CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

math-router

Deterministic router for math cognitive stack - maps user intent to exact CLI commands

Quality

71%

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/math-router/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is a strong example of an executable skill: concrete commands, a realistic worked example with expected output, and an explicit fallback for unrecognized intents, all at a tight token budget. The only notable weaknesses are a small promotional section and an inline route catalog that could be split out. It matches the quality of the good overall examples.

DimensionReasoningScore

Conciseness

The body is lean and command-focused with almost no conceptual explanation, but the 'Why Use The Router' section ('Faster: No need to read skill docs', 'Deterministic: Pattern-based, not LLM inference') is promotional padding that could be trimmed — a minor instance of over-explanation, not the pervasive padding of the lower anchors.

4 / 5

Actionability

Fully executable, copy-paste-ready commands for routing and listing ('uv run python scripts/cc_math/math_router.py route "..."'), a worked end-to-end example with the exact expected JSON output, and an explicit fallback path — concrete examples cover the common cases with no gaps.

5 / 5

Workflow Clarity

The numbered example workflow (user request → run router → execute returned command → return result) is unambiguous for this single-action, non-destructive skill, and the Fallback section gives an explicit error-recovery branch when the router returns '{"command": null}'.

5 / 5

Progressive Disclosure

Sections are clearly organized with no nested references and no bundle files to navigate, but the ~61-line body inlines the 32-route catalog table — reference material that could live in a separate file — which constitutes a minor organization gap rather than fully appropriate placement.

4 / 5

Total

18

/

20

Passed

Description

42%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 states a clear and concrete 'what' but omits any 'when to use' guidance and carries almost no natural trigger keywords, deferring those to a separate frontmatter field. Jargon like 'cognitive stack' further separates it from the language users actually speak. It is serviceable but below the standard of the good examples, which combine enumerated actions with explicit trigger phrases.

Suggestions

Add a 'Use when...' clause to the description itself, e.g. 'Use when the user asks to calculate, solve, integrate, differentiate, plot, convert, or prove anything mathematical' — this fixes both the completeness cap and the missing trigger terms.

Replace internal jargon like 'cognitive stack' with user-facing language, and enumerate the routed capability categories (symbolic computation, unit conversion, geometry, proofs, plotting) so the description conveys breadth without over-claiming.

Clarify the router's relationship to the individual math skills it dispatches to (e.g. 'dispatches to sympy/z3/pint/shapely tools') to reduce conflict risk with those sibling skills.

DimensionReasoningScore

Specificity

"maps user intent to exact CLI commands" gives one concrete action within the math domain, but the description never enumerates the routed capabilities (integrate, solve, convert, prove), so coverage is not comprehensive — matching the '1-2 concrete actions' anchor rather than the several-action anchor.

3 / 5

Completeness

The 'what' is clear (deterministic intent-to-CLI-command mapping), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

The only natural user term in the description is "math"; the phrases users actually say (calculate, solve, integrate, plot, convert) sit in the separate 'triggers' frontmatter field, not the description itself, and "cognitive stack" is internal jargon users would never utter.

2 / 5

Distinctiveness Conflict Risk

"Deterministic router for math cognitive stack" carves a niche, but the router is intended to intercept every math request, overlapping with the individual skills it routes to, and the description does not articulate its relationship to those siblings — more than minor overlap risk.

3 / 5

Total

11

/

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

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 5 missing, 5 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/math-router/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.