reliable-mutations

How the agent must perform writes so they actually persist under the hosted foreground run budget and long-running background handoffs. Use whenever you create, update, delete, or batch-write app data — especially "do this for many items" loops, or any task where the user expects N things to end up saved.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/reliable-mutations/SKILL.md

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.

A well-organized, actionable skill body that assumes Claude's competence and centers verification for a batch/destructive operation. Minor room to tighten How/Don't overlap and add an explicit fix-and-retry loop.

Suggestions

Add a short fix-and-retry loop after the verify step (e.g., on mismatch, re-issue the atomic call or report the partial state) to reach the top workflow_clarity anchor.

Trim overlap between the Don't section and How steps 2/4 to improve conciseness without losing the negative-guidance framing.

Dimension	Reasoning	Score
Conciseness	Lean and free of generic-concept padding; the Why section carries non-obvious run-budget context, with only minor redundancy between How and Don't sections.	4 / 5
Actionability	Instruction-only yet concrete — "pass the full batch in one call", "Re-read the data (a list/read action, a count query)", and example reports like "saved 12 of 12 panels (ids…)" give executable guidance.	4 / 5
Workflow Clarity	Five sequenced How-steps include an explicit verify checkpoint (step 3) and cutoff handling (step 5), but lack a fix-and-retry feedback loop, stopping just short of the top anchor.	4 / 5
Progressive Disclosure	Clean Rule/Why/How/Don't/Related structure with one-level-deep, clearly signaled pointers to sibling skills and a design doc; no bundle files to organize, so structure carries the score.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong, third-person description that clearly states both capability and explicit usage triggers with natural user language. Coverage of actions and triggers is comprehensive with only minor gaps.

Dimension	Reasoning	Score
Specificity	Names several concrete write actions — "create, update, delete, or batch-write app data" — giving actionable coverage with only minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ("perform writes so they actually persist") and when ("Use whenever you create, update, delete, or batch-write app data") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases such as "do this for many items", "N things to end up saved", and "create, update, delete", with only a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche around reliable write persistence; minor overlap risk with sibling skills like actions/storing-data but triggers are well-scoped.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: BuilderIO/agent-native
Path: .agents/skills/reliable-mutations/SKILL.md
Commit: d477ebc

Reviewed: ~17 hours ago

Table of Contents

Discovery Implementation Validation

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.