CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-security

Use when reviewing a branch diff for security concerns — auth, tokens and sessions, injection, secrets, cookies, CSP and third-party content — and reporting findings with S-C/H/M/L IDs in the four-field format.

72

Quality

90%

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

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.

A well-engineered procedural skill: the report-skeleton-first design, mid-run shape validation, grep-based section routing, and forced sibling-verb comparison are concrete and executable, and the reference split matches the actual bundle. The only weakness is mild repetition of the shape-check and comment-is-a-claim rationales across sections, which costs tokens without adding new instruction.

DimensionReasoningScore

Conciseness

The body is dense, repo-specific procedure with no padding that teaches concepts Claude already knows — commands, routing tables, and checklists dominate. Minor over-explanation remains: the shape-check rationale is repeated across Step 0, Step 2, and the final section, and the 'comment is a claim, not a control' rule is stated twice (Step 2 and again under JWT verification), which could be trimmed.

4 / 5

Actionability

Fully executable throughout: a verbatim heredoc for the report skeleton, exact git commands for base-branch resolution, a grep routing table mapping patterns to mandatory sections, a checkable shape invariant (grep -c must print 4), an exact finding template, and stepwise procedures (list exports, group by resource, compare sibling verbs; tabulate JWT claims with required/pinned verdicts). Copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

A clear Step 0 → Step 1 → Step 2 → report sequence with explicit validation checkpoints: the shape check runs mid-run as soon as the first finding lands and again on the finished file, both commands are given, the expected count is pinned ('It must print 4'), and error recovery (restore headings, re-place the finding) plus resume semantics are spelled out. This is a batch/destructive-adjacent review task and the feedback loops are present.

5 / 5

Progressive Disclosure

The split is well judged: nine sections the routing rarely reaches live in references/checklists.md (verified present with matching headings) and compliance detail in references/compliance.md, each referenced one level deep with an explicit signal of what is inside and when to open it ('open the file whenever Step 1 routes to one of them'), while the two most-misapplied bullets are kept inline in the body.

5 / 5

Total

19

/

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 with an explicit 'Use when' trigger, concrete domain keywords, and a specific output format. Its main gap is that compliance review (C- findings, GDPR/CCPA checks), which occupies roughly a third of the skill body, is not mentioned at all, so the description undersells the skill's actual scope.

Suggestions

Add compliance to the description's domain list (e.g., 'security and compliance concerns — auth, cookies, injection, GDPR/CCPA compliance') so the description covers the C- findings half of the skill and matches users asking for a 'compliance review'.

Add one or two common synonyms such as 'vulnerabilities' or 'OWASP' to widen the natural trigger phrases users might say when they need this skill.

DimensionReasoningScore

Specificity

Names two concrete actions ('reviewing a branch diff for security concerns' and 'reporting findings with S-C/H/M/L IDs in the four-field format') plus a specific domain list (auth, tokens and sessions, injection, secrets, cookies, CSP, third-party content). Not 5 because the compliance-review half of the skill is entirely absent from the description; not 3 because it goes beyond 1-2 actions to specify the report format and ID scheme.

4 / 5

Completeness

Explicitly answers both: 'Use when reviewing a branch diff for security concerns' gives the when with concrete triggers, and 'reporting findings with S-C/H/M/L IDs in the four-field format' gives the what including the output artifact. Both are explicit and concrete, matching the anchor requiring clear what AND when with trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('security concerns', 'auth', 'cookies', 'injection', 'branch diff', 'secrets'). Not 5 because common synonyms like 'vulnerabilities', 'secure', 'OWASP', or 'threat' are missing, which leaves a few natural entry phrases uncovered.

4 / 5

Distinctiveness Conflict Risk

Clear niche (security review of a branch diff) with domain-specific triggers that a generic code-review skill would not claim. Not 5 because the phrase 'reviewing a branch diff' overlaps with general code-review skills and only the 'security concerns' qualifier separates them, leaving minor conflict risk with closely related review skills.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

englishstreetventures/osn

Path

.claude/skills/review-security/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.