche is mostly distinct, but "migrations" and "batch work" are broad enough to overlap with generic refactoring or scripting skills, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

16

/

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

skill_md_line_count

SKILL.md is long (684 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

nyldn/claude-octopus

Path

.claude/skills/skill-parallel-agents/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.