fallback-doc-with-delegation

Generate professional documents after tool failures using shell_agent for complex formats or write_file for simple text/markdown

Quality

43%

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

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/write-file-fallback-report-enhanced/SKILL.md

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and self-contained but overly verbose with redundant tables and restated concepts; validation is implied rather than an explicit feedback loop and write_file examples lean on placeholders.

Suggestions

Collapse the redundant decision aids — the comparison table, decision checklist, and decision tree all restate the same shell_agent-vs-write_file split; keep one and remove the others to cut length.

Replace placeholder write_file templates ([Document Title], [Brief overview]) with a concrete filled-in example so guidance is copy-paste ready.

Make Step 6 an explicit validation feedback loop ('verify file exists; if missing or invalid, re-run and re-check') rather than marking verification as optional.

Dimension	Reasoning	Score
Conciseness	The 250-line body heavily restates concepts Claude already knows (what shell_agent does, advantages of delegation, repeated decision tables and checklists) and reproduces the same template/structure multiple times, padding the context with redundant material.	1 / 3
Actionability	It provides concrete shell_agent/write_file call examples and a full function, but the write_file examples use placeholder templates ([Document Title], [Brief overview...]) rather than copy-paste-ready executable content, leaving key details to be filled in.	2 / 3
Workflow Clarity	Steps 1-6 are clearly sequenced with a decision tree, but validation (Step 6) is described as optional/illustrative ('optionally verify') rather than an explicit validate-then-fix feedback loop, so checkpoints are present but implicit.	2 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the skill is a single self-contained workflow; the body is organized into well-labeled sections with no nested external references, satisfying the simple-skill carve-out for a 3.	3 / 3
	Total	8 / 12 Passed

Description

45%

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 specific about actions and tools but lacks natural user-facing trigger terms and an explicit 'Use when...' clause, capping completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when primary data-retrieval tools (read_file, search_web, execute_code_sandbox) fail and a document still needs to be produced.'

Include natural user-side terms like 'report', 'PDF', 'the tool errored', or 'fallback' so it triggers on how users actually phrase the need.

Reframe around the user's situation ('when a requested document can't be sourced normally') rather than internal tool names to reduce conflict with general document skills.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Generate professional documents') and specific tools (shell_agent, write_file) with a format split (complex vs simple text/markdown), listing multiple specific capabilities rather than vague language.	3 / 3
Completeness	It states clearly WHAT it does (generate documents via the two tools) but the WHEN is only implied via 'after tool failures' rather than an explicit 'Use when...' trigger clause, which per guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Triggers rely on internal tool names ('tool failures', 'shell_agent', 'write_file') that a user would not naturally say; it lacks the natural user phrasing (e.g. 'generate a report', 'PDF', 'the tool broke') that anchors this level.	1 / 3
Distinctiveness Conflict Risk	The fallback/delegation niche is somewhat specific, but 'generate professional documents' is broad and could overlap with general document-generation skills unless the tool-failure context is present.	2 / 3
	Total	8 / 12 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: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/write-file-fallback-report-enhanced/SKILL.md
Commit: c5a9c4b

Reviewed: 2 days ago

Table of Contents

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.