CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

common-review-policy

Define a repository review policy fixing what each review pass checks, how severities rank, which paths are skipped, the nit cap, and who approves. Use when review findings feel inconsistent or noisy, or when tuning an automated reviewer.

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 ./.agents/skills/common/common-review-policy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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-structured, actionable policy standard with excellent progressive disclosure and a clear tuning feedback loop. Its main weakness is token efficiency: the Anti-Patterns, Red Flags, and Canonical response anchors sections restate earlier rules rather than adding new content.

Suggestions

Merge the Anti-Patterns and Red Flags sections into the rules they restate (sections 3-6), keeping at most a one-line negative phrasing per rule, to cut roughly a third of the body's tokens.

Drop or compress the 'Canonical response anchors' section since every listed term (Blocker/Major/Nit, skip list, nit cap, needs validation, branch protection) already appears in the body's rules.

Add an explicit numbered drafting sequence (check for existing policy -> audit with template -> fill sections -> record in tuning log) to make the primary workflow as explicit as the tuning loop.

DimensionReasoningScore

Conciseness

Core sections are lean directive bullets with no known-concept padding, but the Anti-Patterns (6 items), Red Flags (3 items), and 'Canonical response anchors' sections systematically restate rules already stated in sections 3-6, occupying roughly a third of the body.

3 / 5

Actionability

Concrete, executable guidance throughout: exact file location, a passes table with explicit in/out-of-scope columns, severity definitions, glob-based skip lists, a monthly tuning procedure, and a verified template reference. Minor gaps remain, such as no example severity mapping or sample nit-cap value.

4 / 5

Workflow Clarity

Sections are logically sequenced and the tuning loop has an explicit validation checkpoint ('rate a sample of findings as useful or noise, then adjust cap, skip list, and pass scope') plus the 'needs validation' rule, but the drafting/audit sequence is implicit rather than explicitly stepped.

4 / 5

Progressive Disclosure

The body holds the standard while the copy-paste artifact lives in a real, verified one-level-deep reference (references/review-policy-template.md), clearly signaled both in section 1 and in a References section.

5 / 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 description that clearly states what the skill does and when to use it, with concrete enumerated capabilities and natural trigger phrases. Minor improvements are possible in action verb variety and synonym coverage for trigger terms.

DimensionReasoningScore

Specificity

Enumerates concrete deliverables ('what each review pass checks, how severities rank, which paths are skipped, the nit cap, and who approves') rather than vague language, but centers on a single action verb ('Define a repository review policy') with minor coverage gaps rather than multiple distinct actions.

4 / 5

Completeness

Explicitly answers both what ('Define a repository review policy fixing...') and when ('Use when review findings feel inconsistent or noisy, or when tuning an automated reviewer') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'review findings feel inconsistent or noisy' and 'tuning an automated reviewer' are natural user phrases with good coverage, though common variations like 'code review', 'PR review', and 'severity' are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche (defining a review policy, not performing reviews) with distinct terms like 'nit cap' and severity ranking, but 'review findings' could mildly overlap with a general code-review skill.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

HoangNguyen0403/agent-skills-standard

Path

.agents/skills/common/common-review-policy/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.