CtrlK
BlogDocsLog inGet started
Tessl Logo

specalign

Align spec files with implementation. Detects drift between spec and code, surfaces discrepancies, user decides whether to update spec or code. Use when both a spec file and its implementation are in context.

90

1.12x

Quality

87%

Does it follow best practices?

Impact

92%

1.12x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid description that clearly communicates its purpose and includes an explicit 'Use when' clause. The main weaknesses are moderate specificity about what types of drift it detects and limited trigger term coverage for natural user language variations.

Suggestions

Add more specific actions like 'compares function signatures, parameter types, return values' to increase specificity

Include natural language variations users might say: 'specification', 'out of sync', 'code doesn't match', 'sync spec with code'

DimensionReasoningScore

Specificity

Names the domain (spec files and implementation) and describes actions (detects drift, surfaces discrepancies), but lacks comprehensive detail about what specific types of drift or discrepancies it handles.

2 / 3

Completeness

Clearly answers both what (detects drift, surfaces discrepancies, user decides update direction) and when (when both a spec file and its implementation are in context) with an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

Includes relevant terms like 'spec file', 'implementation', 'drift', and 'discrepancies', but misses common variations users might say such as 'specification', 'out of sync', 'code doesn't match spec', or 'sync spec'.

2 / 3

Distinctiveness Conflict Risk

Has a clear niche focused specifically on spec-to-code alignment with distinct triggers; unlikely to conflict with general code review or documentation skills due to the specific 'spec file and implementation' context requirement.

3 / 3

Total

10

/

12

Passed

Implementation

100%

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

This is an excellent skill that demonstrates strong technical writing. It efficiently communicates a complex bidirectional alignment workflow with clear categorization of drift types, concrete output templates, and explicit validation steps. The separation of passive awareness principles from active workflow steps is particularly well-designed.

DimensionReasoningScore

Conciseness

The skill is lean and efficient, with no unnecessary explanations of concepts Claude already knows. Every section serves a clear purpose and the content is appropriately dense without padding.

3 / 3

Actionability

Provides concrete, specific guidance throughout: exact file patterns to search, table format for mapping, numbered drift IDs, specific output templates, and clear decision options. The workflow steps are copy-paste ready.

3 / 3

Workflow Clarity

Clear 6-step sequence with explicit validation checkpoints (run lint/typecheck after code changes, run unit tests if they exist). Includes decision points and feedback loops for handling discrepancies.

3 / 3

Progressive Disclosure

Well-structured with clear separation between always-active principles and explicit workflow steps. Content is appropriately organized with headers and the skill is self-contained at an appropriate length without needing external references.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
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.