CtrlK
BlogDocsLog inGet started
Tessl Logo

strict-api

Use when the user says 'no hallucinations', 'verify APIs', 'reality check', or 'don't invent functions'. Prevents the agent from calling methods, imports, or variables that do not provably exist in the user's installed version.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering/strict-api/SKILL.md

The canonical home for this skill is strict-api in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a focused, well-organized single-rule skill with concrete examples and an actionable workflow. Its weakness is mild rhetorical padding in the opening and closing prose that does not add instructional value.

DimensionReasoningScore

Conciseness

The body is mostly lean with concrete, earning examples (made-up method names, framework-twin pairs) that justify their tokens, but retains some editorializing ("confident garbage", "One comment costs nothing. A silent wrong call costs an hour") that could be trimmed, so it sits at anchor 4 rather than 5.

4 / 5

Actionability

Provides concrete, executable guidance — an inline-comment annotation pattern with a real snippet (fs.openAsBlob), a verbatim user-question prompt, and a what-to-do-instead anti-pattern table — with only minor gaps versus fully copy-paste-ready programs.

4 / 5

Workflow Clarity

The four-step workflow (identify, verify, flag, prefer verbose-correct) is a clear sequence with an implicit checkpoint (ask once if no version stated), and the single-rule nature fits the simple-skill exception; it lacks an explicit validate-then-fix feedback loop, keeping it at 4.

4 / 5

Progressive Disclosure

A self-contained, single-purpose skill with no bundle files and clean sectioning (Overview, The Only Rule, What This Blocks, Workflow, Anti-Patterns, Cross-References); the simple-skill exception allows 5 for well-organized sections with no need for external references.

5 / 5

Total

17

/

20

Passed

Description

78%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 is well-constructed: third-person voice, an explicit Use-when trigger clause with natural phrasing, and a clear statement of what it prevents. Its main limitation is that the "what" is a single preventive action rather than a list of several distinct capabilities.

DimensionReasoningScore

Specificity

Names the domain and concrete objects ("calling methods, imports, or variables that do not provably exist") but is essentially a single preventive action rather than a list of several specific actions, so it sits at the anchor-3 level rather than 4.

3 / 5

Completeness

Explicitly answers both questions with a concrete "Use when the user says..." trigger clause and a clear "Prevents the agent from calling..." what clause, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Four natural trigger phrases users would actually say ("no hallucinations", "verify APIs", "reality check", "don't invent functions") give good keyword coverage, just short of the comprehensive synonym/file-extension variety of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The triggers carve a clear API-verification niche, but the goal overlaps with closely related hallucination-prevention skills (acknowledged in the body's cross-references), so minor overlap risk keeps it at 4 rather than 5.

4 / 5

Total

16

/

20

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
alirezarezvani/claude-skills
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.