CtrlK
BlogDocsLog inGet started
Tessl Logo

verification-planning

Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.

67

Quality

80%

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 ./src/skills/verification-planning/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%

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 clearly sequenced, well-organized six-step process with explicit completion checkpoints and no superfluous external references. Its main weaknesses are abstract conceptual framing and a lack of concrete worked examples that would make the guidance more immediately actionable.

Suggestions

Add one or two short worked examples showing what an evidence path looks like for a concrete change (e.g., a refactor or bug fix) to lift actionability from abstract to executable.

Tighten the philosophical framing in the opening ('The purpose is not to select a familiar technique...') into a single direct sentence to improve token efficiency.

Consider a compact template for stating a claim and its failure modes that an agent can fill in, turning the conceptual 'Frame the claim' guidance into a concrete artifact.

DimensionReasoningScore

Conciseness

The body is largely efficient and does not explain basics Claude already knows, but it includes abstract framing ('The purpose is not to select a familiar technique. The purpose is to decide how this system can reveal the truth of this particular change.') that could be tightened, keeping it at the mostly-efficient anchor rather than the leanest one.

2 / 3

Actionability

It gives some concrete guidance (explicit 'Complete when' exit criteria, an enumeration of system properties to derive paths from, and a concrete '@librarian' research trigger), but the steps are largely conceptual and lack worked examples or templates of an evidence path, so the guidance describes more than it makes immediately executable.

2 / 3

Workflow Clarity

The body presents a clearly sequenced six-step process (1-6) with an explicit 'Complete when:' validation checkpoint after each step, functioning as a checklist with gate criteria for a complex multi-phase process.

3 / 3

Progressive Disclosure

The skill is a single self-contained file with no need for external references, organized into clearly headed sections with no nested reference chains; per the rubric's note for skills with no need for external references, well-organized sections warrant the top anchor.

3 / 3

Total

10

/

12

Passed

Description

90%

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 well-formed description that clearly states what the skill does and when to use it, with natural trigger terms and a distinct niche. Its only weakness is that the stated capability is conceptual rather than a list of concrete operations, which keeps specificity at the middle anchor.

DimensionReasoningScore

Specificity

The description names the domain ('Verification planning') and several concrete change scenarios ('feature, bug fix, refactor, cross-system change'), but the core action ('build an evidence path') is conceptual rather than a list of concrete operations like 'extract, fill, merge', so it does not reach the multiple-specific-concrete-actions anchor.

2 / 3

Completeness

It explicitly answers both what ('Verification planning for non-trivial coding work that needs a credible project-specific evidence path') and when ('Use before implementing a feature, bug fix, refactor...'), with an explicit 'Use before' trigger clause.

3 / 3

Trigger Term Quality

The trigger clause 'Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change' uses natural developer terms a user would say when reaching for this skill, giving good coverage; 'evidence path' is skill jargon but the triggers carry the weight.

3 / 3

Distinctiveness Conflict Risk

The 'verification planning / evidence path' niche with explicit non-trivial-coding-work triggers is clearly distinct and unlikely to fire for unrelated skills; it avoids generic phrasing that would cause conflicts.

3 / 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
alvinunreal/oh-my-opencode-slim
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.