CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

post-implementation-review

Review the combined implementation for correctness, clear ownership, and unnecessary complexity. Use when finishing substantial code implementation or refactoring, reviewing changes across callers or public APIs, or asked for a second pass or final sweep. Small edits need proportionate checks; independent architectural review belongs to adversarial-review.

Quality

88%

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

88%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.

An unusually disciplined instruction-only skill: lean token-efficient guidance, a clearly sequenced review workflow with explicit verification loops, and well-signaled deferral of deep method detail to one-level-deep references. The only soft spots are a handful of deliberative directives and inspection bullets whose detail borders on inline reference material.

DimensionReasoningScore

Conciseness

The body is dense, judgment-level guidance with no re-teaching of concepts Claude already knows and no padding — every line adds review criteria or decision rules ('Keep a boundary when it names non-obvious work, enforces a shared rule, owns a lifecycle...'). It assumes competence throughout, matching the lean anchor rather than the minor-over-explanation anchor at 4.

5 / 5

Actionability

Concrete, specific guidance throughout — exact staleness categories to search ('removed or renamed symbols and stale imports, exports, tests, and documentation'), baseline discipline, and a separate-checkout reproduction procedure. As an instruction-only skill no code is expected, but several directives remain deliberative rather than operational (e.g., 'replay the change as if designing it from scratch'), leaving minor gaps below the fully-executable anchor.

4 / 5

Workflow Clarity

A clear Scope → Inspect → Act → Verify → Output sequence with explicit validation checkpoints: 'After repairs, reread the affected code and callers and verify what changed' and a conditional re-check loop ('Repeat checks when a new edit, failure, or unresolved concern warrants it'). The Verify section's baseline discipline and uncertainty reporting matches the explicit-validation-with-feedback-loops anchor; this is a review skill, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

A single well-organized file whose deepest material is appropriately deferred to clearly signaled one-level-deep references (concept inventory, refactoring methods, typescript goto-definition hops, rethink escalation), each annotated with when to follow it. The four long inspection bullets carry borderline-inline method detail that could live in a reference, matching 'good structure, minor organization gaps' rather than the fully-split anchor at 5.

4 / 5

Total

18

/

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' clause carrying multiple natural triggers and active boundary disambiguation against sibling skills. Its only weaknesses are mild: slightly abstract capability wording and a few missing common synonyms for review requests.

DimensionReasoningScore

Specificity

The description names the domain and several concrete review actions — 'Review the combined implementation for correctness, clear ownership, and unnecessary complexity' plus 'reviewing changes across callers or public APIs' — with only minor abstraction ('clear ownership') leaving small coverage gaps. It falls just short of the comprehensive multi-action anchor at 5.

4 / 5

Completeness

It explicitly answers both: what ('Review the combined implementation for correctness, clear ownership, and unnecessary complexity') and when ('Use when finishing substantial code implementation or refactoring, reviewing changes across callers or public APIs, or asked for a second pass or final sweep') with concrete trigger phrases. The when-clause is explicit and multi-triggered, matching the top anchor rather than the 'could be more specific' anchor at 4.

5 / 5

Trigger Term Quality

Natural user phrasings like 'second pass', 'final sweep', 'reviewing changes', and 'finishing substantial code implementation or refactoring' match what users actually say. A few common synonyms ('code review', 'double-check', 'sanity check') are missing, keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

A clear post-implementation niche with active carve-outs ('independent architectural review belongs to adversarial-review', 'Small edits need proportionate checks') that disambiguate the nearest sibling. Minor overlap risk remains with generic review/diff-check skills for plain 'review my changes' requests, matching 'mostly distinct; minor overlap risk' rather than minimal conflict at 5.

4 / 5

Total

17

/

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

relative_links

Relative link issues: 5 suspicious

Warning

Total

15

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/post-implementation-review/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.