case-review

Reviews a reverse-skill case package for scope readiness, Evidence to Finding to Path traceability, work item coverage, timeline references, and optional artifact hash integrity before report handoff.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/case-review/SKILL.md

Quality

Content

76%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.

The body is highly actionable and workflow-clear with executable commands, validation checkpoints, and a verified bundle script, losing points only on conciseness (repetitive next-step menus) and slightly imperfect reference signaling.

Suggestions

Collapse the four near-identical '建议下一步' five-option menus into a single reusable next-step block referenced once, to reclaim tokens.

Make the dependency on scripts/review_case.py an explicit, signaled reference (e.g. a 'Reference implementation' link) rather than only appearing inside command examples.

Trim the Bootstrap boundary and Routing context sections to the essential boundary statements, since they restate constraints already implied by the tool table.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands and tight phase structure, but the four repeated Chinese '建议下一步' five-option menus and the verbose bootstrap/routing sections add padding that could be trimmed, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	Every phase provides copy-paste-ready, fully executable commands (python3 scripts/review_case.py with --format/--strict/--verify-hashes) and a concrete PowerShell example, covering the common cases as the rubric's top anchor requires.	5 / 5
Workflow Clarity	Four clearly sequenced phases each have explicit validation/feedback loops ('resolve every error, then rerun', strict mode before handoff, hash mismatch as hard failure, self-check checklist), matching the 'explicit validation steps and feedback loops' top anchor.	5 / 5
Progressive Disclosure	Well-structured sections with the heavy logic correctly externalized to the real bundle file scripts/review_case.py and standard-library-only tooling; however navigation relies on cross-skill paths (../field-journal, ../tool-index) and inline menus rather than clearly signaled one-level-deep local references, leaving minor organization gaps versus the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

58%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.

The description is specific and third-person with concrete review actions, but it omits an explicit 'Use when...' trigger clause, capping completeness and leaving natural trigger terms under-covered.

Suggestions

Add an explicit trigger clause, e.g. 'Use when handing off or signing off on a reverse-engineering, forensics, or CTF case package before report generation.'

Surface natural user phrasing such as 'case review', 'handoff readiness', or 'evidence traceability check' so the skill matches how users actually ask.

Tighten the long noun chain 'Evidence to Finding to Path traceability' into scannable trigger keywords.

Dimension	Reasoning	Score
Specificity	Lists several concrete review actions (scope readiness, Evidence-to-Finding-to-Path traceability, work item coverage, timeline references, hash integrity) with only minor coverage gaps, fitting the 'several specific actions; minor gaps' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	The 'what' is clearly stated (reviews case package for several concrete properties before handoff) but there is no explicit 'Use when...' or equivalent trigger clause, which the guidelines cap at 3.	3 / 5
Trigger Term Quality	Contains domain-relevant terms (case package, Evidence, Finding, Path, traceability, hash integrity) but lacks the natural trigger phrases a user would say (e.g. 'case review', 'handoff readiness', 'evidence review'), missing common variations.	3 / 5
Distinctiveness Conflict Risk	The reverse-skill / forensics case-review niche with Evidence-Finding-Path traceability is fairly distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against adjacent report/forensics skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: zhaoxuya520/reverse-skill
Path: skills/case-review/SKILL.md
Commit: 7e2097f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.