CtrlK
BlogDocsLog inGet started
Tessl Logo

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs

56

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/regulatory-research-fallback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body lays out a clear, well-organized fallback workflow but is held back by redundant disclaimer text, placeholder rather than executable guidance, and implicit validation checkpoints. It is functional yet padded and indirect.

Suggestions

Consolidate the repeated verification/transparency disclaimers into a single canonical block referenced once instead of restating across Steps 4-5, Key Principles, and the Example Output.

Add an explicit validation checkpoint (e.g. 'confirm each requirement has a cited or best-effort source before drafting the checklist') between research and documentation.

Make the shell_agent and output templates concrete by replacing [TOPIC]/[Agency Name] placeholders with a worked end-to-end example, or extract the templates into a reference file to shorten SKILL.md.

DimensionReasoningScore

Conciseness

The verification/transparency message recurs across Step 4, Step 5, Key Principles (#3 and #5), the Example Output, and Source Transparency, adding redundant tokens; it is mostly efficient but could be tightened, fitting the level-2 anchor.

2 / 3

Actionability

It supplies output templates and a shell_agent prompt, but they are placeholder-filled ([TOPIC], [Agency Name], [state]) rather than executable code or commands, matching 'pseudocode instead of executable code; missing key details'.

2 / 3

Workflow Clarity

The five steps are clearly sequenced with a primary-to-fallback recovery loop, but validation checkpoints are implicit rather than explicit (no step verifies research adequacy before documenting), fitting 'sequence present but checkpoints missing or implicit'.

2 / 3

Progressive Disclosure

The skill is a single well-sectioned file with no nested references, but at ~125 lines the example output templates are inline content that could live in a separate reference file, matching 'some structure but content that should be separate is inline'.

2 / 3

Total

8

/

12

Passed

Description

75%

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 clearly conveys a distinct niche and an explicit use-when trigger, but its 'what' is abstract and its keywords lean technical. It is complete and distinctive yet light on concrete capability specifics.

Suggestions

Replace the abstract 'fallback workflow' phrasing with concrete outputs the skill produces, e.g. 'compiles compliance checklists and research notes'.

Add natural user-facing trigger terms such as 'compliance', 'regulations', or '.gov sites' alongside the technical 'web extraction tools fail' phrasing.

DimensionReasoningScore

Specificity

Names the domain ('regulatory research') and triggering scenario, but 'fallback workflow' is abstract with no concrete actions enumerated, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.

2 / 3

Completeness

It explicitly answers both what ('fallback workflow for regulatory research') and when ('when web extraction tools fail on government PDFs') with an explicit trigger clause, so the missing-trigger cap does not apply and it reaches the 'clearly answers both' anchor.

3 / 3

Trigger Term Quality

'regulatory research' and 'government PDFs' are natural-ish terms, but 'web extraction tools fail' is technical jargon and common variations like 'compliance' or 'regulations' are absent, fitting 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The regulatory-research-fallback niche with a tool-failure trigger is specific and unlikely to overlap with unrelated skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

10

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
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.