CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

idempotent-redundancy

Idempotent Redundancy

Quality

56%

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 ./.claude/skills/idempotent-redundancy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 concise, well-organized DO/DON'T pattern for a simple principle skill, with mostly concrete directives. Its main weaknesses are the source-session filler, unexplained tool-specific references (Braintrust, `_is_merge`), and goal-styled bullets without examples of the check-then-write or atomic-rename patterns.

Suggestions

Replace abstract bullets like "Make reconciliation steps safe to run repeatedly" with concrete tactics (e.g. a check-then-write snippet or a guard clause example).

Cut the "Source Sessions" section — it restates the title without adding actionable guidance.

Add one-line context or a link for the Braintrust-specific bullet so `_is_merge: true` is usable outside that ecosystem.

DimensionReasoningScore

Conciseness

The body is lean with no over-explanation of concepts Claude already knows, matching anchor 4 ("efficient; minor instances that could be trimmed"). The "Source Sessions" section ("a541f08a: 'Redundancy is good only if idempotent'") merely restates the title and could be cut, which keeps it below anchor 5 ("every token earns its place").

4 / 5

Actionability

Several bullets are concrete directives ("Check if value exists before writing (fallback only if missing)", "Use atomic write/rename for file operations", "Use `_is_merge: true` for Braintrust updates"), but others are goals rather than instructions ("Make reconciliation steps safe to run repeatedly", "Allow multiple writers to overwrite each other"), and no example shows the check-then-write or atomic-rename pattern. This matches anchor 3 ("concrete guidance but incomplete; missing key details") — not 4, because the Braintrust reference is unexplained and the abstract bullets lack executable specifics.

3 / 5

Workflow Clarity

This is a single-purpose principle skill with an unambiguous core directive ("When adding redundant paths (fallbacks, belt-and-suspenders), make them idempotent") organized in clear DO/DON'T sections, qualifying for the simple-skill exception. It scores 4 rather than 5 because the unexplained Braintrust-specific bullet ("Use `_is_merge: true` for Braintrust updates") introduces a minor gap in when/how applicability without any sequencing or checkpoint to clarify it.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and uses well-organized sections (Pattern, DO, DON'T, Source Sessions). Per the guideline for simple skills, this matches the 5 anchor condition — clear structure, no buried references, nothing that should be split out.

5 / 5

Total

16

/

20

Passed

Description

20%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 merely a title, not a description: it names a concept but states no capabilities and gives no usage triggers. It fails the core requirements of a skill description — what the skill does and when to invoke it. The body content is far stronger than the frontmatter suggests.

Suggestions

State concrete capabilities in third person, e.g. "Applies idempotency rules when adding redundant paths such as fallbacks, retries, and belt-and-suspenders logic."

Add an explicit trigger clause, e.g. "Use when adding fallback paths, duplicate writes, retry/repair logic, or reconciliation steps that may run more than once."

Include natural user vocabulary (fallback, retry, duplicate writes, repair hooks) so the skill triggers on the phrases users actually say.

DimensionReasoningScore

Specificity

The description is only the phrase "Idempotent Redundancy" — it names a domain concept but lists zero concrete actions or capabilities, falling between anchor 1 ("no concrete actions; pure abstract language") and anchor 2 ("names the domain but actions are minimal or generic"). It is not entirely generic, so it rises above 1, but with no verbs or actions at all it cannot reach 3.

2 / 5

Completeness

The description answers neither "what does this do" (only a topic label, no capability statement) nor "when should Claude use it" (no "Use when..." clause or equivalent). This matches anchor 1 ("missing both what and when, or both are extremely vague"); the missing trigger clause alone would cap this at 3.

1 / 5

Trigger Term Quality

Only two technical keywords ("Idempotent", "Redundancy") are present; the natural phrases a user would actually say — fallback, retry, duplicate writes, repair loop, belt-and-suspenders — are all missing. This matches anchor 2 ("one or two generic keywords; missing the natural phrases users say") better than anchor 3, since the terms lean toward jargon rather than natural user language.

2 / 5

Distinctiveness Conflict Risk

"Idempotent Redundancy" names a somewhat distinct niche concept, but with no trigger guidance it could fire on any mention of redundancy, retries, or idempotency. It fits anchor 3 ("somewhat specific but could still overlap with similar skills") — not 4 because no explicit triggers establish a clear niche, not 2 because the concept is more specific than a generic domain label.

3 / 5

Total

8

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/idempotent-redundancy/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.