CtrlK
BlogDocsLog inGet started
Tessl Logo

review

Use when reviewing a PR/MR by URL or the local working-tree diff — runs multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence) with confidence scoring and optional draft inline comments on the MR. Triggers for `/devflow:review` or any "review this PR/MR" request.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is review in AndreJorgeLopes/devflow

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-structured, highly actionable multi-phase review skill with clear sequencing and validation checkpoints, and effective progressive disclosure to sibling files. The only meaningful weakness is redundancy between the phase content and the closing 'Important rules' recap.

Suggestions

Prune the 'Important rules (do not skip)' section to only items not already stated in the phases, or convert it to a short pointer ('see Phase 1e for pagination, Phase 3 for the cross-check') to remove the recap redundancy.

Verify the referenced sibling files (AGENTS.md, TEMPLATES.md, requirements.json) ship alongside SKILL.md so the one-level-deep references resolve, since none are present in the current bundle directory.

DimensionReasoningScore

Conciseness

Lean for its complexity with no over-explanation of known concepts, but the closing 'Important rules (do not skip)' section recapitulates several points already covered in the phases (Source-of-Truth Hierarchy, never use local diffs, always paginate, never re-flag RAISED-RESOLVED-FIXED) and could be trimmed.

4 / 5

Actionability

Fully executable guidance — copy-paste gh/glab/git commands with real flags, exact paginated API endpoints, task-ID regexes, named MCP tools (mcp__5ebcd1ed-*__getJiraIssue), and concrete thresholds (50 lines, 100k chars, 100 threads).

5 / 5

Workflow Clarity

Clear Phase 0–6 sequence with explicit validation checkpoints (preflight STOP on missing required dep, NEW/RAISED-OPEN/RAISED-RESOLVED-FIXED/RAISED-RESOLVED-NOT-FIXED cross-check table, diff/thread caps) and feedback loops; the destructive step of posting comments is gated by AskUserQuestion.

5 / 5

Progressive Disclosure

The SKILL.md body is an overview that delegates detail via well-signaled, one-level-deep references — 'Read AGENTS.md (sibling to this SKILL.md) for the full agent definitions', 'Read TEMPLATES.md (sibling) for the full scoring rubric', and the sibling requirements.json — keeping the entry file navigable.

5 / 5

Total

19

/

20

Passed

Description

92%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, specific description that clearly conveys both the skill's purpose and its triggers. Minor improvement possible by adding full-form synonyms like 'code review', 'pull request', and 'merge request' for broader keyword coverage.

Suggestions

Add natural synonyms such as 'code review', 'pull request', and 'merge request' to broaden trigger-term coverage.

Consider trimming 'sibling MR/epic coherence' detail in the description to keep the capability list scannable.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence', 'confidence scoring', 'optional draft inline comments on the MR' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ('runs multi-perspective parallel agents… with confidence scoring and optional draft inline comments') and when ('Use when reviewing a PR/MR by URL or the local working-tree diff', 'Triggers for /devflow:review or any review this PR/MR request') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural triggers ('review this PR/MR', 'reviewing a PR/MR by URL', '/devflow:review') but misses common full-form synonyms like 'code review', 'pull request', or 'merge request'.

4 / 5

Distinctiveness Conflict Risk

Clear niche — multi-perspective PR/MR code review — with distinct triggers (/devflow:review, PR/MR URL, local working-tree diff) and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.