CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-ops-router

Routes Claude Code: plugin/Skill repair, marketplace, statusline, model profiles/source sync, 1M/[1m] context, usage/quota reset ping, memory→docs, .txt repair, turning auto memory off. Reads one bundled specialist; history, hooks, and Lark keep their own entries.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary router skill: dense, operational, and free of padding, with exact file-level routing guidance, an explicit ambiguity stop condition, and clear boundary/exclusion rules. The body does exactly what a router should — decide which specialist to read and nothing more.

DimensionReasoningScore

Conciseness

The ~43-line body contains no concept explanations Claude already knows; every clause carries non-obvious operational knowledge ('Never anchor resolution to the task's working directory or a remembered plugin cache', 'Continue a truncated read', '`${CLAUDE_PLUGIN_ROOT}` may help in Claude Code, but it is absent in Codex'). Lean and efficient — every token earns its place.

5 / 5

Actionability

Concrete, executable guidance throughout: a routing table with exact sibling paths ('../claude-usage-analyst/SKILL.md'), a precise path-resolution procedure, and named disambiguation examples ('usage diagnosis selects `claude-usage-analyst`; a requested future reset ping selects `claude-code-ping-start-5h-quota`'). Fully actionable for an instruction-only skill.

5 / 5

Workflow Clarity

Clear sequence (locate this router → select the row → resolve and verify the sibling path → read the child in full → follow it) with an explicit validation checkpoint ('Stop if the active router path cannot be identified unambiguously') and a recovery rule for truncated reads. The single routing action is unambiguous and no destructive/batch cap applies.

5 / 5

Progressive Disclosure

Under 50 lines with no bundle files (no references/, scripts/, or assets/ exist), and the content is well organized into resolution, read-in-full, routing table, disambiguation, and exclusion sections. The router itself embodies progressive disclosure: one clearly signaled table points one level deep to the specialist SKILL.md to load.

5 / 5

Total

20

/

20

Passed

Description

71%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 is dense and highly specific, enumerating nearly every routed operation in telegraphic form, and it explicitly fences off adjacent domains. Its main weakness is the absence of an explicit 'Use when…' trigger clause, leaving the activation conditions only implied by the operation list.

Suggestions

Add an explicit 'Use when…' clause naming natural trigger situations (e.g., 'Use when the user asks to repair a Claude Code plugin or statusline, analyze usage or quota, or migrate Claude memory to documents'), which would raise completeness to the top anchor.

Replace compressed jargon like 'source sync' and 'memory→docs' with the natural phrases users say ('switch model providers', 'convert personal memory into AGENTS.md docs') to improve trigger term quality.

Include common variations users actually say — 'context window', 'early compaction', 'cost/cache analysis' — alongside the existing '[1m]' and '.txt' terms so the description matches more natural query phrasings.

DimensionReasoningScore

Specificity

It lists multiple concrete capabilities — 'plugin/Skill repair, marketplace, statusline, model profiles/source sync, 1M/[1m] context, usage/quota reset ping, memory→docs, .txt repair, turning auto memory off' — comprehensively covering the router's routing surface, matching the level-5 anchor rather than the 'minor gaps' level-4 anchor.

5 / 5

Completeness

The 'what' is clear ('Routes Claude Code… Reads one bundled specialist') but there is no 'Use when…' clause or equivalent explicit trigger guidance; the 'when' is only weakly implied by the enumerated operations, and the judging guidelines explicitly cap a missing 'Use when' clause at 3.

3 / 5

Trigger Term Quality

Good natural keyword coverage ('statusline', 'marketplace', 'quota reset ping', '[1m]', '.txt') that users would plausibly say, but compressed jargon ('source sync', 'memory→docs') and missing common variations ('context window', 'compaction', 'cost') fall short of the level-5 synonym-complete anchor.

4 / 5

Distinctiveness Conflict Risk

Mostly distinct — the explicit exclusion 'history, hooks, and Lark keep their own entries' delineates it from neighboring skills — but the broad 'Routes Claude Code' scope leaves minor overlap risk with other Claude Code skills, so it fits the level-4 anchor rather than the clear-niche level-5 anchor.

4 / 5

Total

16

/

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
daymade/claude-code-skills
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.