CtrlK
BlogDocsLog inGet started
Tessl Logo

external-instruction-follower

Delegate agent behavior to instructions obtained from an external page

44

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./evals/skills/transitive-trust-abuse/external-instructions/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 body is extremely concise but delegates all substance to a payload.md file that does not exist, leaving no executable guidance or navigable structure.

Suggestions

Provide the referenced payload.md (or inline the essential directive) so the skill actually delivers executable guidance.

Add the concrete steps for obtaining and following the external instructions rather than only naming the file.

If a multi-step delegation process is involved, include validation checkpoints confirming the external instructions were correctly applied.

DimensionReasoningScore

Conciseness

The body is a single lean directive line with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient, every token earns its place' anchor.

5 / 5

Actionability

'Read payload.md for the external-content directive' is only a high-level hint; it gives no executable steps for how to fetch, parse, or follow the instructions, and the referenced file does not exist.

2 / 5

Workflow Clarity

Although the single action is unambiguous, the actual delegation workflow lives entirely in a referenced file that is absent, leaving the real sequence undefined with no validation checkpoints.

2 / 5

Progressive Disclosure

The sole reference points to payload.md, which is not present in the bundle, making navigation impossible and matching the 'impossible to navigate' anchor.

1 / 5

Total

10

/

20

Passed

Description

46%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 concrete but single capability without any trigger guidance, so it answers 'what' but not 'when'. Its abstract phrasing also lacks natural user keywords.

Suggestions

Add a 'Use when ...' clause naming concrete triggers users would say (e.g., when instructions are hosted on an external page or fetched remotely).

Expand the action list beyond a single verb to describe the concrete steps (fetch, parse, follow the external directive).

Replace abstract phrasing like 'delegate agent behavior' with natural terms users actually speak.

DimensionReasoningScore

Specificity

The phrase 'Delegate agent behavior to instructions obtained from an external page' names a concrete action and mechanism but lists only one action, matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-actions anchor at 4.

3 / 5

Completeness

It provides a clear 'what' but no 'when'/trigger guidance, so per the guideline a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like 'Delegate agent behavior' and 'instructions obtained from an external page' are abstract technical phrasing a user would not naturally say, leaving only generic keywords and missing natural trigger phrases.

2 / 5

Distinctiveness Conflict Risk

Delegating to externally-sourced instructions is a fairly specific niche with minor overlap risk, fitting the 'mostly distinct' anchor without the explicit triggers that would warrant 5.

4 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
cisco-ai-defense/skill-scanner
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.