CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

77

Quality

96%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured policy skill: actionable guidance, an explicit verify-before-report checkpoint, and a fail-loud recovery path for budget cutoffs, with no padding and no unnecessary external references.

DimensionReasoningScore

Conciseness

Lean and well-sectioned with no padding of concepts Claude already knows; the runtime-budget rationale in "Why" is genuinely non-obvious domain context that earns its tokens, fitting the level-3 anchor.

3 / 3

Actionability

Concrete, specific instructions with example proof statements ("saved 12 of 12 panels (ids …)", "updated 5 rows") and a precise verify procedure; per the instruction-only scoring note, the absence of code is not penalized because the guidance is actionable.

3 / 3

Workflow Clarity

The "How" section gives a clear 5-step sequence with an explicit verification checkpoint (step 3, before reporting) and a fail-loud feedback loop for time-budget cutoffs (step 5), matching the anchor for sequenced steps with validation and error recovery.

3 / 3

Progressive Disclosure

A single self-contained SKILL.md (~62 lines) with well-organized Rule/Why/How/Don't/Related sections and only one-level cross-skill pointers; no bundle files exist and none are needed, so well-organized sections satisfy the level-3 simple-skill anchor.

3 / 3

Total

12

/

12

Passed

Description

92%

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 description with explicit what-and-when framing and concrete, natural-sounding trigger terms. Its main weakness is distinctiveness: the generic create/update/delete triggers risk overlapping with sibling data-skill triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "create, update, delete, or batch-write app data" — matching the anchor for enumerating several specific concrete verbs, not the level-2 single-domain example.

3 / 3

Completeness

Explicitly answers what ("perform writes so they actually persist under the hosted foreground run budget and long-running background handoffs") and when ("Use whenever you create, update, delete, or batch-write app data ..."), matching the what-AND-when anchor.

3 / 3

Trigger Term Quality

Natural trigger phrasings a user would say appear in "do this for many items" loops and "expects N things to end up saved", with good variation; not level 2 because it goes beyond a single keyword to several natural formulations.

3 / 3

Distinctiveness Conflict Risk

The reliable-persistence-under-budgets niche is fairly distinct, but the broad "create, update, delete app data" triggers overlap with the related `actions` and `storing-data` skills it itself cites, so it is not yet a clear, conflict-free niche.

2 / 3

Total

11

/

12

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
BuilderIO/agent-native
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.