CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

throttling-apis

Implement API throttling policies to protect backend services from overload. Use when controlling API request rates. Trigger with phrases like "throttle API", "control request rate", or "add throttling".

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/api-development/api-throttling-manager/skills/throttling-apis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-organized, appropriately lean overview: concrete instructions with real thresholds and status codes, a genuinely useful error-handling table, and clean one-level-deep references. The main gaps are the absence of any inline code, a missing validate-and-adjust feedback loop after load testing, and a referenced implementation guide that is generic boilerplate rather than throttling-specific content.

Suggestions

Add a short feedback loop after the load-test step, e.g. "If engagement thresholds are missed, adjust concurrency limits in throttle-config.js and re-run" — this would lift workflow clarity to the checkpoint-driven level.

Rewrite references/implementation.md to cover the throttling build (limiter, tier queue, breaker, adaptive controller) or point that link at references/examples.md, which already holds the relevant code.

Trim the Overview's second sentence (it duplicates the Instructions) and the Resources section to save tokens.

DimensionReasoningScore

Conciseness

The body is efficient: prerequisites, eight concrete instructions, an error table, and brief examples with no tutorials on concepts Claude already knows. Minor trimmable padding remains — the Overview's second sentence re-enumerates every mechanism the Instructions then repeat, and the Resources list of well-known pattern/library names adds little — so it fits anchor 4 rather than anchor 5's every-token-earns-its-place bar.

4 / 5

Actionability

Instructions are directive and parameterized with real specifics: "rejects new requests with 503 Service Unavailable", "5 failures in 10 seconds", `X-Throttle-Limit`/`X-Throttle-Remaining`/`X-Throttle-Reset` headers, and tier limits (100/25/5). It falls short of anchor 5 because no code or commands appear inline (executable code lives only in references/examples.md) and the referenced "full implementation guide" (references/implementation.md) is a generic API-building outline rather than throttling implementation detail, leaving a gap between promise and payload.

4 / 5

Workflow Clarity

The eight steps form a coherent build order — analyze endpoints, add limiter, priority tiers, circuit breaker, adaptive limits, headers, degradation, then "Write load tests that verify throttle engagement... and recovery behavior" as an explicit validation checkpoint. Anchor 5 is not met because there is no feedback loop (no guidance on adjusting thresholds when load tests fail) and validation appears only at the end rather than as checkpoints during construction.

4 / 5

Progressive Disclosure

The body is a genuine overview with three clearly signaled, one-level-deep markdown links ([`references/implementation.md`], [`references/errors.md`], [`references/examples.md`]), all of which exist as real files. Scored against the actual bundle, structure is good but not ideal: implementation.md is a thin, largely off-topic generic API guide rather than the promised throttling guide, and errors.md covers generic API errors (schema validation, auth) rather than the throttle errors in the body's table — anchor 4's "most content appropriately placed; minor organization gaps".

4 / 5

Total

16

/

20

Passed

Description

66%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 cleanly answers what the skill does and when to use it, with explicit, natural trigger phrases and third-person voice. Its weaknesses are a thin capability statement that undersells the skill's concrete mechanisms, and trigger coverage that omits the "rate limiting" synonym family, creating overlap risk with adjacent skills.

Suggestions

Expand the "what" clause to name the concrete mechanisms, e.g. "Implement API throttling policies — concurrency limits, tier-based priority queues, circuit breakers, and adaptive limits driven by backend latency — to protect services from overload."

Add "rate limiting" / "rate limit" / "return 429" to the trigger phrases, since users asking for rate limiting mean this skill's behavior.

State the framework scope or language-agnosticism if it matters (the body targets Express-style middleware), to further distinguish it from generic API-hardening skills.

DimensionReasoningScore

Specificity

"Implement API throttling policies to protect backend services from overload" names the domain and one concrete action with a goal, but does not enumerate the actual capabilities (concurrency limits, priority queues, circuit breakers, adaptive throttling) that the skill body delivers. This matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than anchor 4, which expects several specific actions.

3 / 5

Completeness

Both parts are present: a clear "what" ("Implement API throttling policies to protect backend services from overload") and an explicit "when" with trigger phrases ("Use when controlling API request rates... 'throttle API', 'control request rate', or 'add throttling'"). The "when" exceeds anchor 4's expectation, but the "what" is a single thin action with no capability detail, falling short of anchor 5's fully concrete what-and-when example.

4 / 5

Trigger Term Quality

Concrete trigger phrases are given: "throttle API", "control request rate", "add throttling", plus "Use when controlling API request rates". Coverage is good but misses the most common synonym users would say, "rate limiting"/"rate limit", so it does not reach anchor 5's comprehensive synonym coverage; it is clearly above anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The API-throttling niche is named, but every trigger term is a throttling variant while the closely adjacent "rate limiting" skill territory is unaddressed — a user asking to "add rate limiting" or "return 429s" would not be clearly routed here versus a generic rate-limit skill. This is anchor 3 (somewhat specific but could still overlap with similar skills) rather than anchor 4's minor-overlap profile.

3 / 5

Total

14

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/api-development/api-throttling-manager/skills/throttling-apis/SKILL.md

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.