Tessl • The management layer for AI agent skills

SkillPublic

file-router

Unified file identification and routing for CCKnowledgeExtractor pipeline. Detects file types via magic bytes with extension fallback, returns processor skill to invoke. Use FIRST when processing any unknown file. Handles databases (sqlite, access), PDFs, images (png, jpg, gif, bmp, tiff), HTML, archives (zip, rar, 7z, tar), Office docs (docx, pptx, xlsx), and plain text.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%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 compact, highly actionable routing reference whose commands and routing table are concrete and verified against the real script. The main weakness is the absence of validation and error-path guidance (unknown types, low confidence, batch failures), which caps workflow clarity, plus a minor command-path inconsistency and some duplicated flag documentation.

Suggestions

Add validation guidance to the Pipeline Integration workflow: what to do when the router returns an unknown type, a low-confidence (extension-only) result, or a processor skill that does not exist before invoking step 3 — this also lifts the batch-operation cap on workflow clarity.

Fix the path inconsistency in Pipeline Integration ('python file_router.py input.file --json' vs 'python scripts/file_router.py') so every command is copy-paste ready.

Consolidate the flag documentation duplicated between Quick Start and CLI Reference (e.g., drop flag explanations from Quick Start) to trim tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows ('Quick Start', 'Routing Table', 'Detection Priority' are all tables or commands), but Quick Start and CLI Reference duplicate the same flags (--json, --dir, --list-types) and the human-readable output example partially repeats the JSON example.	4 / 5
Actionability	Commands are concrete and executable ('python scripts/file_router.py path/to/file --json') and the referenced script exists with a matching CLI, but Pipeline Integration uses 'python file_router.py input.file --json' without the 'scripts/' prefix used elsewhere, so that exact line is not copy-paste ready.	4 / 5
Workflow Clarity	The sequence is clear (route → jq-extract processor → invoke; detection priority 1-3) but no validation checkpoints exist: nothing on handling unknown/unrecognized file types, low-confidence extension-only results, or verifying batch (--dir/--recursive) output, and the rubric caps batch-operation workflows without validation at 3.	3 / 5
Progressive Disclosure	Well-organized sections with the single bundle file scripts/file_router.py existing and correctly referenced; all inline content (quick start, routing table, CLI reference) is appropriately placed at this size, so the structure matches the well-organized simple-skill case.	5 / 5
	Total	16 / 20 Passed

Description

82%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 that answers both what and when explicitly, uses third person, and covers natural trigger terms comprehensively with extensions and synonyms. Its only weaknesses are a narrow action set for specificity and a single, somewhat generic trigger condition plus minor overlap risk with the processor skills it routes to.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Detects file types via magic bytes with extension fallback, returns processor skill to invoke') plus a comprehensive enumeration of handled types, with minor gaps such as no mention of JSON output or batch directory mode. It exceeds the 1-2-action anchor but is not fully comprehensive on capabilities.	4 / 5
Completeness	Has a clear 'what' (detects types via magic bytes, returns processor skill) and an explicit 'when' ('Use FIRST when processing any unknown file'), so it is not capped at 3. The trigger is a single generic condition rather than the concrete trigger-phrase variations of the top anchor.	4 / 5
Trigger Term Quality	Comprehensive natural-term coverage including both synonyms and file extensions across the domain: 'databases (sqlite, access), PDFs, images (png, jpg, gif, bmp, tiff), HTML, archives (zip, rar, 7z, tar), Office docs (docx, pptx, xlsx), and plain text' — matching the anchor's standard of synonyms plus extensions.	5 / 5
Distinctiveness Conflict Risk	Clear niche as the entry-point router ('Use FIRST', 'returns processor skill to invoke') tied to a named pipeline, but it enumerates the same file types handled by the individual processor skills (pdf, image-ocr, archive-extractor), creating minor overlap risk with those closely related skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: KennethJefferson/cc_sdk_knowledge_extractor
Path: skills/file-router/SKILL.md
Revision: 6d9d92a

Reviewed: 5 days ago

Discovery Implementation Validation

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.

file-router

Table of Contents

Is this your skill?