CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verified-state-change

Make scoped state changes with target confirmation, minimal mutation, and read-back verification

Quality

76%

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 ./resources/skills/agent/verified-state-change/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 lean, well-sequenced instruction set with explicit read-back verification, a repair loop, and a verification checklist — exactly the structure this safety-critical topic needs. The only gap is the absence of a worked example showing the procedure applied to a common case.

DimensionReasoningScore

Conciseness

Every line is directive ('Preserve fields the user did not ask to change'; 'Do not report success from an accepted request alone') with no padding and no explanation of concepts Claude already knows, matching the lean-and-efficient anchor.

5 / 5

Actionability

The steps give concrete, executable guidance ('capture the returned identifier, status, or revision'; 'repair only the specific mismatch') and code absence is not penalized for an instruction-only skill, but no worked examples cover common cases, so it stops short of fully copy-paste-ready guidance.

4 / 5

Workflow Clarity

The 6-step procedure has explicit validation (step 5 read-back through an independent operation) and a feedback loop (step 6 compare-and-repair), plus a verification checklist, satisfying the destructive-operation validation requirement.

5 / 5

Progressive Disclosure

The body is under 50 lines with no need for external references and is organized into clear sections (When to Use, Procedure, Pitfalls, Verification), qualifying for 5 under the simple-skill exception.

5 / 5

Total

19

/

20

Passed

Description

50%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 gives a clear, compact statement of what the skill does, but omits any trigger guidance and relies on technical vocabulary rather than the natural phrases a user would say when needing it. Adding a 'Use when...' clause with concrete trigger terms would lift most dimensions.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when creating, editing, deleting, or sending changes through an API, filesystem, or service.'

Include natural user-facing terms and synonyms (edit, update, create, delete, move, schedule) alongside the technical vocabulary so the description matches how users phrase requests.

Mention the concrete artifacts involved (files, records, accounts, messages) to sharpen distinctiveness from general-purpose skills.

DimensionReasoningScore

Specificity

The description names concrete practices ('target confirmation, minimal mutation, and read-back verification') but the headline 'Make scoped state changes' is generic, matching the anchor for a domain plus only a couple of concrete actions rather than several specific actions with minor gaps.

3 / 5

Completeness

The 'what' is clear (scoped state changes with confirmation, minimal mutation, and read-back verification), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Terms like 'state changes', 'mutation', and 'verification' are relevant but technical; the natural phrases users would actually say ('edit', 'update', 'delete', 'create') and their variations are missing, fitting the anchor for some relevant keywords but missing common synonyms.

3 / 5

Distinctiveness Conflict Risk

The verification and minimal-mutation framing is a recognizable niche, but it applies to nearly every mutation operation (file edits, API calls, messaging), leaving overlap risk with many related skills rather than only minor overlap with closely related ones.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

odysseus-dev/odysseus

Path

resources/skills/agent/verified-state-change/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.